Bioinformatics Training & Education Program

This one-hour online training introduces participants to predictive modeling techniques for evaluating the toxicity of small molecules using MATLAB. Participants will explore the principles of cheminformatics, learn how to preprocess molecular data, and build predictive models using machine learning. The training highlights MATLAB's specialized tools for feature extraction, model development, and performance evaluation tailored to small-molecule datasets. Designed for researchers and data scientists in fields such as drug discovery and toxicology, this session equips attendees with practical skills for leveraging AI in molecular analysis.

By the end of this training, attendees will be able to:

• Understand the role of data science and AI in predicting toxicity of small molecules
• Import and preprocess molecular data, including handling chemical descriptors and cleaning datasets
• Extract relevant features from molecular datasets to enhance model accuracy
• Develop and evaluate machine learning models, such as classification algorithms, for toxicity prediction
• Visualize model results and interpret performance metrics to assess predictive accuracy
• Utilize MATLAB’s built-in resources and toolboxes to further explore cheminformatics and predictive modeling

Basic familiarity with MATLAB and machine learning concepts is helpful but not required.

Learn about the Federated Learning-based AI in Multi-Modal Exploration (FLAIMME) consortium—a collaboration between NCI and NCI-designated cancer centers seeking to advance multimodal clinical oncology.

 

Dr. Ghulam Rasool from the Moffitt Cancer Center will present:

• how consortium participants are exploring the application of foundational models for clinical applications all while retaining patient-level data.
• an initial use case for adapting models to pathology reports and extracting structured cancer variables relevant to downstream clinical applications.
• the federated architecture.
• practical challenges with multi-institutional training.
• preliminary observations from ongoing experiments and lessons informing continued work.

Whether you’re interested in the power of privacy-preserving foundational models or the collaborative nature of federated learning networks, register to learn more!

The director of the Bridge2AI Cell Maps for AI (CM4AI) Data Generation Project, will discuss the virtual cell models and associated data being generated by the CM4AI project. CM4AI seeks to map the spatiotemporal architecture of human cells and use these maps to interpret cell structure and function in health and disease. 

This one-hour online training will provide a high-level overview of Python coding concepts, as well as some of the integrative development environments (IDEs, such as Jupyter notebooks) used for Python coding. Python is a programming language used for data science, specifically: data analysis, statistical analysis, and visualization of results. The training will feature the following IDEs: Google Colaboratory: Jupyter Notebook; and Anaconda’s: Spyder, Jupyter Notebook, and JupyterLab. This overview training will demonstrate how these skills can boost productivity, rigor, and transparency in reporting research findings.  

By the end of the training, attendees will be able to: 

• Recognize four freely available IDEs for python coding 
• Identify fundamental components of python code 
• Understand how and why notebooks support rigor and transparency in analysis 

Attendees are not expected to have any prior knowledge of python coding or the IDEs to be successful in this training.  

If you choose to follow along with Google Colab or Jupyter Notebooks, these IDEs should be installed and ready to go. Code will be provided during the training for this option. 

Single-cell sequencing has become a standard method for understanding the heterogeneity in cell states. Single-nuclei multiomics offers the ability to measure transcriptomic and epigenetic alterations, but preprocessing and visualizing these data is not a straightforward process.

In this webinar, Adam Catching Ph.D. of the Center of Alzheimer's and Related Dementia will go over a peer-reviewed, reproducible, and turn-key method of processing sequenced multiomic data into an integrated and annotated object from which downstream analysis can be performed. The second half of the session will focus on how to present datasets as interactive plots that tackle presenting high-dimensional complex data.

This webinar assumes familiarity with:

• Python
• Biowulf/Slurm HPCs
• Snakemake
• Singularity containers

How do R, GraphPad Prism, and LLM tools compare when analyzing and visualizing differences between groups? This talk will use practical examples to explore parametric and nonparametric approaches, highlighting each tool’s strengths, limitations, and common pitfalls. We’ll discuss choosing appropriate tests, interpreting results, and creating figures that accurately communicate the evidence.

At this time, this workshop is only for NIH-affiliated staff & scientists only. Please