[2026-07-16 20:05:32.180 UTC] Starting pipeline: WGSA2, Current time: 2026-07-16 20:05
[2026-07-16 20:05:32.180 UTC] Pipeline version: 0.3.0, nephele_pipeline_utils version: 0.1.61
[2026-07-16 20:05:32.183 UTC] Pipeline arguments:
	--decontaminate_db_path /dbs/wgsa2/decontam_db/decontam_human+mouse_db
 	--kr2confidence_host 0.0
 	--classification_db_name plusPFV
 	--kr2confidence_taxonomic 0.15
 	--classification_db_path /dbs/wgsa2plus_lora/plus_PFV_Oct2025
 	--eggnog_db_path /dbs/wgsa2/eggnog_data
 	--annotations_type ko
 	--annotations_map_db_path /dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt
 	--annotations_hrr_db_path /dbs/lora/minpath_data/KEGGdb_0624/KEGGhrr_brite_0624.txt
 	--krona_tax_db_path /dbs/wgsa2/KronaTools_taxonomy
 	--find_args True
 	--args_db_path /dbs/wgsa2_plus/CARD_db-v4.0.1
 	--read_norm False
 	--readCoverage 50
 	--denovo_mtx True
 	--tax_genes True
 	--tax_scaffolds True
 	--mag False
 	--include_ted_files False
 	--trim_filter True
 	--average_read_quality 10
 	--min_read_length 60
 	--trim_of_5 20
 	--trim_of_3 15
 	--mapping_file_path /inputs/mapping_file.csv
 	--outputs_dir_path /outputs
[2026-07-16 20:05:32.184 UTC] Pipeline initialized with 3 samples
[2026-07-16 20:05:32.184 UTC] Samples ids: SRR12904817, SRR12904818, SRR12904821
[2026-07-16 20:05:32.184 UTC] Samples info:
[2026-07-16 20:05:32.184 UTC] {'#SampleID': 'SRR12904817', 'Description': 'SRR12904817', 'TreatmentGroup': '12 month', 'ForwardFastqFile': '/inputs/SRR12904817_1_2Msub.fastq.gz', 'ReverseFastqFile': '/inputs/SRR12904817_2_2Msub.fastq.gz'}
[2026-07-16 20:05:32.184 UTC] {'#SampleID': 'SRR12904818', 'Description': 'SRR12904818', 'TreatmentGroup': '12 month', 'ForwardFastqFile': '/inputs/SRR12904818_1_2Msub.fastq.gz', 'ReverseFastqFile': '/inputs/SRR12904818_2_2Msub.fastq.gz'}
[2026-07-16 20:05:32.184 UTC] {'#SampleID': 'SRR12904821', 'Description': 'SRR12904821', 'TreatmentGroup': '1 month', 'ForwardFastqFile': '/inputs/SRR12904821_1_2Msub.fastq.gz', 'ReverseFastqFile': '/inputs/SRR12904821_2_2Msub.fastq.gz'}
[2026-07-16 20:05:32.190 UTC] Starting WGSA pipeline...
[2026-07-16 20:05:32.190 UTC] Running command: bash -c snakemake -p --cores --nocolor --use-conda --rerun-incomplete --resources mem_gb=186 --keep-going --directory /outputs/tmp --latency-wait 10  --config num_cpus=48 map_file=/inputs/mapping_file.csv output_dir=/outputs total_mem_gb=186 tmp_dir=/outputs/tmp trim_filter=True include_ted_files=False ted_file_name=TEDfastq.tar biom_file_name=for_microbiomedb.biom decontaminate=/dbs/wgsa2/decontam_db/decontam_human+mouse_db kr2confidence_host=0.0 classification_db_name=plusPFV classification_db=/dbs/wgsa2plus_lora/plus_PFV_Oct2025 kr2confidence_taxonomic=0.15 find_args=True read_norm=False denovo_mtx=True eggnog_db=/dbs/wgsa2/eggnog_data annotations_type=ko annotations_map=/dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt annotations_hrr=/dbs/lora/minpath_data/KEGGdb_0624/KEGGhrr_brite_0624.txt tax_genes=True krona_tax_db=/dbs/wgsa2/KronaTools_taxonomy tax_scaffolds=True mag=False samples='{"SRR12904817": {"f": "/inputs/SRR12904817_1_2Msub.fastq.gz", "r": "/inputs/SRR12904817_2_2Msub.fastq.gz"}, "SRR12904818": {"f": "/inputs/SRR12904818_1_2Msub.fastq.gz", "r": "/inputs/SRR12904818_2_2Msub.fastq.gz"}, "SRR12904821": {"f": "/inputs/SRR12904821_1_2Msub.fastq.gz", "r": "/inputs/SRR12904821_2_2Msub.fastq.gz"}}' average_read_quality=10 min_read_length=60 trim_of_5=20 trim_of_3=15 args_db_path=/dbs/wgsa2_plus/CARD_db-v4.0.1
/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Building DAG of jobs...
Using shell: /usr/bin/bash
Provided cores: 48
Rules claiming more threads will be scaled down.
Provided resources: mem_gb=186
Job stats:
job                             count
----------------------------  -------
PWY_collation                       1
PWY_collation_biom                  1
PWY_diversity_plots                 1
TAX_collation                       1
TAX_collation_biom                  1
TAX_diversity_plots                 1
add_derep_stats                     3
all                                 1
bowtie2_build                       3
bowtie2_run                         3
copy_annotation_file                3
cp_geneTPM_files                    1
create_pathways_report              3
gene_annot_geneTPMs                 3
gene_annot_iTPMs                    3
gene_annot_seqExtract               3
gene_annotation                     3
gene_annotation_grep                3
gene_prediction                     3
generate_scaftax                    3
gff_to_gtf                          3
kreport2krona_import_text           1
kreport2krona_per_sample            3
krona_import_text                   1
kt_genetax_html                     1
kt_scaftax_html                     1
merge_ARGtabs                       1
pwy_biom_per_sample                 3
remove_rRNA                         3
rename_verse_summary                3
run_RGI                             3
run_bbtools_stats                   3
run_fastp                           3
run_genes2krona                     3
run_kraken2_classification          3
run_kraken2_decontaminate           3
run_min_path                        3
run_trinity                         3
run_verse                           3
samtools_to_bam                     3
scaffold_and_read_counts            3
tax_biom_per_sample                 3
tax_classification_genes            3
tax_classification_scaffolds        3
tax_genes_4krona                    3
tax_genes_ABUNtabtax                3
tax_scafs_4krona                    3
tpm_normalization                   3
total                             118


    set +o pipefail
    echo "Dependencies:"
    fastp --version
    metaspades.py --version
    bowtie2 --version | awk '{print "bowtie2 version", $3}' | head -n1
    samtools --version | head -n1
    metabat2 2>&1 >/dev/null | grep version
    prodigal -v 2>&1 >/dev/null | head -n2 | tail -n1
    conda list checkm -n checkm | tail -n1 | awk '{print $1,$2}'
    ktImportText | head -n2 | tail -n1 | sed 's/[^a-zA-Z0-9. ]//g' | sed 's/^ *//g'
    metaprokka --version
    cat /usr/local/src/MinPath/MinPath.py | grep version | head -n1
    verse -v | head -n2 | tail -n1
    kraken2 --version | head -n1
    conda list rgi -n rgi | tail -n1 | awk '{print $1, $2}'
    # rgi -h |grep "Resistance Gene Identifier - " | sed 's/ - / version /g'
    emapper.py --version | tail -n1 | awk '{print $1}'
    R --version | head -n1
    ribodetector_cpu --version | awk '{print "ribodetector version", $2}'
    Trinity --version | head -n1
    snakemake --version | awk '{print "Snakemake version", $1}'
    
Dependencies:
fastp 0.24.0
SPAdes genome assembler v4.0.0 [metaSPAdes mode]
bowtie2 version 2.5.4
samtools 1.21
MetaBAT: Metagenome Binning based on Abundance and Tetranucleotide frequency (version 2:2.17 (Bioconda); 2024-06-20T09:50:37)
Prodigal V2.6.3: February, 2016
checkm-genome 1.2.2
KronaTools 2.8.1  ktImportText 
Use of uninitialized value in subroutine entry at /opt/conda/bin/metaprokka line 236.
metaprokka 1.15.0
# MinPath (current version: 1.6)
VERSE v0.1.5
Kraken version 2.1.3
rgi 6.0.5
emapper-2.1.6
R version 4.3.3 (2024-02-29) -- "Angel Food Cake"
ribodetector version 0.3.2
Trinity version: Trinity-v2.15.1
Snakemake version 7.32.4
Select jobs to execute...

[Thu Jul 16 20:05:37 2026]
rule run_fastp:
    input: /inputs/SRR12904821_1_2Msub.fastq.gz, /inputs/SRR12904821_2_2Msub.fastq.gz
    output: /outputs/TEDreads_fqs/SRR12904821_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_te.fastq.gz, /outputs/TEDreads_mtx/SRR12904821_fastplog.html, /outputs/TEDreads_mtx/SRR12904821_fastp.json
    jobid: 16
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904821_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_te.fastq.gz
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp

[Thu Jul 16 20:05:37 2026]
rule run_fastp:
    input: /inputs/SRR12904818_1_2Msub.fastq.gz, /inputs/SRR12904818_2_2Msub.fastq.gz
    output: /outputs/TEDreads_fqs/SRR12904818_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_te.fastq.gz, /outputs/TEDreads_mtx/SRR12904818_fastplog.html, /outputs/TEDreads_mtx/SRR12904818_fastp.json
    jobid: 11
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904818_R2_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R1_te.fastq.gz
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp

[Thu Jul 16 20:05:37 2026]
rule run_fastp:
    input: /inputs/SRR12904817_1_2Msub.fastq.gz, /inputs/SRR12904817_2_2Msub.fastq.gz
    output: /outputs/TEDreads_fqs/SRR12904817_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R2_te.fastq.gz, /outputs/TEDreads_mtx/SRR12904817_fastplog.html, /outputs/TEDreads_mtx/SRR12904817_fastp.json
    jobid: 6
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904817_R2_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R1_te.fastq.gz
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp

/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Building DAG of jobs...
Building DAG of jobs...
Building DAG of jobs...
Using shell: /usr/bin/bash
Provided cores: 48
Using shell: /usr/bin/bash
Rules claiming more threads will be scaled down.
Provided cores: 48
Rules claiming more threads will be scaled down.
Select jobs to execute...
Select jobs to execute...
Using shell: /usr/bin/bash
Provided cores: 48
Rules claiming more threads will be scaled down.
Select jobs to execute...
fastp -i /inputs/SRR12904817_1_2Msub.fastq.gz -I /inputs/SRR12904817_2_2Msub.fastq.gz -o /outputs/TEDreads_fqs/SRR12904817_R1_te.fastq.gz -O /outputs/TEDreads_fqs/SRR12904817_R2_te.fastq.gz -h /outputs/TEDreads_mtx/SRR12904817_fastplog.html -j /outputs/TEDreads_mtx/SRR12904817_fastp.json                 --trim_poly_x --cut_window_size 4 --thread 16 --low_complexity_filter --correction --average_qual 10 --length_required 60 --cut_front                     --cut_front_mean_quality 20 --cut_tail  --cut_tail_mean_quality 15 2>> /outputs/TEDreads_mtx/SRR12904817_fastplog.txt
fastp -i /inputs/SRR12904818_1_2Msub.fastq.gz -I /inputs/SRR12904818_2_2Msub.fastq.gz -o /outputs/TEDreads_fqs/SRR12904818_R1_te.fastq.gz -O /outputs/TEDreads_fqs/SRR12904818_R2_te.fastq.gz -h /outputs/TEDreads_mtx/SRR12904818_fastplog.html -j /outputs/TEDreads_mtx/SRR12904818_fastp.json                 --trim_poly_x --cut_window_size 4 --thread 16 --low_complexity_filter --correction --average_qual 10 --length_required 60 --cut_front                     --cut_front_mean_quality 20 --cut_tail  --cut_tail_mean_quality 15 2>> /outputs/TEDreads_mtx/SRR12904818_fastplog.txt
fastp -i /inputs/SRR12904821_1_2Msub.fastq.gz -I /inputs/SRR12904821_2_2Msub.fastq.gz -o /outputs/TEDreads_fqs/SRR12904821_R1_te.fastq.gz -O /outputs/TEDreads_fqs/SRR12904821_R2_te.fastq.gz -h /outputs/TEDreads_mtx/SRR12904821_fastplog.html -j /outputs/TEDreads_mtx/SRR12904821_fastp.json                 --trim_poly_x --cut_window_size 4 --thread 16 --low_complexity_filter --correction --average_qual 10 --length_required 60 --cut_front                     --cut_front_mean_quality 20 --cut_tail  --cut_tail_mean_quality 15 2>> /outputs/TEDreads_mtx/SRR12904821_fastplog.txt
[Thu Jul 16 20:05:50 2026]
Finished job 11.
1 of 118 steps (1%) done
Removing temporary output /outputs/TEDreads_mtx/SRR12904818_fastp.json.
Select jobs to execute...

[Thu Jul 16 20:05:50 2026]
rule run_kraken2_decontaminate:
    input: /outputs/TEDreads_fqs/SRR12904818_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_te.fastq.gz
    output: /outputs/TEDreads_fqs/SRR12904818_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904818_R_2_ted.fastq, /outputs/TEDreads_mtx/SRR12904818_kr2_contamREPORT.txt, /outputs/TEDreads_mtx/SRR12904818_kr2_contamLOG.txt
    jobid: 10
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904818_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904818_R_2_ted.fastq; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904818_R2_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R1_te.fastq.gz
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --gzip-compressed --threads 16 --confidence 0.0 --db /dbs/wgsa2/decontam_db/decontam_human+mouse_db --paired /outputs/TEDreads_fqs/SRR12904818_R1_te.fastq.gz /outputs/TEDreads_fqs/SRR12904818_R2_te.fastq.gz --unclassified-out /outputs/TEDreads_fqs/SRR12904818_R#_ted.fastq --output -  --report /outputs/TEDreads_mtx/SRR12904818_kr2_contamREPORT.txt 2>> /outputs/TEDreads_mtx/SRR12904818_kr2_contamLOG.txt
[Thu Jul 16 20:05:50 2026]
Finished job 6.
2 of 118 steps (2%) done
Removing temporary output /outputs/TEDreads_mtx/SRR12904817_fastp.json.
Select jobs to execute...
[Thu Jul 16 20:05:50 2026]
Finished job 16.
3 of 118 steps (3%) done
Removing temporary output /outputs/TEDreads_mtx/SRR12904821_fastp.json.
[Thu Jul 16 20:06:03 2026]
Finished job 10.
4 of 118 steps (3%) done
Removing temporary output /outputs/TEDreads_fqs/SRR12904818_R2_te.fastq.gz.
Removing temporary output /outputs/TEDreads_fqs/SRR12904818_R1_te.fastq.gz.

[Thu Jul 16 20:06:03 2026]
rule remove_rRNA:
    input: /outputs/TEDreads_fqs/SRR12904818_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904818_R_2_ted.fastq
    output: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz
    jobid: 9
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904818_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904818_R_2_ted.fastq
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp


        ribodetector_cpu -t 16 -l 100 --chunk_size 3200 -e norrna         -i /outputs/TEDreads_fqs/SRR12904818_R_1_ted.fastq /outputs/TEDreads_fqs/SRR12904818_R_2_ted.fastq  --log /outputs/TEDreads_mtx/SRR12904818_rna_filter_LOG.txt         -o /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz 

        sed -i 's/\\[[0-9;]*m//g' /outputs/TEDreads_mtx/SRR12904818_rna_filter_LOG.txt

        line_count=$(pigz -dc -p 16 /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz | wc -l )
        if [ "$line_count" -lt 400 ]; then
            echo "ERROR: Fewer than 100 reads remain after rRNA filtering for SRR12904818, and reads are unlikely to assemble. 
            If this dataset is 16S rRNA amplicon reads, consider using our DADA2 or QIIME pipelines."
            exit
        fi
        

[Thu Jul 16 20:06:03 2026]
rule run_kraken2_decontaminate:
    input: /outputs/TEDreads_fqs/SRR12904817_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R2_te.fastq.gz
    output: /outputs/TEDreads_fqs/SRR12904817_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904817_R_2_ted.fastq, /outputs/TEDreads_mtx/SRR12904817_kr2_contamREPORT.txt, /outputs/TEDreads_mtx/SRR12904817_kr2_contamLOG.txt
    jobid: 5
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904817_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904817_R_2_ted.fastq; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904817_R2_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R1_te.fastq.gz
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --gzip-compressed --threads 16 --confidence 0.0 --db /dbs/wgsa2/decontam_db/decontam_human+mouse_db --paired /outputs/TEDreads_fqs/SRR12904817_R1_te.fastq.gz /outputs/TEDreads_fqs/SRR12904817_R2_te.fastq.gz --unclassified-out /outputs/TEDreads_fqs/SRR12904817_R#_ted.fastq --output -  --report /outputs/TEDreads_mtx/SRR12904817_kr2_contamREPORT.txt 2>> /outputs/TEDreads_mtx/SRR12904817_kr2_contamLOG.txt
2026-07-16 20:06:03 : INFO  Using high RECALL model
2026-07-16 20:06:03 : INFO  Log file: /outputs/TEDreads_mtx/SRR12904818_rna_filter_LOG.txt
2026-07-16 20:06:03 : INFO  Classify paired-end reads with chunk size [1m3200[0m
2026-07-16 20:06:03 : INFO  Writing output non-rRNA sequences into file: [94m/outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz[0m
[Thu Jul 16 20:06:37 2026]
Finished job 5.
5 of 118 steps (4%) done
Removing temporary output /outputs/TEDreads_fqs/SRR12904817_R2_te.fastq.gz.
Removing temporary output /outputs/TEDreads_fqs/SRR12904817_R1_te.fastq.gz.
Select jobs to execute...

[Thu Jul 16 20:06:38 2026]
rule run_kraken2_decontaminate:
    input: /outputs/TEDreads_fqs/SRR12904821_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_te.fastq.gz
    output: /outputs/TEDreads_fqs/SRR12904821_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904821_R_2_ted.fastq, /outputs/TEDreads_mtx/SRR12904821_kr2_contamREPORT.txt, /outputs/TEDreads_mtx/SRR12904821_kr2_contamLOG.txt
    jobid: 15
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904821_R_2_ted.fastq, /outputs/TEDreads_fqs/SRR12904821_R_1_ted.fastq; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904821_R1_te.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_te.fastq.gz
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --gzip-compressed --threads 16 --confidence 0.0 --db /dbs/wgsa2/decontam_db/decontam_human+mouse_db --paired /outputs/TEDreads_fqs/SRR12904821_R1_te.fastq.gz /outputs/TEDreads_fqs/SRR12904821_R2_te.fastq.gz --unclassified-out /outputs/TEDreads_fqs/SRR12904821_R#_ted.fastq --output -  --report /outputs/TEDreads_mtx/SRR12904821_kr2_contamREPORT.txt 2>> /outputs/TEDreads_mtx/SRR12904821_kr2_contamLOG.txt

[Thu Jul 16 20:06:38 2026]
rule remove_rRNA:
    input: /outputs/TEDreads_fqs/SRR12904817_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904817_R_2_ted.fastq
    output: /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz
    jobid: 4
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904817_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904817_R_2_ted.fastq
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp


        ribodetector_cpu -t 16 -l 100 --chunk_size 3200 -e norrna         -i /outputs/TEDreads_fqs/SRR12904817_R_1_ted.fastq /outputs/TEDreads_fqs/SRR12904817_R_2_ted.fastq  --log /outputs/TEDreads_mtx/SRR12904817_rna_filter_LOG.txt         -o /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz 

        sed -i 's/\\[[0-9;]*m//g' /outputs/TEDreads_mtx/SRR12904817_rna_filter_LOG.txt

        line_count=$(pigz -dc -p 16 /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz | wc -l )
        if [ "$line_count" -lt 400 ]; then
            echo "ERROR: Fewer than 100 reads remain after rRNA filtering for SRR12904817, and reads are unlikely to assemble. 
            If this dataset is 16S rRNA amplicon reads, consider using our DADA2 or QIIME pipelines."
            exit
        fi
        
2026-07-16 20:06:38 : INFO  Using high RECALL model
2026-07-16 20:06:38 : INFO  Log file: /outputs/TEDreads_mtx/SRR12904817_rna_filter_LOG.txt
2026-07-16 20:06:38 : INFO  Classify paired-end reads with chunk size [1m3200[0m
2026-07-16 20:06:38 : INFO  Writing output non-rRNA sequences into file: [94m/outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz[0m
[Thu Jul 16 20:06:55 2026]
Finished job 15.
6 of 118 steps (5%) done
Removing temporary output /outputs/TEDreads_fqs/SRR12904821_R1_te.fastq.gz.
Removing temporary output /outputs/TEDreads_fqs/SRR12904821_R2_te.fastq.gz.
Select jobs to execute...

[Thu Jul 16 20:06:55 2026]
rule remove_rRNA:
    input: /outputs/TEDreads_fqs/SRR12904821_R_1_ted.fastq, /outputs/TEDreads_fqs/SRR12904821_R_2_ted.fastq
    output: /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz
    jobid: 14
    reason: Missing output files: /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904821_R_2_ted.fastq, /outputs/TEDreads_fqs/SRR12904821_R_1_ted.fastq
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp


        ribodetector_cpu -t 16 -l 100 --chunk_size 3200 -e norrna         -i /outputs/TEDreads_fqs/SRR12904821_R_1_ted.fastq /outputs/TEDreads_fqs/SRR12904821_R_2_ted.fastq  --log /outputs/TEDreads_mtx/SRR12904821_rna_filter_LOG.txt         -o /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz 

        sed -i 's/\\[[0-9;]*m//g' /outputs/TEDreads_mtx/SRR12904821_rna_filter_LOG.txt

        line_count=$(pigz -dc -p 16 /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz | wc -l )
        if [ "$line_count" -lt 400 ]; then
            echo "ERROR: Fewer than 100 reads remain after rRNA filtering for SRR12904821, and reads are unlikely to assemble. 
            If this dataset is 16S rRNA amplicon reads, consider using our DADA2 or QIIME pipelines."
            exit
        fi
        
2026-07-16 20:06:56 : INFO  Using high RECALL model
2026-07-16 20:06:56 : INFO  Log file: /outputs/TEDreads_mtx/SRR12904821_rna_filter_LOG.txt
2026-07-16 20:06:56 : INFO  Classify paired-end reads with chunk size [1m3200[0m
2026-07-16 20:06:56 : INFO  Writing output non-rRNA sequences into file: [94m/outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz[0m
2026-07-16 20:12:59 : INFO  [92m1440580[0m sequences finished!
2026-07-16 20:12:59 : INFO  Processed [1m[96m1440580[0m sequences in total
2026-07-16 20:12:59 : INFO  Detected [1m[96m57124[0m non-rRNA sequences
2026-07-16 20:12:59 : INFO  Detected [1m[96m1383456[0m rRNA sequences
[Thu Jul 16 20:13:00 2026]
Finished job 4.
7 of 118 steps (6%) done
Removing temporary output /outputs/TEDreads_fqs/SRR12904817_R_1_ted.fastq.
Removing temporary output /outputs/TEDreads_fqs/SRR12904817_R_2_ted.fastq.
Select jobs to execute...

[Thu Jul 16 20:13:01 2026]
rule run_trinity:
    input: /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz
    output: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_contigs.fasta
    jobid: 22
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_contigs.fasta; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=62


        Trinity --seqType fq --left /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz --right /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz --CPU 12             --output /outputs/asmbMTX/SRR12904817_asmb/trinity_SRR12904817 --full_cleanup --max_memory 62G             --bflyHeapSpaceMax 20G --bflyCPU 2 &> /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_trinityLOG.txt
        mv /outputs/asmbMTX/SRR12904817_asmb/trinity_SRR12904817.Trinity.fasta /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_contigs.fasta
        rm /outputs/asmbMTX/SRR12904817_asmb/trinity_SRR12904817.Trinity.fasta.gene_trans_map
        
        line_count=$(wc -l < /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_contigs.fasta)
        if grep -q "No butterfly assemblies to report" /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_trinityLOG.txt || [ "$line_count" -lt 2 ] ; then
            echo "ERROR in sample SRR12904817: Trinity unable to assemble reads into transcripts."
            exit 1
        fi
        
2026-07-16 20:13:13 : INFO  [92m1870423[0m sequences finished!
2026-07-16 20:13:13 : INFO  Processed [1m[96m1870423[0m sequences in total
2026-07-16 20:13:13 : INFO  Detected [1m[96m187469[0m non-rRNA sequences
2026-07-16 20:13:13 : INFO  Detected [1m[96m1682954[0m rRNA sequences
[Thu Jul 16 20:13:14 2026]
Finished job 9.
8 of 118 steps (7%) done
Removing temporary output /outputs/TEDreads_fqs/SRR12904818_R_1_ted.fastq.
Removing temporary output /outputs/TEDreads_fqs/SRR12904818_R_2_ted.fastq.
Select jobs to execute...

[Thu Jul 16 20:13:14 2026]
rule run_trinity:
    input: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz
    output: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_contigs.fasta
    jobid: 28
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_contigs.fasta; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=62


        Trinity --seqType fq --left /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz --right /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz --CPU 12             --output /outputs/asmbMTX/SRR12904818_asmb/trinity_SRR12904818 --full_cleanup --max_memory 62G             --bflyHeapSpaceMax 20G --bflyCPU 2 &> /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_trinityLOG.txt
        mv /outputs/asmbMTX/SRR12904818_asmb/trinity_SRR12904818.Trinity.fasta /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_contigs.fasta
        rm /outputs/asmbMTX/SRR12904818_asmb/trinity_SRR12904818.Trinity.fasta.gene_trans_map
        
        line_count=$(wc -l < /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_contigs.fasta)
        if grep -q "No butterfly assemblies to report" /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_trinityLOG.txt || [ "$line_count" -lt 2 ] ; then
            echo "ERROR in sample SRR12904818: Trinity unable to assemble reads into transcripts."
            exit 1
        fi
        
2026-07-16 20:13:49 : INFO  [92m1839531[0m sequences finished!
2026-07-16 20:13:49 : INFO  Processed [1m[96m1839531[0m sequences in total
2026-07-16 20:13:49 : INFO  Detected [1m[96m98582[0m non-rRNA sequences
2026-07-16 20:13:49 : INFO  Detected [1m[96m1740949[0m rRNA sequences
[Thu Jul 16 20:13:50 2026]
Finished job 14.
9 of 118 steps (8%) done
Removing temporary output /outputs/TEDreads_fqs/SRR12904821_R_2_ted.fastq.
Removing temporary output /outputs/TEDreads_fqs/SRR12904821_R_1_ted.fastq.
Select jobs to execute...

[Thu Jul 16 20:13:50 2026]
rule run_trinity:
    input: /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz
    output: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_contigs.fasta
    jobid: 34
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_contigs.fasta; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=62


        Trinity --seqType fq --left /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz --right /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz --CPU 12             --output /outputs/asmbMTX/SRR12904821_asmb/trinity_SRR12904821 --full_cleanup --max_memory 62G             --bflyHeapSpaceMax 20G --bflyCPU 2 &> /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_trinityLOG.txt
        mv /outputs/asmbMTX/SRR12904821_asmb/trinity_SRR12904821.Trinity.fasta /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_contigs.fasta
        rm /outputs/asmbMTX/SRR12904821_asmb/trinity_SRR12904821.Trinity.fasta.gene_trans_map
        
        line_count=$(wc -l < /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_contigs.fasta)
        if grep -q "No butterfly assemblies to report" /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_trinityLOG.txt || [ "$line_count" -lt 2 ] ; then
            echo "ERROR in sample SRR12904821: Trinity unable to assemble reads into transcripts."
            exit 1
        fi
        
[Thu Jul 16 20:26:45 2026]
Finished job 22.
10 of 118 steps (8%) done
Select jobs to execute...

[Thu Jul 16 20:26:45 2026]
rule run_bbtools_stats:
    input: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_contigs.fasta
    output: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt
    jobid: 21
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_contigs.fasta
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

sed $'s/_cov_/ cov_/g' /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_contigs.fasta > /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta && stats.sh in=/outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta out=/outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt && printf "\nTEDreads mapping stats:\n"  >> /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt
[Thu Jul 16 20:26:46 2026]
Finished job 21.
11 of 118 steps (9%) done
Select jobs to execute...

[Thu Jul 16 20:26:46 2026]
rule bowtie2_build:
    input: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta
    output: /outputs/asmbMTX/SRR12904817_asmb/_bowtie2_build.done
    jobid: 20
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/_bowtie2_build.done; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp

bowtie2-build --quiet --threads 16 /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.db && touch /outputs/asmbMTX/SRR12904817_asmb/_bowtie2_build.done
[Thu Jul 16 20:26:47 2026]
Finished job 20.
12 of 118 steps (10%) done
Select jobs to execute...

[Thu Jul 16 20:26:47 2026]
rule bowtie2_run:
    input: /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904817_asmb/_bowtie2_build.done
    output: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.sam
    jobid: 19
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.sam; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904817_asmb/_bowtie2_build.done
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp

bowtie2 --phred33 --sensitive-local --no-unal --seed 4 -1 /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz -2 /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz -x /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.db -S /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.sam -p 16 2>> /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt
[Thu Jul 16 20:26:51 2026]
Finished job 19.
13 of 118 steps (11%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/_bowtie2_build.done.
Select jobs to execute...

[Thu Jul 16 20:26:51 2026]
rule samtools_to_bam:
    input: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.sam
    output: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_initial.bam, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_colated.bam, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixmate.bam, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixsrtd.bam, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_markdup.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam.bai
    jobid: 18
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_markdup.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.sam
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp

samtools sort /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.sam -o /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_initial.bam -@ 16 -T /outputs/tmpSRR12904817_srtfixd && samtools collate /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_initial.bam -o /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_colated.bam -@ 16 /outputs/tmpSRR12904817_collate && samtools fixmate -m /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_colated.bam /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixmate.bam -@ 16 && samtools sort /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixmate.bam -o /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixsrtd.bam -@ 16 -T /outputs/tmpSRR12904817_srtfixd && samtools markdup -r -s /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixsrtd.bam -f /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_markdup.txt /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam -@ 16 -T /outputs/tmpSRR12904817_markdup && samtools index -b /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam -@ 16
[bam_sort_core] merging from 0 files and 16 in-memory blocks...
[bam_sort_core] merging from 0 files and 16 in-memory blocks...
[Thu Jul 16 20:26:54 2026]
Finished job 18.
14 of 118 steps (12%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/SRR12904817.sam.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_initial.bam.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_colated.bam.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixmate.bam.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_fixsrtd.bam.
Select jobs to execute...

[Thu Jul 16 20:26:54 2026]
rule add_derep_stats:
    input: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_markdup.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/_added_derep_stats.done
    jobid: 108
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/_added_derep_stats.done; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_markdup.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

cat /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt <(printf "\nRead alignment de-replication stats:\n") /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_markdup.txt > /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_tmp_file.txt && mv /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_tmp_file.txt /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbStats.txt && touch /outputs/asmbMTX/SRR12904817_asmb/_added_derep_stats.done

[Thu Jul 16 20:26:54 2026]
rule scaffold_and_read_counts:
    input: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam
    output: /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt, /outputs/asmbMTX/SRR12904817_asmb/tmp_basecov.txt, /outputs/asmbMTX/SRR12904817_asmb/tmp_idx.txt, /outputs/asmbMTX/SRR12904817_asmb/tmp_readcount.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt, /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov1.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt
    jobid: 17
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp, mem_gb=46

pileup.sh -Xmx46g /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam out=/outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt overwrite=true && sort -o /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt && jgi_summarize_bam_contig_depths /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam --outputDepth /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt && sort /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt | sed '1 s/^/#/' | cut -f 1-3 > /outputs/asmbMTX/SRR12904817_asmb/tmp_basecov.txt && samtools idxstats /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam > /outputs/asmbMTX/SRR12904817_asmb/tmp_idx.txt && cut -f 1-3 /outputs/asmbMTX/SRR12904817_asmb/tmp_idx.txt | sed -e '1s/^/#contigName\tLength\tReadsCount\n/' | sort | grep -v "*" > /outputs/asmbMTX/SRR12904817_asmb/tmp_readcount.txt && paste /outputs/asmbMTX/SRR12904817_asmb/tmp_readcount.txt /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt /outputs/asmbMTX/SRR12904817_asmb/tmp_basecov.txt | cut -f 1,2,3,8-14,17 -d $'\t' > /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov1.txt && awk 'BEGIN{FS=OFS="\t"} NR>1 {if ($2>0 && $3>0) $12=sprintf("%0.2f", $3*1e3/$2); else $12=0; print}'  /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov1.txt | sed -e '1s/^/#NODE\tlen\tReads\t\%NodeCovered\t\%bpCovered\tplusReads\tminusReads\t\%GC\tMedFold\tstDev\tAveDepth\tRPK\n/' > /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt
[Thu Jul 16 20:26:54 2026]
Finished job 108.
15 of 118 steps (13%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_markdup.txt.
Select jobs to execute...
java -ea -Xmx46g -cp /opt/conda/opt/bbmap-39.15-0/current/ jgi.CoveragePileup -Xmx46g /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam out=/outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt overwrite=true
Executing jgi.CoveragePileup [-Xmx46g, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam, out=/outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt, overwrite=true]

Found samtools 1.21
Could not find sambamba.
Reads:                               	83380
Mapped reads:                        	83380
Mapped bases:                        	11209315
Ref scaffolds:                       	2844
Ref bases:                           	1447787

Percent mapped:                      	100.000
Percent proper pairs:                	96.608
Average coverage:                    	7.742
Average coverage with deletions:     	7.742
Standard deviation:                    	14.285
Percent scaffolds with any coverage: 	100.00
Percent of reference bases covered:  	99.55

Time: 	0.770 seconds.
Output depth matrix to /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt
jgi_summarize_bam_contig_depths 2.17 (Bioconda) 2024-06-20T09:50:37
Running with 1 threads to save memory you can reduce the number of threads with the OMP_NUM_THREADS variable
Output matrix to /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt
Opening all bam files and validating headers
Processing bam files with largest_contig=0
Thread 0 opening and reading the header for file: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam
Thread 0 opened the file: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam
Thread 0 processing bam 0: SRR12904817_asmbFinal.bam
Thread 0 finished reading bam 0: SRR12904817_asmbFinal.bam
Thread 0 finished: SRR12904817_asmbFinal.bam with 83380 reads and 81210 readsWellMapped (97.3975%)
Creating depth matrix file: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt
Closing last bam file
Finished
[Thu Jul 16 20:26:55 2026]
Finished job 17.
16 of 118 steps (14%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/tmp_basecov.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/tmp_idx.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/tmp_readcount.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/tmp_scafcov1.txt.
[Thu Jul 16 20:33:47 2026]
Finished job 28.
17 of 118 steps (14%) done

[Thu Jul 16 20:33:47 2026]
rule run_bbtools_stats:
    input: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_contigs.fasta
    output: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt
    jobid: 27
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_contigs.fasta
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

sed $'s/_cov_/ cov_/g' /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_contigs.fasta > /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta && stats.sh in=/outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta out=/outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt && printf "\nTEDreads mapping stats:\n"  >> /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt
[Thu Jul 16 20:33:48 2026]
Finished job 27.
18 of 118 steps (15%) done
Select jobs to execute...

[Thu Jul 16 20:33:48 2026]
rule bowtie2_build:
    input: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta
    output: /outputs/asmbMTX/SRR12904818_asmb/_bowtie2_build.done
    jobid: 26
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/_bowtie2_build.done; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp

bowtie2-build --quiet --threads 16 /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.db && touch /outputs/asmbMTX/SRR12904818_asmb/_bowtie2_build.done
[Thu Jul 16 20:33:51 2026]
Finished job 26.
19 of 118 steps (16%) done
Select jobs to execute...

[Thu Jul 16 20:33:51 2026]
rule bowtie2_run:
    input: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904818_asmb/_bowtie2_build.done
    output: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.sam
    jobid: 25
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.sam; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904818_asmb/_bowtie2_build.done, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp

bowtie2 --phred33 --sensitive-local --no-unal --seed 4 -1 /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz -2 /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz -x /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.db -S /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.sam -p 16 2>> /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt
[Thu Jul 16 20:34:07 2026]
Finished job 25.
20 of 118 steps (17%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/_bowtie2_build.done.
Select jobs to execute...

[Thu Jul 16 20:34:07 2026]
rule samtools_to_bam:
    input: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.sam
    output: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_initial.bam, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_colated.bam, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixmate.bam, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixsrtd.bam, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_markdup.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam.bai
    jobid: 24
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_markdup.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.sam
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp

samtools sort /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.sam -o /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_initial.bam -@ 16 -T /outputs/tmpSRR12904818_srtfixd && samtools collate /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_initial.bam -o /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_colated.bam -@ 16 /outputs/tmpSRR12904818_collate && samtools fixmate -m /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_colated.bam /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixmate.bam -@ 16 && samtools sort /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixmate.bam -o /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixsrtd.bam -@ 16 -T /outputs/tmpSRR12904818_srtfixd && samtools markdup -r -s /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixsrtd.bam -f /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_markdup.txt /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam -@ 16 -T /outputs/tmpSRR12904818_markdup && samtools index -b /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam -@ 16
[bam_sort_core] merging from 0 files and 16 in-memory blocks...
[bam_sort_core] merging from 0 files and 16 in-memory blocks...
[Thu Jul 16 20:34:11 2026]
Finished job 24.
21 of 118 steps (18%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/SRR12904818.sam.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_initial.bam.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_colated.bam.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixmate.bam.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_fixsrtd.bam.
Select jobs to execute...

[Thu Jul 16 20:34:11 2026]
rule add_derep_stats:
    input: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_markdup.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/_added_derep_stats.done
    jobid: 109
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/_added_derep_stats.done; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_markdup.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

cat /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt <(printf "\nRead alignment de-replication stats:\n") /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_markdup.txt > /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_tmp_file.txt && mv /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_tmp_file.txt /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbStats.txt && touch /outputs/asmbMTX/SRR12904818_asmb/_added_derep_stats.done

[Thu Jul 16 20:34:11 2026]
rule scaffold_and_read_counts:
    input: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam
    output: /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt, /outputs/asmbMTX/SRR12904818_asmb/tmp_basecov.txt, /outputs/asmbMTX/SRR12904818_asmb/tmp_idx.txt, /outputs/asmbMTX/SRR12904818_asmb/tmp_readcount.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt, /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov1.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt
    jobid: 23
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp, mem_gb=46

pileup.sh -Xmx46g /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam out=/outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt overwrite=true && sort -o /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt && jgi_summarize_bam_contig_depths /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam --outputDepth /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt && sort /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt | sed '1 s/^/#/' | cut -f 1-3 > /outputs/asmbMTX/SRR12904818_asmb/tmp_basecov.txt && samtools idxstats /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam > /outputs/asmbMTX/SRR12904818_asmb/tmp_idx.txt && cut -f 1-3 /outputs/asmbMTX/SRR12904818_asmb/tmp_idx.txt | sed -e '1s/^/#contigName\tLength\tReadsCount\n/' | sort | grep -v "*" > /outputs/asmbMTX/SRR12904818_asmb/tmp_readcount.txt && paste /outputs/asmbMTX/SRR12904818_asmb/tmp_readcount.txt /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt /outputs/asmbMTX/SRR12904818_asmb/tmp_basecov.txt | cut -f 1,2,3,8-14,17 -d $'\t' > /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov1.txt && awk 'BEGIN{FS=OFS="\t"} NR>1 {if ($2>0 && $3>0) $12=sprintf("%0.2f", $3*1e3/$2); else $12=0; print}'  /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov1.txt | sed -e '1s/^/#NODE\tlen\tReads\t\%NodeCovered\t\%bpCovered\tplusReads\tminusReads\t\%GC\tMedFold\tstDev\tAveDepth\tRPK\n/' > /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt
[Thu Jul 16 20:34:11 2026]
Finished job 109.
22 of 118 steps (19%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_markdup.txt.
Select jobs to execute...
java -ea -Xmx46g -cp /opt/conda/opt/bbmap-39.15-0/current/ jgi.CoveragePileup -Xmx46g /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam out=/outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt overwrite=true
Executing jgi.CoveragePileup [-Xmx46g, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam, out=/outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt, overwrite=true]

Found samtools 1.21
Could not find sambamba.
Reads:                               	323645
Mapped reads:                        	323645
Mapped bases:                        	44698882
Ref scaffolds:                       	4966
Ref bases:                           	2906776

Percent mapped:                      	100.000
Percent proper pairs:                	96.538
Average coverage:                    	15.377
Average coverage with deletions:     	15.378
Standard deviation:                    	74.076
Percent scaffolds with any coverage: 	100.00
Percent of reference bases covered:  	98.84

Time: 	0.776 seconds.
Output depth matrix to /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt
jgi_summarize_bam_contig_depths 2.17 (Bioconda) 2024-06-20T09:50:37
Running with 1 threads to save memory you can reduce the number of threads with the OMP_NUM_THREADS variable
Output matrix to /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt
Opening all bam files and validating headers
Processing bam files with largest_contig=0
Thread 0 opening and reading the header for file: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam
Thread 0 opened the file: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam
Thread 0 processing bam 0: SRR12904818_asmbFinal.bam
Thread 0 finished reading bam 0: SRR12904818_asmbFinal.bam
Thread 0 finished: SRR12904818_asmbFinal.bam with 323645 reads and 312691 readsWellMapped (96.6154%)
Creating depth matrix file: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt
Closing last bam file
Finished
[Thu Jul 16 20:34:13 2026]
Finished job 23.
23 of 118 steps (19%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/tmp_basecov.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/tmp_idx.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/tmp_readcount.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/tmp_scafcov1.txt.
[Thu Jul 16 20:34:27 2026]
Finished job 34.
24 of 118 steps (20%) done

[Thu Jul 16 20:34:27 2026]
rule run_bbtools_stats:
    input: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_contigs.fasta
    output: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt
    jobid: 33
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_contigs.fasta
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

sed $'s/_cov_/ cov_/g' /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_contigs.fasta > /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta && stats.sh in=/outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta out=/outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt && printf "\nTEDreads mapping stats:\n"  >> /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt

[Thu Jul 16 20:34:27 2026]
rule run_kraken2_classification:
    input: /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz
    output: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904821_taxREPORT.txt, /outputs/TAXprofiles/readsTAX_plusPFV/taxlogs/SRR12904821_classLOG.txt
    jobid: 13
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904821_taxREPORT.txt; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --gzip-compressed --threads 16 --confidence 0.15 --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --memory-mapping --paired /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz  --output - --report /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904821_taxREPORT.txt 2>> /outputs/TAXprofiles/readsTAX_plusPFV/taxlogs/SRR12904821_classLOG.txt
[Thu Jul 16 20:34:27 2026]
Finished job 33.
25 of 118 steps (21%) done
Select jobs to execute...

[Thu Jul 16 20:34:27 2026]
rule bowtie2_build:
    input: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta
    output: /outputs/asmbMTX/SRR12904821_asmb/_bowtie2_build.done
    jobid: 32
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/_bowtie2_build.done; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp

bowtie2-build --quiet --threads 16 /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.db && touch /outputs/asmbMTX/SRR12904821_asmb/_bowtie2_build.done
[Thu Jul 16 20:34:28 2026]
Finished job 32.
26 of 118 steps (22%) done
Select jobs to execute...

[Thu Jul 16 20:34:28 2026]
rule bowtie2_run:
    input: /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904821_asmb/_bowtie2_build.done
    output: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.sam
    jobid: 31
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.sam; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904821_asmb/_bowtie2_build.done, /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp

bowtie2 --phred33 --sensitive-local --no-unal --seed 4 -1 /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz -2 /outputs/TEDreads_fqs/SRR12904821_R2_ted_mtx.fastq.gz -x /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.db -S /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.sam -p 16 2>> /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt
[Thu Jul 16 20:34:32 2026]
Finished job 31.
27 of 118 steps (23%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/_bowtie2_build.done.
Select jobs to execute...

[Thu Jul 16 20:34:32 2026]
rule samtools_to_bam:
    input: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.sam
    output: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_initial.bam, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_colated.bam, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixmate.bam, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixsrtd.bam, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_markdup.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam.bai
    jobid: 30
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_markdup.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.sam
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp

samtools sort /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.sam -o /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_initial.bam -@ 16 -T /outputs/tmpSRR12904821_srtfixd && samtools collate /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_initial.bam -o /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_colated.bam -@ 16 /outputs/tmpSRR12904821_collate && samtools fixmate -m /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_colated.bam /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixmate.bam -@ 16 && samtools sort /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixmate.bam -o /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixsrtd.bam -@ 16 -T /outputs/tmpSRR12904821_srtfixd && samtools markdup -r -s /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixsrtd.bam -f /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_markdup.txt /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam -@ 16 -T /outputs/tmpSRR12904821_markdup && samtools index -b /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam -@ 16
[bam_sort_core] merging from 0 files and 16 in-memory blocks...
[bam_sort_core] merging from 0 files and 16 in-memory blocks...
[Thu Jul 16 20:34:35 2026]
Finished job 30.
28 of 118 steps (24%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/SRR12904821.sam.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_initial.bam.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_colated.bam.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixmate.bam.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_fixsrtd.bam.
Select jobs to execute...

[Thu Jul 16 20:34:35 2026]
rule add_derep_stats:
    input: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_markdup.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/_added_derep_stats.done
    jobid: 110
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/_added_derep_stats.done; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_markdup.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

cat /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt <(printf "\nRead alignment de-replication stats:\n") /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_markdup.txt > /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_tmp_file.txt && mv /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_tmp_file.txt /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbStats.txt && touch /outputs/asmbMTX/SRR12904821_asmb/_added_derep_stats.done
[Thu Jul 16 20:34:35 2026]
Finished job 110.
29 of 118 steps (25%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_markdup.txt.
Select jobs to execute...
[Thu Jul 16 20:35:09 2026]
Finished job 13.
30 of 118 steps (25%) done

[Thu Jul 16 20:35:09 2026]
rule run_kraken2_classification:
    input: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz
    output: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904818_taxREPORT.txt, /outputs/TAXprofiles/readsTAX_plusPFV/taxlogs/SRR12904818_classLOG.txt
    jobid: 8
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904818_taxREPORT.txt; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --gzip-compressed --threads 16 --confidence 0.15 --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --memory-mapping --paired /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz /outputs/TEDreads_fqs/SRR12904818_R2_ted_mtx.fastq.gz  --output - --report /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904818_taxREPORT.txt 2>> /outputs/TAXprofiles/readsTAX_plusPFV/taxlogs/SRR12904818_classLOG.txt

[Thu Jul 16 20:35:09 2026]
rule kreport2krona_per_sample:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904821_taxREPORT.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904821.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt
    jobid: 12
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904821_taxREPORT.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

sed -E 's_\tR[12]\t(.*)(Viruses|Bacteria|Eukaryota|Archaea)_\tD\t\1\2_g' /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904821_taxREPORT.txt > /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904821.txt &&python3 /pipeline/utils/report2krona_wTAXid_last.py --report-file /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904821.txt --no-tax-prefixes -o /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt &&sed -i ':a; 2s/\t\t/\tUnclassified\t/; ta'  /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt
Namespace(r_file='/outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904821.txt', r_dir=None, o_file='/outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt', x_include=False, tax_exclude=True, m_file=None)
[Thu Jul 16 20:35:09 2026]
Finished job 12.
31 of 118 steps (26%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904821.txt.
Select jobs to execute...

[Thu Jul 16 20:35:09 2026]
rule tax_biom_per_sample:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_4biom.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_json.biom
    jobid: 74
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_json.biom; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

sed 's/\t/;/g' /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt | sed 's/;/\t/1' | nl -n ln |sed '1s/^/\t/' | sed '1s/1\s\+\t#/\t/' | sed 's/\s\+\t/\t/g' | sed '1s/LINEAGE/taxonomy/' | sed -e '1s/Level.*/taxonomy/' > /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_4biom.txt && biom convert -i /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_4biom.txt -o /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_json.biom --to-json --table-type='OTU table' --process-obs-metadata taxonomy
[Thu Jul 16 20:35:10 2026]
Finished job 74.
32 of 118 steps (27%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_4biom.txt.
Select jobs to execute...
[Thu Jul 16 20:35:20 2026]
Finished job 8.
33 of 118 steps (28%) done

[Thu Jul 16 20:35:20 2026]
rule kreport2krona_per_sample:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904818_taxREPORT.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904818.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt
    jobid: 7
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904818_taxREPORT.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

sed -E 's_\tR[12]\t(.*)(Viruses|Bacteria|Eukaryota|Archaea)_\tD\t\1\2_g' /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904818_taxREPORT.txt > /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904818.txt &&python3 /pipeline/utils/report2krona_wTAXid_last.py --report-file /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904818.txt --no-tax-prefixes -o /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt &&sed -i ':a; 2s/\t\t/\tUnclassified\t/; ta'  /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt

[Thu Jul 16 20:35:20 2026]
rule run_kraken2_classification:
    input: /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz
    output: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904817_taxREPORT.txt, /outputs/TAXprofiles/readsTAX_plusPFV/taxlogs/SRR12904817_classLOG.txt
    jobid: 3
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904817_taxREPORT.txt; Input files updated by another job: /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --gzip-compressed --threads 16 --confidence 0.15 --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --memory-mapping --paired /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz /outputs/TEDreads_fqs/SRR12904817_R2_ted_mtx.fastq.gz  --output - --report /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904817_taxREPORT.txt 2>> /outputs/TAXprofiles/readsTAX_plusPFV/taxlogs/SRR12904817_classLOG.txt
Namespace(r_file='/outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904818.txt', r_dir=None, o_file='/outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt', x_include=False, tax_exclude=True, m_file=None)
[Thu Jul 16 20:35:20 2026]
Finished job 7.
34 of 118 steps (29%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904818.txt.
Select jobs to execute...

[Thu Jul 16 20:35:20 2026]
rule tax_biom_per_sample:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_4biom.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_json.biom
    jobid: 73
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_json.biom; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

sed 's/\t/;/g' /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt | sed 's/;/\t/1' | nl -n ln |sed '1s/^/\t/' | sed '1s/1\s\+\t#/\t/' | sed 's/\s\+\t/\t/g' | sed '1s/LINEAGE/taxonomy/' | sed -e '1s/Level.*/taxonomy/' > /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_4biom.txt && biom convert -i /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_4biom.txt -o /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_json.biom --to-json --table-type='OTU table' --process-obs-metadata taxonomy
[Thu Jul 16 20:35:21 2026]
Finished job 73.
35 of 118 steps (30%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_4biom.txt.
Select jobs to execute...
[Thu Jul 16 20:35:25 2026]
Finished job 3.
36 of 118 steps (31%) done

[Thu Jul 16 20:35:25 2026]
rule kreport2krona_per_sample:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904817_taxREPORT.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904817.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt
    jobid: 2
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904817_taxREPORT.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

sed -E 's_\tR[12]\t(.*)(Viruses|Bacteria|Eukaryota|Archaea)_\tD\t\1\2_g' /outputs/TAXprofiles/readsTAX_plusPFV/reports/SRR12904817_taxREPORT.txt > /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904817.txt &&python3 /pipeline/utils/report2krona_wTAXid_last.py --report-file /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904817.txt --no-tax-prefixes -o /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt &&sed -i ':a; 2s/\t\t/\tUnclassified\t/; ta'  /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt

[Thu Jul 16 20:35:25 2026]
rule scaffold_and_read_counts:
    input: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam
    output: /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt, /outputs/asmbMTX/SRR12904821_asmb/tmp_basecov.txt, /outputs/asmbMTX/SRR12904821_asmb/tmp_idx.txt, /outputs/asmbMTX/SRR12904821_asmb/tmp_readcount.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt, /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov1.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    jobid: 29
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp, mem_gb=46

pileup.sh -Xmx46g /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam out=/outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt overwrite=true && sort -o /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt && jgi_summarize_bam_contig_depths /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam --outputDepth /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt && sort /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt | sed '1 s/^/#/' | cut -f 1-3 > /outputs/asmbMTX/SRR12904821_asmb/tmp_basecov.txt && samtools idxstats /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam > /outputs/asmbMTX/SRR12904821_asmb/tmp_idx.txt && cut -f 1-3 /outputs/asmbMTX/SRR12904821_asmb/tmp_idx.txt | sed -e '1s/^/#contigName\tLength\tReadsCount\n/' | sort | grep -v "*" > /outputs/asmbMTX/SRR12904821_asmb/tmp_readcount.txt && paste /outputs/asmbMTX/SRR12904821_asmb/tmp_readcount.txt /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt /outputs/asmbMTX/SRR12904821_asmb/tmp_basecov.txt | cut -f 1,2,3,8-14,17 -d $'\t' > /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov1.txt && awk 'BEGIN{FS=OFS="\t"} NR>1 {if ($2>0 && $3>0) $12=sprintf("%0.2f", $3*1e3/$2); else $12=0; print}'  /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov1.txt | sed -e '1s/^/#NODE\tlen\tReads\t\%NodeCovered\t\%bpCovered\tplusReads\tminusReads\t\%GC\tMedFold\tstDev\tAveDepth\tRPK\n/' > /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
java -ea -Xmx46g -cp /opt/conda/opt/bbmap-39.15-0/current/ jgi.CoveragePileup -Xmx46g /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam out=/outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt overwrite=true
Namespace(r_file='/outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904817.txt', r_dir=None, o_file='/outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt', x_include=False, tax_exclude=True, m_file=None)
[Thu Jul 16 20:35:25 2026]
Finished job 2.
37 of 118 steps (31%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/klogs/reports/tmp_SRR12904817.txt.
Select jobs to execute...

[Thu Jul 16 20:35:25 2026]
rule kreport2krona_import_text:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/TAXplots_readsTAX_plusPFV.html
    jobid: 1
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/TAXplots_readsTAX_plusPFV.html; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt
    resources: tmpdir=/docker_tmp

ktImportText /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt -o /outputs/TAXprofiles/readsTAX_plusPFV/TAXplots_readsTAX_plusPFV.html

[Thu Jul 16 20:35:25 2026]
rule tax_biom_per_sample:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_4biom.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_json.biom
    jobid: 72
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_json.biom; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

sed 's/\t/;/g' /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt | sed 's/;/\t/1' | nl -n ln |sed '1s/^/\t/' | sed '1s/1\s\+\t#/\t/' | sed 's/\s\+\t/\t/g' | sed '1s/LINEAGE/taxonomy/' | sed -e '1s/Level.*/taxonomy/' > /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_4biom.txt && biom convert -i /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_4biom.txt -o /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_json.biom --to-json --table-type='OTU table' --process-obs-metadata taxonomy

[Thu Jul 16 20:35:25 2026]
rule TAX_collation:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt
    output: /outputs/TAXprofiles/readsTAX_plusPFV/SccList.txt, /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+TAX.txt, /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage.txt, /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/TAX_collationR.log.txt
    jobid: 115
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage.txt, /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+TAX.txt; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904818_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904821_wTAXid_4krona.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bin/SRR12904817_wTAXid_4krona.txt
    resources: tmpdir=/docker_tmp

find /outputs/TAXprofiles/readsTAX_plusPFV/bin//*_4krona.txt -type f -empty -delete && ls -1 /outputs/TAXprofiles/readsTAX_plusPFV/bin/ | xargs basename -a -s _wTAXid_4krona.txt > /outputs/TAXprofiles/readsTAX_plusPFV/SccList.txt && Rscript /pipeline/utils/TableMergingShortReads_TAX_v5.R --binDIR /outputs/TAXprofiles/readsTAX_plusPFV/bin/ --sccList /outputs/TAXprofiles/readsTAX_plusPFV/SccList.txt --outdir /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/                     --genesDIR NA 2>&1 >/outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/TAX_collationR.log.txt
Executing jgi.CoveragePileup [-Xmx46g, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam, out=/outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt, overwrite=true]

Found samtools 1.21
Writing /outputs/TAXprofiles/readsTAX_plusPFV/TAXplots_readsTAX_plusPFV.html...
[Thu Jul 16 20:35:25 2026]
Finished job 1.
38 of 118 steps (32%) done
Could not find sambamba.
Reads:                               	124575
Mapped reads:                        	124575
Mapped bases:                        	17147951
Ref scaffolds:                       	4632
Ref bases:                           	2276814

Percent mapped:                      	100.000
Percent proper pairs:                	95.759
Average coverage:                    	7.532
Average coverage with deletions:     	7.532
Standard deviation:                    	56.281
Percent scaffolds with any coverage: 	100.00
Percent of reference bases covered:  	99.55

Time: 	0.460 seconds.
Output depth matrix to /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt
jgi_summarize_bam_contig_depths 2.17 (Bioconda) 2024-06-20T09:50:37
Running with 1 threads to save memory you can reduce the number of threads with the OMP_NUM_THREADS variable
Output matrix to /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt
Opening all bam files and validating headers
Processing bam files with largest_contig=0
Thread 0 opening and reading the header for file: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam
Thread 0 opened the file: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam
Thread 0 processing bam 0: SRR12904821_asmbFinal.bam
Thread 0 finished reading bam 0: SRR12904821_asmbFinal.bam
Thread 0 finished: SRR12904821_asmbFinal.bam with 124575 reads and 121052 readsWellMapped (97.172%)
Creating depth matrix file: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt
Closing last bam file
Finished
[Thu Jul 16 20:35:26 2026]
Finished job 29.
39 of 118 steps (33%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/tmp_basecov.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/tmp_idx.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/tmp_readcount.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/tmp_scafcov1.txt.
Select jobs to execute...

[Thu Jul 16 20:35:26 2026]
rule gene_prediction:
    input: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gff, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna
    jobid: 42
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gff, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp

prodigal -p meta -i /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta -f gff -o /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gff -a /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa -d /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna -q

[Thu Jul 16 20:35:26 2026]
rule gene_prediction:
    input: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gff, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna
    jobid: 38
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gff, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp

prodigal -p meta -i /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta -f gff -o /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gff -a /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa -d /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna -q
[Thu Jul 16 20:35:26 2026]
Finished job 72.
40 of 118 steps (34%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_4biom.txt.
Select jobs to execute...
`summarise()` has grouped output by 'Kingdom', 'Phylum', 'Class', 'Order',
'Family', 'Genus', 'Species'. You can override using the `.groups` argument.
`summarise()` has grouped output by 'Kingdom', 'Phylum', 'Class', 'Order',
'Family', 'Genus', 'Species'. You can override using the `.groups` argument.
`summarise()` has grouped output by 'Kingdom', 'Phylum', 'Class', 'Order',
'Family', 'Genus', 'Species'. You can override using the `.groups` argument.
Warning message:
There was 1 warning in `group_by()`.
ℹ In argument: `across(tiers)`.
Caused by warning:
! Using an external vector in selections was deprecated in tidyselect 1.1.0.
ℹ Please use `all_of()` or `any_of()` instead.
  # Was:
  data %>% select(tiers)

  # Now:
  data %>% select(all_of(tiers))

See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>. 
Warning message:
In dir.create(output$dir) :
  '/outputs/TAXprofiles/readsTAX_plusPFV/merged_tables' already exists
[Thu Jul 16 20:35:28 2026]
Finished job 115.
41 of 118 steps (35%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/SccList.txt.

[Thu Jul 16 20:35:28 2026]
rule gene_prediction:
    input: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gff, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna
    jobid: 46
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gff, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp

prodigal -p meta -i /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta -f gff -o /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gff -a /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa -d /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna -q
[Thu Jul 16 20:35:30 2026]
Finished job 38.
42 of 118 steps (36%) done
Select jobs to execute...

[Thu Jul 16 20:35:30 2026]
rule run_RGI:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_raw.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_seqs.faa
    jobid: 84
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_main.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp


            mkdir -p /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/

            cp /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904817_asmb/functional/RGI//_tmpPREDgenes.faa
            sed -E  's/\*//g' /outputs/asmbMTX/SRR12904817_asmb/functional/RGI//_tmpPREDgenes.faa > /outputs/asmbMTX/SRR12904817_asmb/functional/RGI//_tmpPREDgenes_noStar.faa  


            echo "-------- Running RGI -------"
            cp -r /dbs/wgsa2_plus/CARD_db-v4.0.1 /outputs/asmbMTX/SRR12904817_asmb/functional/RGI//cardDB/
            cd /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/  && rgi load --local -i cardDB/card.json
            rgi main --input_type protein -i _tmpPREDgenes_noStar.faa --clean --local                      -o _tmpRGIraw --data wgs --num_threads 16
            

            cut -f '1,9,11,15,16,17,28' _tmpRGIraw.txt |sed -E 's/ # .*;gc_cont=0....//g' >  RGI_main.txt 
            cut -f1  _tmpRGIraw.txt > _tmpHeaders.txt
            seqtk subseq _tmpPREDgenes.faa _tmpHeaders.txt > RGI_seqs.faa
            cp _tmpRGIraw.txt  RGI_raw.txt 
            
            rm -rf _tmp* localDB cardDB
            
Activating conda environment: rgi
-------- Running RGI -------
WARNING 2026-07-16 20:35:36,105 : No snp for model (2252, LpxD). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,105 : No snp for model (2313, Enterococcus faecalis YvlB with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,105 : No snp for model (2312, Enterococcus faecalis drmA with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,105 : No snp for model (2302, Enterococcus faecalis gdpD with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,106 : No snp for model (3717, Mycobacterium tuberculosis Rv1667 mutations confer resistance to pyrazinamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,107 : No snp for model (3734, Mycobacterium tuberculosis nat mutations conferring resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,107 : No snp for model (3708, Mycobacterium tuberculosis whib7 mutations confer resistance to kanamycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,107 : No snp for model (3709, Mycobacterium tuberculosis whib7 mutation conferring resistance to streptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,107 : No snp for model (3736, Mycobacterium tuberculosis Rv0565c mutation conferring resistance to ethionamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,107 : No snp for model (3744, Mycobacterium tuberculosis ald mutations confer resistance to cycloserine). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,107 : No snp for model (3724, Mycobacterium tuberculosis fabG1 mutations confer resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,113 : No snp for model (2304, Staphylococcus aureus agrA with mutation conferring resistance to daptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,113 : No snp for model (3739, Mycobacterium tuberculosis fabG1 mutation conferring resistance to ethionamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,113 : No snp for model (3749, Neisseria gonorrhoeae mtrC with mutation conferring resistance to azithromycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,113 : No snp for model (3895, Mycobacterium tuberculosis ethA mutations conferring resistance to perchlozone). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,113 : No snp for model (3710, Mycobacterium tuberculosis Rv1258c mutations confer resistance to streptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,114 : No snp for model (6024, Mycobacterium tuberculosis iniA mutations conferring resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:36,117 : No snp for model (5925, Escherichia coli PBP3 mutants conferring resistance to beta-lactam antibiotics). RGI will omit this model and keep running.
[Thu Jul 16 20:35:41 2026]
Finished job 42.
43 of 118 steps (36%) done
Select jobs to execute...

[Thu Jul 16 20:35:42 2026]
rule run_RGI:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_raw.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_seqs.faa
    jobid: 85
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_main.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp


            mkdir -p /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/

            cp /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904818_asmb/functional/RGI//_tmpPREDgenes.faa
            sed -E  's/\*//g' /outputs/asmbMTX/SRR12904818_asmb/functional/RGI//_tmpPREDgenes.faa > /outputs/asmbMTX/SRR12904818_asmb/functional/RGI//_tmpPREDgenes_noStar.faa  


            echo "-------- Running RGI -------"
            cp -r /dbs/wgsa2_plus/CARD_db-v4.0.1 /outputs/asmbMTX/SRR12904818_asmb/functional/RGI//cardDB/
            cd /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/  && rgi load --local -i cardDB/card.json
            rgi main --input_type protein -i _tmpPREDgenes_noStar.faa --clean --local                      -o _tmpRGIraw --data wgs --num_threads 16
            

            cut -f '1,9,11,15,16,17,28' _tmpRGIraw.txt |sed -E 's/ # .*;gc_cont=0....//g' >  RGI_main.txt 
            cut -f1  _tmpRGIraw.txt > _tmpHeaders.txt
            seqtk subseq _tmpPREDgenes.faa _tmpHeaders.txt > RGI_seqs.faa
            cp _tmpRGIraw.txt  RGI_raw.txt 
            
            rm -rf _tmp* localDB cardDB
            
Activating conda environment: rgi
-------- Running RGI -------
[Thu Jul 16 20:35:42 2026]
Finished job 46.
44 of 118 steps (37%) done
Select jobs to execute...

[Thu Jul 16 20:35:42 2026]
rule run_RGI:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_raw.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_seqs.faa
    jobid: 86
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_main.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp


            mkdir -p /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/

            cp /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904821_asmb/functional/RGI//_tmpPREDgenes.faa
            sed -E  's/\*//g' /outputs/asmbMTX/SRR12904821_asmb/functional/RGI//_tmpPREDgenes.faa > /outputs/asmbMTX/SRR12904821_asmb/functional/RGI//_tmpPREDgenes_noStar.faa  


            echo "-------- Running RGI -------"
            cp -r /dbs/wgsa2_plus/CARD_db-v4.0.1 /outputs/asmbMTX/SRR12904821_asmb/functional/RGI//cardDB/
            cd /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/  && rgi load --local -i cardDB/card.json
            rgi main --input_type protein -i _tmpPREDgenes_noStar.faa --clean --local                      -o _tmpRGIraw --data wgs --num_threads 16
            

            cut -f '1,9,11,15,16,17,28' _tmpRGIraw.txt |sed -E 's/ # .*;gc_cont=0....//g' >  RGI_main.txt 
            cut -f1  _tmpRGIraw.txt > _tmpHeaders.txt
            seqtk subseq _tmpPREDgenes.faa _tmpHeaders.txt > RGI_seqs.faa
            cp _tmpRGIraw.txt  RGI_raw.txt 
            
            rm -rf _tmp* localDB cardDB
            
Activating conda environment: rgi
-------- Running RGI -------
WARNING 2026-07-16 20:35:47,258 : No snp for model (2252, LpxD). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,258 : No snp for model (2313, Enterococcus faecalis YvlB with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,258 : No snp for model (2312, Enterococcus faecalis drmA with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,258 : No snp for model (2302, Enterococcus faecalis gdpD with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,259 : No snp for model (3717, Mycobacterium tuberculosis Rv1667 mutations confer resistance to pyrazinamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,260 : No snp for model (3734, Mycobacterium tuberculosis nat mutations conferring resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,260 : No snp for model (3708, Mycobacterium tuberculosis whib7 mutations confer resistance to kanamycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,260 : No snp for model (3709, Mycobacterium tuberculosis whib7 mutation conferring resistance to streptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,260 : No snp for model (3736, Mycobacterium tuberculosis Rv0565c mutation conferring resistance to ethionamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,261 : No snp for model (3744, Mycobacterium tuberculosis ald mutations confer resistance to cycloserine). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,261 : No snp for model (3724, Mycobacterium tuberculosis fabG1 mutations confer resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,267 : No snp for model (2304, Staphylococcus aureus agrA with mutation conferring resistance to daptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,267 : No snp for model (3739, Mycobacterium tuberculosis fabG1 mutation conferring resistance to ethionamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,267 : No snp for model (3749, Neisseria gonorrhoeae mtrC with mutation conferring resistance to azithromycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,267 : No snp for model (3895, Mycobacterium tuberculosis ethA mutations conferring resistance to perchlozone). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,267 : No snp for model (3710, Mycobacterium tuberculosis Rv1258c mutations confer resistance to streptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,268 : No snp for model (6024, Mycobacterium tuberculosis iniA mutations conferring resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:47,271 : No snp for model (5925, Escherichia coli PBP3 mutants conferring resistance to beta-lactam antibiotics). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,189 : No snp for model (2252, LpxD). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,189 : No snp for model (2313, Enterococcus faecalis YvlB with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,189 : No snp for model (2312, Enterococcus faecalis drmA with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,189 : No snp for model (2302, Enterococcus faecalis gdpD with mutation conferring daptomycin resistance). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,190 : No snp for model (3717, Mycobacterium tuberculosis Rv1667 mutations confer resistance to pyrazinamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,191 : No snp for model (3734, Mycobacterium tuberculosis nat mutations conferring resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,191 : No snp for model (3708, Mycobacterium tuberculosis whib7 mutations confer resistance to kanamycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,191 : No snp for model (3709, Mycobacterium tuberculosis whib7 mutation conferring resistance to streptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,191 : No snp for model (3736, Mycobacterium tuberculosis Rv0565c mutation conferring resistance to ethionamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,192 : No snp for model (3744, Mycobacterium tuberculosis ald mutations confer resistance to cycloserine). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,192 : No snp for model (3724, Mycobacterium tuberculosis fabG1 mutations confer resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,198 : No snp for model (2304, Staphylococcus aureus agrA with mutation conferring resistance to daptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,198 : No snp for model (3739, Mycobacterium tuberculosis fabG1 mutation conferring resistance to ethionamide). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,198 : No snp for model (3749, Neisseria gonorrhoeae mtrC with mutation conferring resistance to azithromycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,198 : No snp for model (3895, Mycobacterium tuberculosis ethA mutations conferring resistance to perchlozone). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,198 : No snp for model (3710, Mycobacterium tuberculosis Rv1258c mutations confer resistance to streptomycin). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,199 : No snp for model (6024, Mycobacterium tuberculosis iniA mutations conferring resistance to isoniazid). RGI will omit this model and keep running.
WARNING 2026-07-16 20:35:48,202 : No snp for model (5925, Escherichia coli PBP3 mutants conferring resistance to beta-lactam antibiotics). RGI will omit this model and keep running.
[Thu Jul 16 20:35:49 2026]
Finished job 84.
45 of 118 steps (38%) done
Select jobs to execute...

[Thu Jul 16 20:35:49 2026]
rule tax_classification_genes:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna
    output: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_taxREPORT.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_classLOG.txt
    jobid: 89
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --threads 16  --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --confidence 0.15 /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna --memory-mapping --output /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt --report /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_taxREPORT.txt 2>> /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_classLOG.txt
[Thu Jul 16 20:35:52 2026]
Finished job 89.
46 of 118 steps (39%) done
Select jobs to execute...

[Thu Jul 16 20:35:52 2026]
rule tax_classification_genes:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna
    output: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_taxREPORT.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_classLOG.txt
    jobid: 91
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --threads 16  --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --confidence 0.15 /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna --memory-mapping --output /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt --report /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_taxREPORT.txt 2>> /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_classLOG.txt
[Thu Jul 16 20:35:56 2026]
Finished job 91.
47 of 118 steps (40%) done
Select jobs to execute...

[Thu Jul 16 20:35:56 2026]
rule tax_classification_genes:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna
    output: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_taxREPORT.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_classLOG.txt
    jobid: 93
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --threads 16  --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --confidence 0.15 /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna --memory-mapping --output /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt --report /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_taxREPORT.txt 2>> /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_classLOG.txt
[Thu Jul 16 20:35:59 2026]
Finished job 93.
48 of 118 steps (41%) done
Select jobs to execute...

[Thu Jul 16 20:35:59 2026]
rule gene_annotation:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.hits, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.seed_orthologs, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations
    jobid: 65
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

emapper.py -i /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa -o annots --output_dir /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ --cpu 16 --itype proteins --block_size 4 --index_chunks 2 --data_dir /dbs/wgsa2/eggnog_data --override --temp_dir /outputs/tmp  --scratch_dir /outputs/tmp --dbmem
[Thu Jul 16 20:36:05 2026]
Finished job 86.
49 of 118 steps (42%) done
Select jobs to execute...

[Thu Jul 16 20:36:05 2026]
rule gff_to_gtf:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gff
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf
    jobid: 41
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gff
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

/pipeline/utils/gff2gtf.sh /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gff > /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf

[Thu Jul 16 20:36:05 2026]
rule TAX_diversity_plots:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+TAX.txt, /inputs/mapping_file.csv
    output: /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/TAX_diversity_plotsR.log.txt
    jobid: 117
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/TAX_diversity_plotsR.log.txt; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+TAX.txt
    resources: tmpdir=/docker_tmp


            sed '1s/^#//' /inputs/mapping_file.csv > /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/tmp_mapping_file.txt
            Rscript /pipeline/utils/DiversityPlotsShortReads_TAX_v5.R --wdir /outputs/tmp --indir /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/                 --mfile /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/tmp_mapping_file.txt --outdir /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/  2>&1 >/outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/TAX_diversity_plotsR.log.txt ||              echo "Failed to generate TAX_diversity_plots"  2>&1 >>/outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/TAX_diversity_plotsR.log.txt
            touch /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/TAX_diversity_plotsR.log.txt && rm /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/tmp_mapping_file.txt
            

[Thu Jul 16 20:36:05 2026]
rule gff_to_gtf:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gff
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf
    jobid: 45
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gff
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

/pipeline/utils/gff2gtf.sh /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gff > /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf

[Thu Jul 16 20:36:05 2026]
rule gff_to_gtf:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gff
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf
    jobid: 37
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gff
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

/pipeline/utils/gff2gtf.sh /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gff > /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf

[Thu Jul 16 20:36:05 2026]
rule TAX_collation_biom:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage.txt, /inputs/mapping_file.csv
    output: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage_json.biom, /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/tmp_.txt
    jobid: 114
    reason: Missing output files: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage_json.biom; Input files updated by another job: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage.txt
    resources: tmpdir=/docker_tmp

sed '1s/Lineage/taxonomy/' /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage.txt > /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/tmp_.txt && biom convert -i /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/tmp_.txt -m <(sed '1s/^/#/' /inputs/mapping_file.csv) -o /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage_json.biom --to-json --table-type='OTU table' --process-obs-metadata taxonomy
[Thu Jul 16 20:36:05 2026]
Finished job 41.
50 of 118 steps (42%) done
Select jobs to execute...
[Thu Jul 16 20:36:05 2026]
Finished job 37.
51 of 118 steps (43%) done
[Thu Jul 16 20:36:05 2026]
Finished job 45.
52 of 118 steps (44%) done
Loading required package: data.table
Loading required package: fossil
Loading required package: sp
[Thu Jul 16 20:36:06 2026]
Finished job 114.
53 of 118 steps (45%) done
Removing temporary output /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/tmp_.txt.
Loading required package: maps
Loading required package: shapefiles
Loading required package: foreign

Attaching package: ‘shapefiles’

The following objects are masked from ‘package:foreign’:

    read.dbf, write.dbf

Loading required package: ggplot2
Loading required package: vegan
Loading required package: permute
Loading required package: ampvis2
Loading required package: tidyverse
[Thu Jul 16 20:36:09 2026]
Finished job 85.
54 of 118 steps (46%) done

[Thu Jul 16 20:36:09 2026]
rule run_verse:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.summary.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.txt
    jobid: 44
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.summary.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp

verse -a /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf -t 'CDS' -g gene_id -z 0 -s 0 -o /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.bam -T 4
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.6.0
✔ lubridate 1.9.4     ✔ tibble    3.3.1
✔ purrr     1.2.1     ✔ tidyr     1.3.2
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::between()     masks data.table::between()
✖ dplyr::filter()      masks stats::filter()
✖ dplyr::first()       masks data.table::first()
✖ lubridate::hour()    masks data.table::hour()
✖ lubridate::isoweek() masks data.table::isoweek()
✖ lubridate::isoyear() masks data.table::isoyear()
✖ dplyr::lag()         masks stats::lag()
✖ dplyr::last()        masks data.table::last()
✖ purrr::map()         masks maps::map()
✖ lubridate::mday()    masks data.table::mday()
✖ lubridate::minute()  masks data.table::minute()
✖ lubridate::month()   masks data.table::month()
✖ lubridate::quarter() masks data.table::quarter()
✖ lubridate::second()  masks data.table::second()
✖ purrr::transpose()   masks data.table::transpose()
✖ lubridate::wday()    masks data.table::wday()
✖ lubridate::week()    masks data.table::week()
✖ lubridate::yday()    masks data.table::yday()
✖ lubridate::year()    masks data.table::year()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
All packages loaded successfully
Warning message:
Failed to locate timezone database 
Warning message:
In dir.create(path$outdir) :
  '/outputs/TAXprofiles/readsTAX_plusPFV/DivPlots' already exists
Warning message:
In tables$meta <- read.table(paste0(args$mfile), header = T, sep = "\t",  :
  Coercing LHS to a list
Warning message:
In alpha1$reads = colSums(tables$counts) : Coercing LHS to a list
Warning message:
In sst$meta = tables$meta : Coercing LHS to a list

        ===      ===    %%  %%  %%%%%%  %%   %%  %%       %%%%   %%%%%   
         ==      ==     %% %%     %%    %%% %%%  %%      %%  %%  %%  %%  
          ==    ==      %%%%      %%    %% % %%  %%      %%%%%%  %%%%%   
           ==  ==       %% %%     %%    %%   %%  %%      %%  %%  %%  %%  
            ====        %%  %%  %%%%%%  %%   %%  %%%%%%  %%  %%  %%%%%   
             ==        ................................................. 
	  v0.1.5

//============================== VERSE setting ===============================\\
||            Running mode : Default(featureCounts)                           ||
||            Feature type : CDS                                              ||
||              Input file : 1 BAM file                                       ||
||                           P /outputs/asmbMTX/SRR12904821_asmb/SRR12904 ... ||
||             Output file : /outputs/asmbMTX/SRR12904821_asmb/functional ... ||
||         Annotation file : /outputs/asmbMTX/SRR12904821_asmb/functional ... ||
||                                                                            ||
||                 Threads : 4                                                ||
|| Multithreaded BAM unzip : no                                               ||
||                                                                            ||
||              Paired-end : yes                                              ||
||         Strand specific : no                                               ||
||      Multimapping reads : not counted                                      ||
||                                                                            ||
||          Chimeric reads : counted                                          ||
||        Both ends mapped : not required                                     ||
||                                                                            ||
\\============= Based on the framework of featureCounts(SUBREAD) =============//

//================================= Running ==================================\\
||                                                                            ||
|| Load annotation file /outputs/asmbMTX/SRR12904821_asmb/functional/gene ... ||
||    CDSs : 5227                                                             ||
||    CDSs after merge : 5227                                                 ||
||    Genes : 5227                                                            ||
||    Chromosomes : 4574                                                      ||
||                                                                            ||
|| Process BAM file /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFin ... ||
||    Quantifying in paired-end mode.                                         ||
||    Assign read pairs to features...                                        ||
||    Read pairs with missing mates : 86593                                   ||
||    Total read pairs : 105584                                               ||
||    Successfully assigned read pairs : 86405 (81.8%)                        ||
||    Running time : 0.00 minutes                                             ||
||                                                                            ||
||                         Read assignment finished.                          ||
||                                                                            ||
\\====== VERSE: a Versatile and Efficient Rna-SEq read assignment tool =======//

[Thu Jul 16 20:36:09 2026]
Finished job 44.
55 of 118 steps (47%) done
Select jobs to execute...

[Thu Jul 16 20:36:09 2026]
rule rename_verse_summary:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.summary.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_stats.txt
    jobid: 43
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_stats.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.summary.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

mv /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.summary.txt /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_stats.txt

[Thu Jul 16 20:36:09 2026]
rule run_verse:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.summary.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.txt
    jobid: 36
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.summary.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp

verse -a /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf -t 'CDS' -g gene_id -z 0 -s 0 -o /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.bam -T 4

[Thu Jul 16 20:36:09 2026]
rule tpm_normalization:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_lengths.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_counts.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_coverage.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_RPK.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt
    jobid: 66
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

cut -f4,5,9 /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.gtf | sed 's/gene_id //g' | gawk '{print $3,$2-$1+1}' | tr ' ' '\t' | sed '1s/^/gene\tlength\n/' > /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_lengths.txt && join /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_lengths.txt /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.txt -t $'\t' > /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_counts.txt && grep "_" /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_counts.txt   | awk -v OFS="\t" '{$4 = sprintf("%0.0f", $3*150/$2)}1' | sort | sed -e '1s/^/#name\tlen\treads\tcov\n/' > /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_coverage.txt && grep "_" /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_coverage.txt | awk -v OFS="\t" '{$5 = sprintf("%0.0f", $3*1e3/$2)}1' | sort | sed -e '1s/^/#name\tlen\treads\tcov\tRPK\n/' > /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_RPK.txt && awk -v OFS="\t" 'NR==FNR{sum+= $5; next} FNR==1{print $0,"iTPM"; next} {printf("%s %0.0f\n", $0,$5*1e6/sum)}'  /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_RPK.txt /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_RPK.txt |sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt  
[Thu Jul 16 20:36:09 2026]
Finished job 43.
56 of 118 steps (47%) done
Select jobs to execute...
[Thu Jul 16 20:36:09 2026]
Finished job 66.
57 of 118 steps (48%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/genes/verse.CDS.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_lengths.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_counts.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_coverage.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/genes/tmp_RPK.txt.

[Thu Jul 16 20:36:09 2026]
rule tax_genes_ABUNtabtax:
    input: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    jobid: 92
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

cut -f2-3 /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt | sed -e 's/ (taxid /\t/g' | sed -e 's/)$//g' | sort | sed '1s/^/#contigName\tTAXname\tTAXid\n/' > /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt &&paste /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt <(cut -f2-3 /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt) > /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt 
[Thu Jul 16 20:36:09 2026]
Finished job 92.
58 of 118 steps (49%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt.
Select jobs to execute...

[Thu Jul 16 20:36:09 2026]
rule tax_genes_4krona:
    input: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    output: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904821_4krona.txt
    jobid: 97
    reason: Missing output files: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904821_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

cut -f6-8 /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt | awk -F'\t' 'NR>1{k = $3; sum[k]+= $1; name[k]=$2} END { print; for (k in sum) print sum[k], name[k], k}' OFS="	" |sed -e '1 s/^/#iTPM\tTAXname\tTAXid\n/' > /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904821_4krona.txt
[Thu Jul 16 20:36:09 2026]
Finished job 97.
59 of 118 steps (50%) done
Select jobs to execute...

        ===      ===    %%  %%  %%%%%%  %%   %%  %%       %%%%   %%%%%   
         ==      ==     %% %%     %%    %%% %%%  %%      %%  %%  %%  %%  
          ==    ==      %%%%      %%    %% % %%  %%      %%%%%%  %%%%%   
           ==  ==       %% %%     %%    %%   %%  %%      %%  %%  %%  %%  
            ====        %%  %%  %%%%%%  %%   %%  %%%%%%  %%  %%  %%%%%   
             ==        ................................................. 
	  v0.1.5

//============================== VERSE setting ===============================\\
||            Running mode : Default(featureCounts)                           ||
||            Feature type : CDS                                              ||
||              Input file : 1 BAM file                                       ||
||                           P /outputs/asmbMTX/SRR12904817_asmb/SRR12904 ... ||
||             Output file : /outputs/asmbMTX/SRR12904817_asmb/functional ... ||
||         Annotation file : /outputs/asmbMTX/SRR12904817_asmb/functional ... ||
||                                                                            ||
||                 Threads : 4                                                ||
|| Multithreaded BAM unzip : no                                               ||
||                                                                            ||
||              Paired-end : yes                                              ||
||         Strand specific : no                                               ||
||      Multimapping reads : not counted                                      ||
||                                                                            ||
||          Chimeric reads : counted                                          ||
||        Both ends mapped : not required                                     ||
||                                                                            ||
\\============= Based on the framework of featureCounts(SUBREAD) =============//

//================================= Running ==================================\\
||                                                                            ||
|| Load annotation file /outputs/asmbMTX/SRR12904817_asmb/functional/gene ... ||
||    CDSs : 3348                                                             ||
||    CDSs after merge : 3348                                                 ||
||    Genes : 3348                                                            ||
||    Chromosomes : 2796                                                      ||
||                                                                            ||
|| Process BAM file /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFin ... ||
||    Quantifying in paired-end mode.                                         ||
||    Assign read pairs to features...                                        ||
||    Read pairs with missing mates : 48860                                   ||
||    Total read pairs : 66120                                                ||
||    Successfully assigned read pairs : 57693 (87.3%)                        ||
||    Running time : 0.00 minutes                                             ||
||                                                                            ||
||                         Read assignment finished.                          ||
||                                                                            ||
\\====== VERSE: a Versatile and Efficient Rna-SEq read assignment tool =======//

[Thu Jul 16 20:36:09 2026]
Finished job 36.
60 of 118 steps (51%) done

[Thu Jul 16 20:36:09 2026]
rule run_verse:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.summary.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.txt
    jobid: 40
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.summary.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp

verse -a /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf -t 'CDS' -g gene_id -z 0 -s 0 -o /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.bam -T 4

[Thu Jul 16 20:36:09 2026]
rule rename_verse_summary:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.summary.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_stats.txt
    jobid: 35
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_stats.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.summary.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

mv /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.summary.txt /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_stats.txt

[Thu Jul 16 20:36:09 2026]
rule tpm_normalization:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_lengths.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_counts.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_coverage.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_RPK.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt
    jobid: 52
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

cut -f4,5,9 /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.gtf | sed 's/gene_id //g' | gawk '{print $3,$2-$1+1}' | tr ' ' '\t' | sed '1s/^/gene\tlength\n/' > /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_lengths.txt && join /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_lengths.txt /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.txt -t $'\t' > /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_counts.txt && grep "_" /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_counts.txt   | awk -v OFS="\t" '{$4 = sprintf("%0.0f", $3*150/$2)}1' | sort | sed -e '1s/^/#name\tlen\treads\tcov\n/' > /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_coverage.txt && grep "_" /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_coverage.txt | awk -v OFS="\t" '{$5 = sprintf("%0.0f", $3*1e3/$2)}1' | sort | sed -e '1s/^/#name\tlen\treads\tcov\tRPK\n/' > /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_RPK.txt && awk -v OFS="\t" 'NR==FNR{sum+= $5; next} FNR==1{print $0,"iTPM"; next} {printf("%s %0.0f\n", $0,$5*1e6/sum)}'  /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_RPK.txt /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_RPK.txt |sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt  
[Thu Jul 16 20:36:09 2026]
Finished job 35.
61 of 118 steps (52%) done
Select jobs to execute...
[Thu Jul 16 20:36:09 2026]
Finished job 52.
62 of 118 steps (53%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/genes/verse.CDS.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_lengths.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_counts.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_coverage.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/genes/tmp_RPK.txt.

[Thu Jul 16 20:36:09 2026]
rule tax_genes_ABUNtabtax:
    input: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    jobid: 88
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

cut -f2-3 /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt | sed -e 's/ (taxid /\t/g' | sed -e 's/)$//g' | sort | sed '1s/^/#contigName\tTAXname\tTAXid\n/' > /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt &&paste /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt <(cut -f2-3 /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt) > /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt 
[Thu Jul 16 20:36:09 2026]
Finished job 88.
63 of 118 steps (53%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt.
Select jobs to execute...

[Thu Jul 16 20:36:09 2026]
rule tax_genes_4krona:
    input: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    output: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904817_4krona.txt
    jobid: 95
    reason: Missing output files: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904817_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

cut -f6-8 /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt | awk -F'\t' 'NR>1{k = $3; sum[k]+= $1; name[k]=$2} END { print; for (k in sum) print sum[k], name[k], k}' OFS="	" |sed -e '1 s/^/#iTPM\tTAXname\tTAXid\n/' > /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904817_4krona.txt
[Thu Jul 16 20:36:09 2026]
Finished job 95.
64 of 118 steps (54%) done
Select jobs to execute...
Warning message:
Could not find a column named one of "OTU, ASV, #OTU ID" in otutable. Using row names as OTU ID's. 
438 OTUs not present in more than 0.01% relative abundance in any sample have been filtered 
Before: 580 OTUs
After: 142 OTUs

        ===      ===    %%  %%  %%%%%%  %%   %%  %%       %%%%   %%%%%   
         ==      ==     %% %%     %%    %%% %%%  %%      %%  %%  %%  %%  
          ==    ==      %%%%      %%    %% % %%  %%      %%%%%%  %%%%%   
           ==  ==       %% %%     %%    %%   %%  %%      %%  %%  %%  %%  
            ====        %%  %%  %%%%%%  %%   %%  %%%%%%  %%  %%  %%%%%   
             ==        ................................................. 
	  v0.1.5

//============================== VERSE setting ===============================\\
||            Running mode : Default(featureCounts)                           ||
||            Feature type : CDS                                              ||
||              Input file : 1 BAM file                                       ||
||                           P /outputs/asmbMTX/SRR12904818_asmb/SRR12904 ... ||
||             Output file : /outputs/asmbMTX/SRR12904818_asmb/functional ... ||
||         Annotation file : /outputs/asmbMTX/SRR12904818_asmb/functional ... ||
||                                                                            ||
||                 Threads : 4                                                ||
|| Multithreaded BAM unzip : no                                               ||
||                                                                            ||
||              Paired-end : yes                                              ||
||         Strand specific : no                                               ||
||      Multimapping reads : not counted                                      ||
||                                                                            ||
||          Chimeric reads : counted                                          ||
||        Both ends mapped : not required                                     ||
||                                                                            ||
\\============= Based on the framework of featureCounts(SUBREAD) =============//

//================================= Running ==================================\\
||                                                                            ||
|| Load annotation file /outputs/asmbMTX/SRR12904818_asmb/functional/gene ... ||
||    CDSs : 6105                                                             ||
||    CDSs after merge : 6105                                                 ||
||    Genes : 6105                                                            ||
||    Chromosomes : 4903                                                      ||
||                                                                            ||
|| Process BAM file /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFin ... ||
||    Quantifying in paired-end mode.                                         ||
||    Assign read pairs to features...                                        ||
||    Read pairs with missing mates : 262811                                  ||
||    Total read pairs : 293228                                               ||
||    Successfully assigned read pairs : 256792 (87.6%)                       ||
||    Running time : 0.01 minutes                                             ||
||                                                                            ||
||                         Read assignment finished.                          ||
||                                                                            ||
\\====== VERSE: a Versatile and Efficient Rna-SEq read assignment tool =======//

[Thu Jul 16 20:36:10 2026]
Finished job 40.
65 of 118 steps (55%) done

[Thu Jul 16 20:36:10 2026]
rule rename_verse_summary:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.summary.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_stats.txt
    jobid: 39
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_stats.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.summary.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

mv /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.summary.txt /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_stats.txt

[Thu Jul 16 20:36:10 2026]
rule tpm_normalization:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_lengths.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_counts.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_coverage.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_RPK.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt
    jobid: 59
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

cut -f4,5,9 /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.gtf | sed 's/gene_id //g' | gawk '{print $3,$2-$1+1}' | tr ' ' '\t' | sed '1s/^/gene\tlength\n/' > /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_lengths.txt && join /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_lengths.txt /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.txt -t $'\t' > /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_counts.txt && grep "_" /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_counts.txt   | awk -v OFS="\t" '{$4 = sprintf("%0.0f", $3*150/$2)}1' | sort | sed -e '1s/^/#name\tlen\treads\tcov\n/' > /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_coverage.txt && grep "_" /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_coverage.txt | awk -v OFS="\t" '{$5 = sprintf("%0.0f", $3*1e3/$2)}1' | sort | sed -e '1s/^/#name\tlen\treads\tcov\tRPK\n/' > /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_RPK.txt && awk -v OFS="\t" 'NR==FNR{sum+= $5; next} FNR==1{print $0,"iTPM"; next} {printf("%s %0.0f\n", $0,$5*1e6/sum)}'  /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_RPK.txt /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_RPK.txt |sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt  
[Thu Jul 16 20:36:10 2026]
Finished job 39.
66 of 118 steps (56%) done
Select jobs to execute...
[Thu Jul 16 20:36:10 2026]
Finished job 59.
67 of 118 steps (57%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/genes/verse.CDS.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_lengths.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_counts.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_coverage.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/genes/tmp_RPK.txt.

[Thu Jul 16 20:36:10 2026]
rule merge_ARGtabs:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt
    output: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_argsTPMtable.txt
    jobid: 87
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_argsTPMtable.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt
    threads: 16
    resources: tmpdir=/docker_tmp

python3 /pipeline/utils/RGI_merger_N3.py /outputs/asmbMTX/

[Thu Jul 16 20:36:10 2026]
rule tax_genes_ABUNtabtax:
    input: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    jobid: 90
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

cut -f2-3 /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt | sed -e 's/ (taxid /\t/g' | sed -e 's/)$//g' | sort | sed '1s/^/#contigName\tTAXname\tTAXid\n/' > /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt &&paste /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt <(cut -f2-3 /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt) > /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt 
[Thu Jul 16 20:36:10 2026]
Finished job 90.
68 of 118 steps (58%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_klog.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_tmptax.txt.
Select jobs to execute...

[Thu Jul 16 20:36:10 2026]
rule tax_genes_4krona:
    input: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    output: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904818_4krona.txt
    jobid: 96
    reason: Missing output files: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904818_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

cut -f6-8 /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt | awk -F'\t' 'NR>1{k = $3; sum[k]+= $1; name[k]=$2} END { print; for (k in sum) print sum[k], name[k], k}' OFS="	" |sed -e '1 s/^/#iTPM\tTAXname\tTAXid\n/' > /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904818_4krona.txt
[Thu Jul 16 20:36:10 2026]
Finished job 96.
69 of 118 steps (58%) done
Select jobs to execute...

[Thu Jul 16 20:36:10 2026]
rule kt_genetax_html:
    input: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904817_4krona.txt, /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904818_4krona.txt, /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904821_4krona.txt
    output: /outputs/TAXprofiles/geneTAX_plusPFV/TAXplots_genesTAX_plusPFV.html
    jobid: 94
    reason: Missing output files: /outputs/TAXprofiles/geneTAX_plusPFV/TAXplots_genesTAX_plusPFV.html; Input files updated by another job: /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904817_4krona.txt, /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904821_4krona.txt, /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904818_4krona.txt
    resources: tmpdir=/docker_tmp

ktImportTaxonomy /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904817_4krona.txt /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904818_4krona.txt /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904821_4krona.txt -m 1 -q 2 -t 3 -d 10 -tax /dbs/wgsa2/KronaTools_taxonomy -o /outputs/TAXprofiles/geneTAX_plusPFV/TAXplots_genesTAX_plusPFV.html
   [ WARNING ]  Score column already in use; not reading scores.
[Thu Jul 16 20:36:11 2026]
Finished job 87.
70 of 118 steps (59%) done
Select jobs to execute...
Warning messages:
1: `aes_string()` was deprecated in ggplot2 3.0.0.
ℹ Please use tidy evaluation idioms with `aes()`.
ℹ See also `vignette("ggplot2-in-packages")` for more information.
ℹ The deprecated feature was likely used in the ampvis2 package.
  Please report the issue at <https://github.com/kasperskytte/ampvis2/issues>. 
2: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
ℹ Please use the `linewidth` argument instead.
ℹ The deprecated feature was likely used in the ampvis2 package.
  Please report the issue at <https://github.com/kasperskytte/ampvis2/issues>. 
438 OTUs not present in more than 0.01% relative abundance in any sample have been filtered 
Before: 580 OTUs
After: 142 OTUs
Warning messages:
1: In vegan::metaMDS(data$abund, distance = distmeasure, trace = FALSE,  :
  stress is (nearly) zero: you may have insufficient data
2: In postMDS(out$points, dis, plot = max(0, plot - 1), ...) :
  skipping half-change scaling: too few points below threshold
Warning messages:
1: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.
ℹ The deprecated feature was likely used in the ampvis2 package.
  Please report the issue at <https://github.com/kasperskytte/ampvis2/issues>. 
2: In scale_fill_gradientn(colours = color.pal, trans = plot_colorscale,  :
  log-10 transformation introduced infinite values.
The following sample(s) have not been rarefied (less than 142957.5 reads):
SRR12904817, SRR12904821
0 samples have been filtered.
Warning message:
Removed 584 rows containing missing values or values outside the scale range
(`geom_ribbon()`). 
[Thu Jul 16 20:36:13 2026]
Finished job 117.
71 of 118 steps (60%) done
   [ WARNING ]  The following taxonomy IDs were not found in the local
                database and were set to root (if they were recently added to
                NCBI, use updateTaxonomy.sh to update the local database):
                3110288 3391424 2993430 3379134 3391429 3434353 2913503 2972775
                2995234 3434352 3391428 3344666 3409772
Loading taxonomy...
Importing /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904817_4krona.txt...
Importing /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904818_4krona.txt...
Importing /outputs/TAXprofiles/geneTAX_plusPFV/bin/SRR12904821_4krona.txt...
Writing /outputs/TAXprofiles/geneTAX_plusPFV/TAXplots_genesTAX_plusPFV.html...
[Thu Jul 16 20:36:14 2026]
Finished job 94.
72 of 118 steps (61%) done
[1;32mFunctional annotation of hits...[0m
0 1.430511474609375e-06 0.00 q/s (% mem usage: 1.70, % mem avail: 98.27)
[1;34mTime to load the DB into memory: 43.735817670822144[0m
500 46.70451259613037 10.71 q/s (% mem usage: 23.80, % mem avail: 76.25)
1000 49.58624291419983 20.17 q/s (% mem usage: 23.80, % mem avail: 76.25)
1500 52.43701171875 28.61 q/s (% mem usage: 23.80, % mem avail: 76.25)
2000 55.691222190856934 35.91 q/s (% mem usage: 23.80, % mem avail: 76.25)
2500 58.7389702796936 42.56 q/s (% mem usage: 23.80, % mem avail: 76.25)
3000 61.64482855796814 48.67 q/s (% mem usage: 23.80, % mem avail: 76.25)
3500 64.43695664405823 54.32 q/s (% mem usage: 23.80, % mem avail: 76.25)
4000 67.3941879272461 59.35 q/s (% mem usage: 23.80, % mem avail: 76.24)
4500 70.24899554252625 64.06 q/s (% mem usage: 23.80, % mem avail: 76.24)
4530 72.05258703231812 62.87 q/s (% mem usage: 23.70, % mem avail: 76.31)
#  emapper-2.1.6
# emapper.py  -i /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa -o annots --output_dir /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ --cpu 16 --itype proteins --block_size 4 --index_chunks 2 --data_dir /dbs/wgsa2/eggnog_data --override --temp_dir /outputs/tmp --scratch_dir /outputs/tmp --dbmem
[1;33m  /opt/conda/bin/diamond blastp -d /dbs/wgsa2/eggnog_data/eggnog_proteins.dmnd -q /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa --threads 16 -o /outputs/tmp/annots.emapper.hits  --sensitive --iterate -e 0.001 --block-size 4.0 -c 2 --top 3  --outfmt 6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qcovhsp scovhsp[0m
Loading source DB...
[31mWarning: this can take a few minutes and load up to 45GB to RAM. Using --dbmem is recommended to annotate a large number of sequences.[0m
 Copying result file /outputs/tmp/annots.emapper.hits from scratch to /outputs/asmbMTX/SRR12904821_asmb/functional/annotations
 Copying result file /outputs/tmp/annots.emapper.seed_orthologs from scratch to /outputs/asmbMTX/SRR12904821_asmb/functional/annotations
 Copying result file /outputs/tmp/annots.emapper.annotations from scratch to /outputs/asmbMTX/SRR12904821_asmb/functional/annotations
[31mData in /outputs/tmp will be not removed. Please, clear it manually.[0m
[32mDone[0m
   /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.hits
   /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.seed_orthologs
   /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations

================================================================================
CITATION:
If you use this software, please cite:

[1] eggNOG-mapper v2: functional annotation, orthology assignments, and domain 
      prediction at the metagenomic scale. Carlos P. Cantalapiedra, 
      Ana Hernandez-Plaza, Ivica Letunic, Peer Bork, Jaime Huerta-Cepas. 2021.
      Molecular Biology and Evolution, msab293, https://doi.org/10.1093/molbev/msab293

[2] eggNOG 5.0: a hierarchical, functionally and phylogenetically annotated
      orthology resource based on 5090 organisms and 2502 viruses. Jaime
      Huerta-Cepas, Damian Szklarczyk, Davide Heller, Ana Hernandez-Plaza,
      Sofia K Forslund, Helen Cook, Daniel R Mende, Ivica Letunic, Thomas
      Rattei, Lars J Jensen, Christian von Mering and Peer Bork. Nucleic Acids
      Research, Volume 47, Issue D1, 8 January 2019, Pages D309-D314,
      https://doi.org/10.1093/nar/gky1085 

[3] Sensitive protein alignments at tree-of-life scale using DIAMOND.
       Buchfink B, Reuter K, Drost HG. 2021.
       Nature Methods 18, 366–368 (2021). https://doi.org/10.1038/s41592-021-01101-x

e.g. Functional annotation was performed using emapper-2.1.6 [1]
 based on eggNOG orthology data [2]. Sequence searches were performed using [3].


================================================================================

Total hits processed: 4530
Total time: 1116 secs
FINISHED
[Thu Jul 16 20:54:37 2026]
Finished job 65.
73 of 118 steps (62%) done

[Thu Jul 16 20:54:37 2026]
rule gene_annotation_grep:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.COG.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.KEGGmap.txt
    jobid: 64
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations | cut -f 1,11 | sed -e 's/\t-//g' | grep -e $'\t' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations | cut -f 1,5 > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.COG.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations | cut -f1,12 | grep "ko:" | sed 's/ko://g' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.emapper.annotations | cut -f1,13 | grep "ko" | sed 's/,map.*//g' | sed 's/ko/map/g' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.KEGGmap.txt || true
        

[Thu Jul 16 20:54:37 2026]
rule tax_classification_scaffolds:
    input: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_taxREPORT.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_classLOG.txt
    jobid: 99
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --confidence 0.15 --memory-mapping --threads 16 /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbFinal.fasta --output /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt --report /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_taxREPORT.txt 2>> /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_classLOG.txt
[Thu Jul 16 20:54:37 2026]
Finished job 64.
74 of 118 steps (63%) done
Select jobs to execute...

[Thu Jul 16 20:54:37 2026]
rule gene_annot_seqExtract:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.fna
    jobid: 77
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.faa; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        seqtk subseq /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.faa
        seqtk subseq /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.fna
        seqtk subseq /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.faa
        seqtk subseq /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes.fna /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.fna
        

[Thu Jul 16 20:54:37 2026]
rule copy_annotation_file:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt
    jobid: 63
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

[Thu Jul 16 20:54:37 2026]
rule gene_annot_iTPMs:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt
    jobid: 83
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        awk -v OFS="\t" 'NR==FNR { id[$1]=$0; next } ($1 in id){ print $2, id[$1]}'  /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt | sed '1s/^/#KO\tnodeID\tlen\treads\tcov\tiRPK\tiTPM\n/' > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt
        awk -v OFS="\t" 'NR==FNR { id[$1]=$0; next } ($1 in id){ print $2, id[$1]}'  /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.txt | sed '1s/^/#KO\tnodeID\tlen\treads\tcov\tiRPK\tiTPM\n/' > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt        
        
[Thu Jul 16 20:54:37 2026]
Finished job 83.
75 of 118 steps (64%) done
Select jobs to execute...

[Thu Jul 16 20:54:37 2026]
rule gene_annot_geneTPMs:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ec.txt
    jobid: 82
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        cut -f1,7 /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt | sed $'s/#KO.*//g' | awk -F'\t' -f /pipeline/utils/calc_geneTPM.awk > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ko.txt
        awk -F'\t' -f /pipeline/utils/join2files_f2.awk /pipeline/utils/KO_list.txt /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ko.txt |         sed '1s/^/#KO\tgeneTPM\tgeneNAME\n/'> /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt

        cut -f1,7 /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt | sed $'s/#EC.*//g' | awk -F'\t' -f /pipeline/utils/calc_geneTPM.awk > /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ec.txt
        awk -F'\t' -f /pipeline/utils/join2files_f2.awk /pipeline/utils/EC_list.txt /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ec.txt |         sed '1s/^/#EC\tgeneTPM\tgeneNAME\n/'> /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ec.txt
        
[Thu Jul 16 20:54:37 2026]
Finished job 77.
76 of 118 steps (64%) done
Select jobs to execute...
[Thu Jul 16 20:54:37 2026]
Finished job 82.
77 of 118 steps (65%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ko.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/tmp_geneTPMtab.ec.txt.
/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Building DAG of jobs...
Using shell: /usr/bin/bash
Provided cores: 48
Rules claiming more threads will be scaled down.
Select jobs to execute...
cp /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.txt /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt && cut -f 1,5 /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_ABUNtab.txt > /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt
[Thu Jul 16 20:54:40 2026]
Finished job 63.
78 of 118 steps (66%) done

[Thu Jul 16 20:54:40 2026]
rule run_min_path:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.details.txt
    jobid: 68
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt ]; then
            python3 /usr/local/src/MinPath/MinPath.py -any /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt -map /dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt -mps /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.mps                 -report /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt -details /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.details.txt >> /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.minpath.log.txt
            # rm /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2ggmissing_pathways.txt
        else
            echo "The input file /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt is empty, so run_min_path will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.details.txt /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.minpath.log.txt
        fi
        
[Thu Jul 16 20:54:49 2026]
Finished job 68.
79 of 118 steps (67%) done
Select jobs to execute...

[Thu Jul 16 20:54:49 2026]
rule create_pathways_report:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt
    jobid: 67
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt ]; then
            grep 'minpath\ 1' /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt > /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt
        else
            echo "The input file /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt is empty, so create_pathways_report will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt
        fi
        
[Thu Jul 16 20:54:49 2026]
Finished job 67.
80 of 118 steps (68%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_report.txt.
Select jobs to execute...

[Thu Jul 16 20:54:49 2026]
rule run_genes2krona:
    input: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_4kr.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt
    jobid: 62
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt -a -s /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt -a -s /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt ]; then
            python3 /pipeline/utils/genes2KronaTable.py -i /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt            -m /dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt -H /dbs/lora/minpath_data/KEGGdb_0624/KEGGhrr_brite_0624.txt -n SRR12904821 -c /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt            -l /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/ko2gg.report.txt -o /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_4kr.txt &&            sed '1s/^/#/' /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_4kr.txt > /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt &&            cp /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt
        else
            echo "One of the input file is empty, so run_genes2krona will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_4kr.txt /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt
        fi
        
[Thu Jul 16 20:54:49 2026]
Finished job 62.
81 of 118 steps (69%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_TPM.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_annots.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/tmp_4kr.txt.
Select jobs to execute...

[Thu Jul 16 20:54:49 2026]
rule pwy_biom_per_sample:
    input: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt
    output: /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_4biom.txt, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_json.biom
    jobid: 71
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_json.biom; Input files updated by another job: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt ]; then
            sed 's/\t/;/g' /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt | sed 's/;/\t/1' | nl -n ln |sed '1s/^/\t/' | sed '1s/1\s\+\t#/\t/' | sed 's/\s\+\t/\t/g' | sed '1s/LINEAGE/taxonomy/' | sed -e '1s/Level.*/taxonomy/' > /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_4biom.txt
            biom convert -i /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_4biom.txt -o /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_json.biom --to-json --table-type='Pathway table' --process-obs-metadata taxonomy || touch /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_json.biom
        else
            echo "The input file /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt is empty, so pwy_biom_per_sample will not run. All output file(s) from this step are empty."
            touch /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_4biom.txt /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_json.biom
        fi
        
[Thu Jul 16 20:54:50 2026]
Finished job 71.
82 of 118 steps (69%) done
Removing temporary output /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_4biom.txt.
Select jobs to execute...
[Thu Jul 16 20:55:36 2026]
Finished job 99.
83 of 118 steps (70%) done

[Thu Jul 16 20:55:36 2026]
rule gene_annotation:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.hits, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.seed_orthologs, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations
    jobid: 51
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa
    wildcards: sample=SRR12904817
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

emapper.py -i /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa -o annots --output_dir /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ --cpu 16 --itype proteins --block_size 4 --index_chunks 2 --data_dir /dbs/wgsa2/eggnog_data --override --temp_dir /outputs/tmp  --scratch_dir /outputs/tmp --dbmem

[Thu Jul 16 20:55:36 2026]
rule generate_scaftax:
    input: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt
    jobid: 98
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

cut -f2-3 /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt | sed -e 's/ (taxid /\t/g' | sed -e 's/)$//g' | sort | sed '1s/^/#contigName\tTAXname\tTAXid\n/' > /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt && paste /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt <(cut -f2-3 /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt) > /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
[Thu Jul 16 20:55:36 2026]
Finished job 98.
84 of 118 steps (71%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt.
Select jobs to execute...

[Thu Jul 16 20:55:36 2026]
rule tax_scafs_4krona:
    input: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
    output: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904817_4krona.txt
    jobid: 105
    reason: Missing output files: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904817_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

cut -f12,13,14 /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt | awk -F'\t' 'NR>1{k = $3; sum[k]+= $1; name[k]=$2} END { print; for (k in sum) print sum[k], name[k], k}' OFS="	" |sed -e '1 s/^/#RPK\tTAXname\tTAXid\n/' > /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904817_4krona.txt
[Thu Jul 16 20:55:36 2026]
Finished job 105.
85 of 118 steps (72%) done
Select jobs to execute...
[1;32mFunctional annotation of hits...[0m
0 9.5367431640625e-07 0.00 q/s (% mem usage: 1.70, % mem avail: 98.30)
[1;34mTime to load the DB into memory: 44.14315104484558[0m
500 46.757951974868774 10.69 q/s (% mem usage: 23.80, % mem avail: 76.25)
1000 49.39547324180603 20.24 q/s (% mem usage: 23.80, % mem avail: 76.25)
1500 53.22248148918152 28.18 q/s (% mem usage: 23.80, % mem avail: 76.25)
2000 56.249425649642944 35.56 q/s (% mem usage: 23.80, % mem avail: 76.25)
2500 58.9567756652832 42.40 q/s (% mem usage: 23.80, % mem avail: 76.25)
3000 61.6925573348999 48.63 q/s (% mem usage: 23.80, % mem avail: 76.23)
3245 64.66567325592041 50.18 q/s (% mem usage: 23.70, % mem avail: 76.29)
#  emapper-2.1.6
# emapper.py  -i /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa -o annots --output_dir /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ --cpu 16 --itype proteins --block_size 4 --index_chunks 2 --data_dir /dbs/wgsa2/eggnog_data --override --temp_dir /outputs/tmp --scratch_dir /outputs/tmp --dbmem
[1;33m  /opt/conda/bin/diamond blastp -d /dbs/wgsa2/eggnog_data/eggnog_proteins.dmnd -q /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa --threads 16 -o /outputs/tmp/annots.emapper.hits  --sensitive --iterate -e 0.001 --block-size 4.0 -c 2 --top 3  --outfmt 6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qcovhsp scovhsp[0m
Loading source DB...
[31mWarning: this can take a few minutes and load up to 45GB to RAM. Using --dbmem is recommended to annotate a large number of sequences.[0m
 Copying result file /outputs/tmp/annots.emapper.hits from scratch to /outputs/asmbMTX/SRR12904817_asmb/functional/annotations
 Copying result file /outputs/tmp/annots.emapper.seed_orthologs from scratch to /outputs/asmbMTX/SRR12904817_asmb/functional/annotations
 Copying result file /outputs/tmp/annots.emapper.annotations from scratch to /outputs/asmbMTX/SRR12904817_asmb/functional/annotations
[31mData in /outputs/tmp will be not removed. Please, clear it manually.[0m
[32mDone[0m
   /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.hits
   /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.seed_orthologs
   /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations

================================================================================
CITATION:
If you use this software, please cite:

[1] eggNOG-mapper v2: functional annotation, orthology assignments, and domain 
      prediction at the metagenomic scale. Carlos P. Cantalapiedra, 
      Ana Hernandez-Plaza, Ivica Letunic, Peer Bork, Jaime Huerta-Cepas. 2021.
      Molecular Biology and Evolution, msab293, https://doi.org/10.1093/molbev/msab293

[2] eggNOG 5.0: a hierarchical, functionally and phylogenetically annotated
      orthology resource based on 5090 organisms and 2502 viruses. Jaime
      Huerta-Cepas, Damian Szklarczyk, Davide Heller, Ana Hernandez-Plaza,
      Sofia K Forslund, Helen Cook, Daniel R Mende, Ivica Letunic, Thomas
      Rattei, Lars J Jensen, Christian von Mering and Peer Bork. Nucleic Acids
      Research, Volume 47, Issue D1, 8 January 2019, Pages D309-D314,
      https://doi.org/10.1093/nar/gky1085 

[3] Sensitive protein alignments at tree-of-life scale using DIAMOND.
       Buchfink B, Reuter K, Drost HG. 2021.
       Nature Methods 18, 366–368 (2021). https://doi.org/10.1038/s41592-021-01101-x

e.g. Functional annotation was performed using emapper-2.1.6 [1]
 based on eggNOG orthology data [2]. Sequence searches were performed using [3].


================================================================================

Total hits processed: 3245
Total time: 1087 secs
FINISHED
[Thu Jul 16 21:13:44 2026]
Finished job 51.
86 of 118 steps (73%) done

[Thu Jul 16 21:13:44 2026]
rule gene_annotation_grep:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.COG.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.KEGGmap.txt
    jobid: 50
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations | cut -f 1,11 | sed -e 's/\t-//g' | grep -e $'\t' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations | cut -f 1,5 > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.COG.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations | cut -f1,12 | grep "ko:" | sed 's/ko://g' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.emapper.annotations | cut -f1,13 | grep "ko" | sed 's/,map.*//g' | sed 's/ko/map/g' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.KEGGmap.txt || true
        

[Thu Jul 16 21:13:44 2026]
rule gene_annotation:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.hits, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.seed_orthologs, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations
    jobid: 58
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

emapper.py -i /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa -o annots --output_dir /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ --cpu 16 --itype proteins --block_size 4 --index_chunks 2 --data_dir /dbs/wgsa2/eggnog_data --override --temp_dir /outputs/tmp  --scratch_dir /outputs/tmp --dbmem
[Thu Jul 16 21:13:44 2026]
Finished job 50.
87 of 118 steps (74%) done
Select jobs to execute...

[Thu Jul 16 21:13:45 2026]
rule copy_annotation_file:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt
    jobid: 49
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp

[Thu Jul 16 21:13:45 2026]
rule gene_annot_iTPMs:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt
    jobid: 79
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        awk -v OFS="\t" 'NR==FNR { id[$1]=$0; next } ($1 in id){ print $2, id[$1]}'  /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt | sed '1s/^/#KO\tnodeID\tlen\treads\tcov\tiRPK\tiTPM\n/' > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt
        awk -v OFS="\t" 'NR==FNR { id[$1]=$0; next } ($1 in id){ print $2, id[$1]}'  /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt | sed '1s/^/#KO\tnodeID\tlen\treads\tcov\tiRPK\tiTPM\n/' > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt        
        

[Thu Jul 16 21:13:45 2026]
rule gene_annot_seqExtract:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.fna
    jobid: 75
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.faa; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        seqtk subseq /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.faa
        seqtk subseq /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.fna
        seqtk subseq /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.faa
        seqtk subseq /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes.fna /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.txt > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.fna
        
[Thu Jul 16 21:13:45 2026]
Finished job 79.
88 of 118 steps (75%) done
Select jobs to execute...

[Thu Jul 16 21:13:45 2026]
rule gene_annot_geneTPMs:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ec.txt
    jobid: 78
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        cut -f1,7 /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt | sed $'s/#KO.*//g' | awk -F'\t' -f /pipeline/utils/calc_geneTPM.awk > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ko.txt
        awk -F'\t' -f /pipeline/utils/join2files_f2.awk /pipeline/utils/KO_list.txt /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ko.txt |         sed '1s/^/#KO\tgeneTPM\tgeneNAME\n/'> /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt

        cut -f1,7 /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt | sed $'s/#EC.*//g' | awk -F'\t' -f /pipeline/utils/calc_geneTPM.awk > /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ec.txt
        awk -F'\t' -f /pipeline/utils/join2files_f2.awk /pipeline/utils/EC_list.txt /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ec.txt |         sed '1s/^/#EC\tgeneTPM\tgeneNAME\n/'> /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ec.txt
        
[Thu Jul 16 21:13:45 2026]
Finished job 75.
89 of 118 steps (75%) done
Select jobs to execute...
[Thu Jul 16 21:13:45 2026]
Finished job 78.
90 of 118 steps (76%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ko.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/tmp_geneTPMtab.ec.txt.
/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Building DAG of jobs...
Using shell: /usr/bin/bash
Provided cores: 48
Rules claiming more threads will be scaled down.
Select jobs to execute...
cp /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.txt /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt && cut -f 1,5 /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_ABUNtab.txt > /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt
[Thu Jul 16 21:13:46 2026]
Finished job 49.
91 of 118 steps (77%) done

[Thu Jul 16 21:13:46 2026]
rule run_min_path:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.details.txt
    jobid: 54
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt ]; then
            python3 /usr/local/src/MinPath/MinPath.py -any /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt -map /dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt -mps /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.mps                 -report /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt -details /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.details.txt >> /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.minpath.log.txt
            # rm /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2ggmissing_pathways.txt
        else
            echo "The input file /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt is empty, so run_min_path will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.details.txt /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.minpath.log.txt
        fi
        
[Thu Jul 16 21:13:55 2026]
Finished job 54.
92 of 118 steps (78%) done
Select jobs to execute...

[Thu Jul 16 21:13:55 2026]
rule create_pathways_report:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt
    jobid: 53
    reason: Missing output files: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt ]; then
            grep 'minpath\ 1' /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt > /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt
        else
            echo "The input file /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt is empty, so create_pathways_report will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt
        fi
        
[Thu Jul 16 21:13:55 2026]
Finished job 53.
93 of 118 steps (79%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_report.txt.
Select jobs to execute...

[Thu Jul 16 21:13:55 2026]
rule run_genes2krona:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt
    output: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_4kr.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt
    jobid: 48
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt -a -s /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt -a -s /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt ]; then
            python3 /pipeline/utils/genes2KronaTable.py -i /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt            -m /dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt -H /dbs/lora/minpath_data/KEGGdb_0624/KEGGhrr_brite_0624.txt -n SRR12904817 -c /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt            -l /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/ko2gg.report.txt -o /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_4kr.txt &&            sed '1s/^/#/' /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_4kr.txt > /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt &&            cp /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt
        else
            echo "One of the input file is empty, so run_genes2krona will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_4kr.txt /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt
        fi
        
[Thu Jul 16 21:13:55 2026]
Finished job 48.
94 of 118 steps (80%) done
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_TPM.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_annots.txt.
Removing temporary output /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/tmp_4kr.txt.
Select jobs to execute...

[Thu Jul 16 21:13:56 2026]
rule pwy_biom_per_sample:
    input: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt
    output: /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_4biom.txt, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_json.biom
    jobid: 69
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_json.biom; Input files updated by another job: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt
    wildcards: sample=SRR12904817
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt ]; then
            sed 's/\t/;/g' /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt | sed 's/;/\t/1' | nl -n ln |sed '1s/^/\t/' | sed '1s/1\s\+\t#/\t/' | sed 's/\s\+\t/\t/g' | sed '1s/LINEAGE/taxonomy/' | sed -e '1s/Level.*/taxonomy/' > /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_4biom.txt
            biom convert -i /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_4biom.txt -o /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_json.biom --to-json --table-type='Pathway table' --process-obs-metadata taxonomy || touch /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_json.biom
        else
            echo "The input file /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt is empty, so pwy_biom_per_sample will not run. All output file(s) from this step are empty."
            touch /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_4biom.txt /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_json.biom
        fi
        
[Thu Jul 16 21:13:56 2026]
Finished job 69.
95 of 118 steps (81%) done
Removing temporary output /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_4biom.txt.
Select jobs to execute...
[1;32mFunctional annotation of hits...[0m
0 1.1920928955078125e-06 0.00 q/s (% mem usage: 1.70, % mem avail: 98.32)
[1;34mTime to load the DB into memory: 43.479798793792725[0m
500 46.9051730632782 10.66 q/s (% mem usage: 23.80, % mem avail: 76.21)
1000 49.96792531013489 20.01 q/s (% mem usage: 23.80, % mem avail: 76.21)
1500 53.856295585632324 27.85 q/s (% mem usage: 23.80, % mem avail: 76.21)
2000 57.460686445236206 34.81 q/s (% mem usage: 23.80, % mem avail: 76.21)
2500 60.89048480987549 41.06 q/s (% mem usage: 23.80, % mem avail: 76.21)
3000 64.18369364738464 46.74 q/s (% mem usage: 23.80, % mem avail: 76.21)
3500 67.3365831375122 51.98 q/s (% mem usage: 23.80, % mem avail: 76.21)
4000 70.62014436721802 56.64 q/s (% mem usage: 23.80, % mem avail: 76.21)
4500 73.69615960121155 61.06 q/s (% mem usage: 23.80, % mem avail: 76.21)
5000 76.78119325637817 65.12 q/s (% mem usage: 23.80, % mem avail: 76.21)
5500 80.27436780929565 68.52 q/s (% mem usage: 23.80, % mem avail: 76.21)
5762 83.61752986907959 68.91 q/s (% mem usage: 23.70, % mem avail: 76.27)
#  emapper-2.1.6
# emapper.py  -i /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa -o annots --output_dir /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ --cpu 16 --itype proteins --block_size 4 --index_chunks 2 --data_dir /dbs/wgsa2/eggnog_data --override --temp_dir /outputs/tmp --scratch_dir /outputs/tmp --dbmem
[1;33m  /opt/conda/bin/diamond blastp -d /dbs/wgsa2/eggnog_data/eggnog_proteins.dmnd -q /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa --threads 16 -o /outputs/tmp/annots.emapper.hits  --sensitive --iterate -e 0.001 --block-size 4.0 -c 2 --top 3  --outfmt 6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qcovhsp scovhsp[0m
Loading source DB...
[31mWarning: this can take a few minutes and load up to 45GB to RAM. Using --dbmem is recommended to annotate a large number of sequences.[0m
 Copying result file /outputs/tmp/annots.emapper.hits from scratch to /outputs/asmbMTX/SRR12904818_asmb/functional/annotations
 Copying result file /outputs/tmp/annots.emapper.seed_orthologs from scratch to /outputs/asmbMTX/SRR12904818_asmb/functional/annotations
 Copying result file /outputs/tmp/annots.emapper.annotations from scratch to /outputs/asmbMTX/SRR12904818_asmb/functional/annotations
[31mData in /outputs/tmp will be not removed. Please, clear it manually.[0m
[32mDone[0m
   /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.hits
   /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.seed_orthologs
   /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations

================================================================================
CITATION:
If you use this software, please cite:

[1] eggNOG-mapper v2: functional annotation, orthology assignments, and domain 
      prediction at the metagenomic scale. Carlos P. Cantalapiedra, 
      Ana Hernandez-Plaza, Ivica Letunic, Peer Bork, Jaime Huerta-Cepas. 2021.
      Molecular Biology and Evolution, msab293, https://doi.org/10.1093/molbev/msab293

[2] eggNOG 5.0: a hierarchical, functionally and phylogenetically annotated
      orthology resource based on 5090 organisms and 2502 viruses. Jaime
      Huerta-Cepas, Damian Szklarczyk, Davide Heller, Ana Hernandez-Plaza,
      Sofia K Forslund, Helen Cook, Daniel R Mende, Ivica Letunic, Thomas
      Rattei, Lars J Jensen, Christian von Mering and Peer Bork. Nucleic Acids
      Research, Volume 47, Issue D1, 8 January 2019, Pages D309-D314,
      https://doi.org/10.1093/nar/gky1085 

[3] Sensitive protein alignments at tree-of-life scale using DIAMOND.
       Buchfink B, Reuter K, Drost HG. 2021.
       Nature Methods 18, 366–368 (2021). https://doi.org/10.1038/s41592-021-01101-x

e.g. Functional annotation was performed using emapper-2.1.6 [1]
 based on eggNOG orthology data [2]. Sequence searches were performed using [3].


================================================================================

Total hits processed: 5762
Total time: 1112 secs
FINISHED
[Thu Jul 16 21:32:19 2026]
Finished job 58.
96 of 118 steps (81%) done

[Thu Jul 16 21:32:19 2026]
rule tax_classification_scaffolds:
    input: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_taxREPORT.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_classLOG.txt
    jobid: 101
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    wildcards: sample=SRR12904818
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --confidence 0.15 --memory-mapping --threads 16 /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbFinal.fasta --output /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt --report /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_taxREPORT.txt 2>> /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_classLOG.txt

[Thu Jul 16 21:32:19 2026]
rule gene_annotation_grep:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.COG.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.KEGGmap.txt
    jobid: 57
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations | cut -f 1,11 | sed -e 's/\t-//g' | grep -e $'\t' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations | cut -f 1,5 > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.COG.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations | cut -f1,12 | grep "ko:" | sed 's/ko://g' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt || true
        grep -E "NODE_|TRINITY_" /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.emapper.annotations | cut -f1,13 | grep "ko" | sed 's/,map.*//g' | sed 's/ko/map/g' | awk '{n=split($2,s,",");for (i=1;i<=n;i++) {$2=s[i];print}}' | sed -e 's/\s/\t/g' > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.KEGGmap.txt || true
        
[Thu Jul 16 21:32:19 2026]
Finished job 57.
97 of 118 steps (82%) done
Select jobs to execute...

[Thu Jul 16 21:32:19 2026]
rule gene_annot_seqExtract:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.fna
    jobid: 76
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.fna; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        seqtk subseq /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.faa
        seqtk subseq /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.fna
        seqtk subseq /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.faa /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.faa
        seqtk subseq /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes.fna /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.fna
        

[Thu Jul 16 21:32:19 2026]
rule copy_annotation_file:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt
    jobid: 56
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

[Thu Jul 16 21:32:19 2026]
rule gene_annot_iTPMs:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt
    jobid: 81
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        awk -v OFS="\t" 'NR==FNR { id[$1]=$0; next } ($1 in id){ print $2, id[$1]}'  /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt | sed '1s/^/#KO\tnodeID\tlen\treads\tcov\tiRPK\tiTPM\n/' > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt
        awk -v OFS="\t" 'NR==FNR { id[$1]=$0; next } ($1 in id){ print $2, id[$1]}'  /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.txt | sed '1s/^/#KO\tnodeID\tlen\treads\tcov\tiRPK\tiTPM\n/' > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt        
        
[Thu Jul 16 21:32:19 2026]
Finished job 81.
98 of 118 steps (83%) done
Select jobs to execute...

[Thu Jul 16 21:32:19 2026]
rule gene_annot_geneTPMs:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ec.txt
    jobid: 80
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ec.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        cut -f1,7 /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ko.txt | sed $'s/#KO.*//g' | awk -F'\t' -f /pipeline/utils/calc_geneTPM.awk > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ko.txt
        awk -F'\t' -f /pipeline/utils/join2files_f2.awk /pipeline/utils/KO_list.txt /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ko.txt |         sed '1s/^/#KO\tgeneTPM\tgeneNAME\n/'> /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt

        cut -f1,7 /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/ANNOTgenes_ABUNtab.ec.txt | sed $'s/#EC.*//g' | awk -F'\t' -f /pipeline/utils/calc_geneTPM.awk > /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ec.txt
        awk -F'\t' -f /pipeline/utils/join2files_f2.awk /pipeline/utils/EC_list.txt /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ec.txt |         sed '1s/^/#EC\tgeneTPM\tgeneNAME\n/'> /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ec.txt
        
[Thu Jul 16 21:32:19 2026]
Finished job 76.
99 of 118 steps (84%) done
Select jobs to execute...
[Thu Jul 16 21:32:19 2026]
Finished job 80.
100 of 118 steps (85%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ko.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/tmp_geneTPMtab.ec.txt.

[Thu Jul 16 21:32:19 2026]
rule cp_geneTPM_files:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ec.txt
    output: /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904817_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904818_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904821_geneTPMtab.ko.txt
    jobid: 113
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904817_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904821_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904818_geneTPMtab.ko.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ec.txt
    resources: tmpdir=/docker_tmp

/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
/opt/conda/lib/python3.10/site-packages/google/api_core/_python_version_support.py:275: FutureWarning: You are using a Python version (3.10.0) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Config file /pipeline/config.yaml is extended by additional config specified via the command line.
Building DAG of jobs...
Using shell: /usr/bin/bash
Provided cores: 48
Rules claiming more threads will be scaled down.
Select jobs to execute...
cp /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.txt /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt && cut -f 1,5 /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_ABUNtab.txt > /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt
Building DAG of jobs...
Using shell: /usr/bin/bash
Provided cores: 48
Rules claiming more threads will be scaled down.
Select jobs to execute...
cp /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt /outputs/PWYprofiles/keggPWYs.MP/genebin/
[Thu Jul 16 21:32:21 2026]
Finished job 56.
101 of 118 steps (86%) done
Select jobs to execute...

[Thu Jul 16 21:32:21 2026]
rule run_min_path:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.details.txt
    jobid: 61
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt ]; then
            python3 /usr/local/src/MinPath/MinPath.py -any /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt -map /dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt -mps /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.mps                 -report /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt -details /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.details.txt >> /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.minpath.log.txt
            # rm /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2ggmissing_pathways.txt
        else
            echo "The input file /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt is empty, so run_min_path will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.details.txt /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.minpath.log.txt
        fi
        
[Thu Jul 16 21:32:21 2026]
Finished job 113.
102 of 118 steps (86%) done
Select jobs to execute...
[Thu Jul 16 21:32:30 2026]
Finished job 61.
103 of 118 steps (87%) done

[Thu Jul 16 21:32:30 2026]
rule create_pathways_report:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt
    jobid: 60
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt ]; then
            grep 'minpath\ 1' /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt > /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt
        else
            echo "The input file /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt is empty, so create_pathways_report will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt
        fi
        
[Thu Jul 16 21:32:30 2026]
Finished job 60.
104 of 118 steps (88%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_report.txt.
Select jobs to execute...

[Thu Jul 16 21:32:30 2026]
rule run_genes2krona:
    input: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_4kr.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt
    jobid: 55
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt -a -s /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt -a -s /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt ]; then
            python3 /pipeline/utils/genes2KronaTable.py -i /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt            -m /dbs/lora/minpath_data/KEGGdb_0624/KEGGpwy-ko2map_0624.txt -H /dbs/lora/minpath_data/KEGGdb_0624/KEGGhrr_brite_0624.txt -n SRR12904818 -c /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt            -l /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/ko2gg.report.txt -o /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_4kr.txt &&            sed '1s/^/#/' /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_4kr.txt > /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt &&            cp /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt
        else
            echo "One of the input file is empty, so run_genes2krona will not run. All output file(s) from this step are empty."
            touch /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_4kr.txt /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt
        fi
        
[Thu Jul 16 21:32:30 2026]
Finished job 55.
105 of 118 steps (89%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_annots.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_TPM.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/tmp_4kr.txt.
Select jobs to execute...

[Thu Jul 16 21:32:30 2026]
rule pwy_biom_per_sample:
    input: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt
    output: /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_4biom.txt, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_json.biom
    jobid: 70
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_json.biom; Input files updated by another job: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp


        if [ -s /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt ]; then
            sed 's/\t/;/g' /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt | sed 's/;/\t/1' | nl -n ln |sed '1s/^/\t/' | sed '1s/1\s\+\t#/\t/' | sed 's/\s\+\t/\t/g' | sed '1s/LINEAGE/taxonomy/' | sed -e '1s/Level.*/taxonomy/' > /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_4biom.txt
            biom convert -i /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_4biom.txt -o /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_json.biom --to-json --table-type='Pathway table' --process-obs-metadata taxonomy || touch /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_json.biom
        else
            echo "The input file /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt is empty, so pwy_biom_per_sample will not run. All output file(s) from this step are empty."
            touch /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_4biom.txt /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_json.biom
        fi
        

[Thu Jul 16 21:32:30 2026]
rule PWY_collation:
    input: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904817_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904818_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904821_geneTPMtab.ko.txt
    output: /outputs/PWYprofiles/keggPWYs.MP/SccList.txt, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+PWY.txt, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers.txt, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_geneTPMtable.txt, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/PWY_collationR.log.txt
    jobid: 112
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers.txt, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+PWY.txt; Input files updated by another job: /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904818_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904818_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904817_4krona.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904817_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/genebin/SRR12904821_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/pwybin/SRR12904821_4krona.txt
    resources: tmpdir=/docker_tmp

find /outputs/PWYprofiles/keggPWYs.MP/pwybin//*.txt -type f -empty -delete && find /outputs/PWYprofiles/keggPWYs.MP/genebin//*.txt -type f -empty -delete && ls -1 /outputs/PWYprofiles/keggPWYs.MP/pwybin/ | xargs basename -a -s _4krona.txt > /outputs/PWYprofiles/keggPWYs.MP/SccList.txt && head /outputs/PWYprofiles/keggPWYs.MP/SccList.txt &&Rscript /pipeline/utils/TableMergingShortReads_PWY_v5.R --binDIR /outputs/PWYprofiles/keggPWYs.MP/pwybin/ --sccList /outputs/PWYprofiles/keggPWYs.MP/SccList.txt --outdir /outputs/PWYprofiles/keggPWYs.MP/merged_tables/                         --genesDIR /outputs/PWYprofiles/keggPWYs.MP/genebin/ 2>&1 >/outputs/PWYprofiles/keggPWYs.MP/merged_tables/PWY_collationR.log.txt

[Thu Jul 16 21:32:30 2026]
rule krona_import_text:
    input: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt
    output: /outputs/PWYprofiles/keggPWYs.MP/PWYplots_ko2gg.html
    jobid: 47
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/PWYplots_ko2gg.html; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt
    resources: tmpdir=/docker_tmp

ktImportText /outputs/asmbMTX/SRR12904817_asmb/functional/pathways/SRR12904817_4krona.txt /outputs/asmbMTX/SRR12904818_asmb/functional/pathways/SRR12904818_4krona.txt /outputs/asmbMTX/SRR12904821_asmb/functional/pathways/SRR12904821_4krona.txt -o /outputs/PWYprofiles/keggPWYs.MP/PWYplots_ko2gg.html
SRR12904817
SRR12904818
SRR12904821
Writing /outputs/PWYprofiles/keggPWYs.MP/PWYplots_ko2gg.html...
[Thu Jul 16 21:32:30 2026]
Finished job 47.
106 of 118 steps (90%) done
Select jobs to execute...
[Thu Jul 16 21:32:31 2026]
Finished job 70.
107 of 118 steps (91%) done
Removing temporary output /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_4biom.txt.
Warning message:
Failed to locate timezone database 
Warning message:
Expected 18 pieces. Missing pieces filled with `NA` in 109 rows [1, 2, 3, 4, 5,
6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, ...]. 
Warning message:
In dir.create(output$dir) :
  '/outputs/PWYprofiles/keggPWYs.MP/merged_tables' already exists
[Thu Jul 16 21:32:33 2026]
Finished job 112.
108 of 118 steps (92%) done
Removing temporary output /outputs/PWYprofiles/keggPWYs.MP/SccList.txt.

[Thu Jul 16 21:32:33 2026]
rule PWY_collation_biom:
    input: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers.txt, /inputs/mapping_file.csv
    output: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers_json.biom, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/tmp_.txt
    jobid: 111
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers_json.biom; Input files updated by another job: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers.txt
    resources: tmpdir=/docker_tmp

sed '1s/allTiers/taxonomy/' /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers.txt > /outputs/PWYprofiles/keggPWYs.MP/merged_tables/tmp_.txt && biom convert -i /outputs/PWYprofiles/keggPWYs.MP/merged_tables/tmp_.txt -m <(sed '1s/^/#/' /inputs/mapping_file.csv) -o /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers_json.biom --to-json --table-type='Pathway table' --process-obs-metadata taxonomy

[Thu Jul 16 21:32:33 2026]
rule PWY_diversity_plots:
    input: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+PWY.txt, /inputs/mapping_file.csv
    output: /outputs/PWYprofiles/keggPWYs.MP/DivPlots/PWY_diversity_plotsR.log.txt
    jobid: 116
    reason: Missing output files: /outputs/PWYprofiles/keggPWYs.MP/DivPlots/PWY_diversity_plotsR.log.txt; Input files updated by another job: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+PWY.txt
    resources: tmpdir=/docker_tmp


            sed 's/^#//g' /inputs/mapping_file.csv > /outputs/PWYprofiles/keggPWYs.MP/DivPlots/tmp_mapping_file.txt
            Rscript /pipeline/utils/DiversityPlotsShortReads_PWY_v5.R --wdir /outputs/tmp --indir /outputs/PWYprofiles/keggPWYs.MP/merged_tables/                     --mfile /outputs/PWYprofiles/keggPWYs.MP/DivPlots/tmp_mapping_file.txt --outdir /outputs/PWYprofiles/keggPWYs.MP/DivPlots/  2>&1 >/outputs/PWYprofiles/keggPWYs.MP/DivPlots/PWY_diversity_plotsR.log.txt ||                     echo "Failed to generate PWY_diversity_plots"  2>&1 >>/outputs/PWYprofiles/keggPWYs.MP/DivPlots/PWY_diversity_plotsR.log.txt
            touch /outputs/PWYprofiles/keggPWYs.MP/DivPlots/PWY_diversity_plotsR.log.txt && rm /outputs/PWYprofiles/keggPWYs.MP/DivPlots/tmp_mapping_file.txt
            
[Thu Jul 16 21:32:34 2026]
Finished job 111.
109 of 118 steps (92%) done
Removing temporary output /outputs/PWYprofiles/keggPWYs.MP/merged_tables/tmp_.txt.
Select jobs to execute...
Warning message:
Failed to locate timezone database 
Warning message:
In dir.create(path$outdir) :
  '/outputs/PWYprofiles/keggPWYs.MP/DivPlots' already exists
Warning message:
In tables$meta <- read.table(paste0(args$mfile), header = T, sep = "\t",  :
  Coercing LHS to a list
0 OTU's have been filtered.
Warning messages:
1: `aes_string()` was deprecated in ggplot2 3.0.0.
ℹ Please use tidy evaluation idioms with `aes()`.
ℹ See also `vignette("ggplot2-in-packages")` for more information.
ℹ The deprecated feature was likely used in the ampvis2 package.
  Please report the issue at <https://github.com/kasperskytte/ampvis2/issues>. 
2: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
ℹ Please use the `linewidth` argument instead.
ℹ The deprecated feature was likely used in the ampvis2 package.
  Please report the issue at <https://github.com/kasperskytte/ampvis2/issues>. 
0 OTU's have been filtered.
Warning messages:
1: In vegan::metaMDS(data$abund, distance = distmeasure, trace = FALSE,  :
  stress is (nearly) zero: you may have insufficient data
2: In postMDS(out$points, dis, plot = max(0, plot - 1), ...) :
  skipping half-change scaling: too few points below threshold
Warning messages:
1: The data has already been normalised. Setting normalise = TRUE (the default) will normalise the data again and the relative abundance information about the original data of which the provided data is a subset will be lost. 
2: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.
ℹ The deprecated feature was likely used in the ampvis2 package.
  Please report the issue at <https://github.com/kasperskytte/ampvis2/issues>. 
3: In scale_fill_gradientn(colours = color.pal, trans = plot_colorscale,  :
  log-10 transformation introduced infinite values.
[Thu Jul 16 21:32:38 2026]
Finished job 116.
110 of 118 steps (93%) done
[Thu Jul 16 21:33:54 2026]
Finished job 101.
111 of 118 steps (94%) done

[Thu Jul 16 21:33:54 2026]
rule generate_scaftax:
    input: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt
    jobid: 100
    reason: Missing output files: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

cut -f2-3 /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt | sed -e 's/ (taxid /\t/g' | sed -e 's/)$//g' | sort | sed '1s/^/#contigName\tTAXname\tTAXid\n/' > /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt && paste /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt <(cut -f2-3 /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt) > /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt

[Thu Jul 16 21:33:54 2026]
rule tax_classification_scaffolds:
    input: /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_taxREPORT.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_classLOG.txt
    jobid: 103
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    wildcards: sample=SRR12904821
    threads: 16
    resources: tmpdir=/docker_tmp, mem_gb=186

kraken2 --use-names --db /dbs/wgsa2plus_lora/plus_PFV_Oct2025 --confidence 0.15 --memory-mapping --threads 16 /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbFinal.fasta --output /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt --report /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_taxREPORT.txt 2>> /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_classLOG.txt
[Thu Jul 16 21:33:54 2026]
Finished job 100.
112 of 118 steps (95%) done
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt.
Removing temporary output /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt.
Select jobs to execute...

[Thu Jul 16 21:33:54 2026]
rule tax_scafs_4krona:
    input: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
    output: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904818_4krona.txt
    jobid: 106
    reason: Missing output files: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904818_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
    wildcards: sample=SRR12904818
    resources: tmpdir=/docker_tmp

cut -f12,13,14 /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt | awk -F'\t' 'NR>1{k = $3; sum[k]+= $1; name[k]=$2} END { print; for (k in sum) print sum[k], name[k], k}' OFS="	" |sed -e '1 s/^/#RPK\tTAXname\tTAXid\n/' > /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904818_4krona.txt
[Thu Jul 16 21:33:54 2026]
Finished job 106.
113 of 118 steps (96%) done
[Thu Jul 16 21:34:42 2026]
Finished job 103.
114 of 118 steps (97%) done
Select jobs to execute...

[Thu Jul 16 21:34:42 2026]
rule generate_scaftax:
    input: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    output: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt
    jobid: 102
    reason: Missing output files: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

cut -f2-3 /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt | sed -e 's/ (taxid /\t/g' | sed -e 's/)$//g' | sort | sed '1s/^/#contigName\tTAXname\tTAXid\n/' > /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt && paste /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt <(cut -f2-3 /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt) > /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
[Thu Jul 16 21:34:42 2026]
Finished job 102.
115 of 118 steps (97%) done
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_klog.txt.
Removing temporary output /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_tmp_tax.txt.
Select jobs to execute...

[Thu Jul 16 21:34:42 2026]
rule tax_scafs_4krona:
    input: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
    output: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904821_4krona.txt
    jobid: 107
    reason: Missing output files: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904821_4krona.txt; Input files updated by another job: /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt
    wildcards: sample=SRR12904821
    resources: tmpdir=/docker_tmp

cut -f12,13,14 /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt | awk -F'\t' 'NR>1{k = $3; sum[k]+= $1; name[k]=$2} END { print; for (k in sum) print sum[k], name[k], k}' OFS="	" |sed -e '1 s/^/#RPK\tTAXname\tTAXid\n/' > /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904821_4krona.txt
[Thu Jul 16 21:34:42 2026]
Finished job 107.
116 of 118 steps (98%) done
Select jobs to execute...

[Thu Jul 16 21:34:42 2026]
rule kt_scaftax_html:
    input: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904817_4krona.txt, /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904818_4krona.txt, /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904821_4krona.txt
    output: /outputs/TAXprofiles/scafTAX_plusPFV/TAXplots_scaffTAX_plusPFV.html
    jobid: 104
    reason: Missing output files: /outputs/TAXprofiles/scafTAX_plusPFV/TAXplots_scaffTAX_plusPFV.html; Input files updated by another job: /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904817_4krona.txt, /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904821_4krona.txt, /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904818_4krona.txt
    resources: tmpdir=/docker_tmp

ktImportTaxonomy /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904817_4krona.txt /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904818_4krona.txt /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904821_4krona.txt -m 1 -q 2 -t 3 -d 10 -tax /dbs/wgsa2/KronaTools_taxonomy -o /outputs/TAXprofiles/scafTAX_plusPFV/TAXplots_scaffTAX_plusPFV.html
   [ WARNING ]  Score column already in use; not reading scores.
   [ WARNING ]  The following taxonomy IDs were not found in the local
                database and were set to root (if they were recently added to
                NCBI, use updateTaxonomy.sh to update the local database):
                3110288 3434353 2972775 3434352 3379134 3344666 3391429 2993430
                3409772 2913503 2995234 3391424
Loading taxonomy...
Importing /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904817_4krona.txt...
Importing /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904818_4krona.txt...
Importing /outputs/TAXprofiles/scafTAX_plusPFV/bin/SRR12904821_4krona.txt...
Writing /outputs/TAXprofiles/scafTAX_plusPFV/TAXplots_scaffTAX_plusPFV.html...
[Thu Jul 16 21:34:45 2026]
Finished job 104.
117 of 118 steps (99%) done
Select jobs to execute...

[Thu Jul 16 21:34:45 2026]
localrule all:
    input: /outputs/TAXprofiles/readsTAX_plusPFV/TAXplots_readsTAX_plusPFV.html, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_stats.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_stats.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_stats.txt, /outputs/PWYprofiles/keggPWYs.MP/PWYplots_ko2gg.html, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_json.biom, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_json.biom, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_json.biom, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_json.biom, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_json.biom, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_json.biom, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_main.txt, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_argsTPMtable.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt, /outputs/TAXprofiles/geneTAX_plusPFV/TAXplots_genesTAX_plusPFV.html, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/TAXprofiles/scafTAX_plusPFV/TAXplots_scaffTAX_plusPFV.html, /outputs/asmbMTX/SRR12904817_asmb/_added_derep_stats.done, /outputs/asmbMTX/SRR12904818_asmb/_added_derep_stats.done, /outputs/asmbMTX/SRR12904821_asmb/_added_derep_stats.done, /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers_json.biom, /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage_json.biom, /outputs/PWYprofiles/keggPWYs.MP/DivPlots/PWY_diversity_plotsR.log.txt, /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/TAX_diversity_plotsR.log.txt
    jobid: 0
    reason: Input files updated by another job: /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbDepths.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/genes/PREDgenes_stats.txt, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904821_json.biom, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.faa, /outputs/TEDreads_fqs/SRR12904818_R1_ted_mtx.fastq.gz, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904821_json.biom, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbDepths.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904817_json.biom, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904818_asmb/SRR12904818_asmbCovr.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.faa, /outputs/asmbMTX/SRR12904817_asmb/SRR12904817_asmbCovr.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ko.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/RGI/RGI_main.txt, /outputs/TAXprofiles/scafTAX_plusPFV/TAXplots_scaffTAX_plusPFV.html, /outputs/TEDreads_fqs/SRR12904821_R1_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904818_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904818_json.biom, /outputs/PWYprofiles/keggPWYs.MP/DivPlots/PWY_diversity_plotsR.log.txt, /outputs/asmbMTX/SRR12904818_asmb/taxonomic/scafTAX_plusPFV/scafTAX_asmbCovr_wTAX.txt, /outputs/asmbMTX/SRR12904817_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/genes/PREDgenes_stats.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ec.faa, /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage_json.biom, /outputs/asmbMTX/SRR12904821_asmb/taxonomic/genesTAX_plusPFV/geneTAX_ABUNtab_wTAX.txt, /outputs/TAXprofiles/readsTAX_plusPFV/bioms/SRR12904818_json.biom, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ko.fna, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.fna, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/SRR12904818_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904821_asmb/functional/annotations/SRR12904821_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_argsTPMtable.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ko.txt, /outputs/PWYprofiles/keggPWYs.MP/bioms/SRR12904817_json.biom, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbDepths.txt, /outputs/asmbMTX/SRR12904821_asmb/functional/RGI/RGI_main.txt, /outputs/asmbMTX/SRR12904821_asmb/_added_derep_stats.done, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/SRR12904817_geneTPMtab.ec.txt, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ko.faa, /outputs/TAXprofiles/geneTAX_plusPFV/TAXplots_genesTAX_plusPFV.html, /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers_json.biom, /outputs/asmbMTX/SRR12904817_asmb/functional/annotations/annots.ec.faa, /outputs/asmbMTX/SRR12904817_asmb/_added_derep_stats.done, /outputs/asmbMTX/SRR12904821_asmb/SRR12904821_asmbCovr.txt, /outputs/PWYprofiles/keggPWYs.MP/PWYplots_ko2gg.html, /outputs/asmbMTX/SRR12904818_asmb/_added_derep_stats.done, /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/TAX_diversity_plotsR.log.txt, /outputs/asmbMTX/SRR12904818_asmb/functional/annotations/annots.ko.fna, /outputs/TEDreads_fqs/SRR12904817_R1_ted_mtx.fastq.gz, /outputs/asmbMTX/SRR12904818_asmb/functional/genes/PREDgenes_stats.txt, /outputs/TAXprofiles/readsTAX_plusPFV/TAXplots_readsTAX_plusPFV.html
    resources: tmpdir=/docker_tmp

[Thu Jul 16 21:34:45 2026]
Finished job 0.
118 of 118 steps (100%) done
Complete log: .snakemake/log/2026-07-16T200532.347867.snakemake.log

    set +o pipefail
    echo "Cleaning output..."
    rm -rf /outputs/asmbMTX/SRR12904817_asmb/*.bt2 /outputs/asmbMTX/SRR12904818_asmb/*.bt2 /outputs/asmbMTX/SRR12904821_asmb/*.bt2 /outputs/asmbMTX/SRR12904817_asmb/*.done /outputs/asmbMTX/SRR12904818_asmb/*.done /outputs/asmbMTX/SRR12904821_asmb/*.done /outputs/asmbMTX/SRR12904817_asmb/taxonomic/MAGs/magsQA/QCplots/*.done /outputs/asmbMTX/SRR12904818_asmb/taxonomic/MAGs/magsQA/QCplots/*.done /outputs/asmbMTX/SRR12904821_asmb/taxonomic/MAGs/magsQA/QCplots/*.done /outputs/TAXprofiles/readsTAX_plusPFV/klogs/ 
    
        rm -rf /outputs/TEDreads_fqs/
        cp /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage_json.biom /outputs/for_microbiomedb.biom
Cleaning output...
---> moving FASTA & BAM files from assembly to /outputs/asmb_files/ 
---> links to create SRR12904817
---> links to create SRR12904818
---> links to create SRR12904821
[2026-07-16 21:34:45.811 UTC] Generating outputs report: /outputs/outputs.json
[2026-07-16 21:34:45.812 UTC] Output reported: /outputs/for_microbiomedb.biom
[2026-07-16 21:34:45.813 UTC] Output reported: /outputs/TAXprofiles/readsTAX_plusPFV/DivPlots/.TAX_BetaDiv_PCoA.png
[2026-07-16 21:34:45.813 UTC] Output reported: /outputs/TAXprofiles/readsTAX_plusPFV/TAXplots_readsTAX_plusPFV.html
[2026-07-16 21:34:45.814 UTC] Output reported: /outputs/TAXprofiles/geneTAX_plusPFV/TAXplots_genesTAX_plusPFV.html
[2026-07-16 21:34:45.814 UTC] Output reported: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+TAX.txt
[2026-07-16 21:34:45.814 UTC] Output reported: /outputs/PWYprofiles/keggPWYs.MP/DivPlots/.PWY_BetaDiv_PCoA.png
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/PWYprofiles/keggPWYs.MP/PWYplots_ko2gg.html
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+PWY.txt
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_argsTPMtable.txt
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_geneTPMtable.txt
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904817_asmbFinal.bam
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904818_asmbFinal.bam
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904821_asmbFinal.bam
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904817_asmbFinal.bam.bai
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904818_asmbFinal.bam.bai
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904821_asmbFinal.bam.bai
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904817_asmbFinal.fasta
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904818_asmbFinal.fasta
[2026-07-16 21:34:45.815 UTC] Output reported: /outputs/asmb_files/SRR12904821_asmbFinal.fasta
[2026-07-16 21:34:45.816 UTC] Output reported: /outputs/asmb_files/SRR12904817_asmbDepths.txt
[2026-07-16 21:34:45.816 UTC] Output reported: /outputs/asmb_files/SRR12904818_asmbDepths.txt
[2026-07-16 21:34:45.816 UTC] Output reported: /outputs/asmb_files/SRR12904821_asmbDepths.txt
[2026-07-16 21:34:45.816 UTC] Output reported: /outputs/TAXprofiles/readsTAX_plusPFV/merged_tables/merged_Counts+Lineage.txt
[2026-07-16 21:34:45.816 UTC] Output reported: /outputs/PWYprofiles/keggPWYs.MP/merged_tables/merged_Counts+allTiers.txt
[2026-07-16 21:34:45.816 UTC] Outputs report generated: /outputs/outputs.json
[2026-07-16 21:34:45.817 UTC] Pipeline completed
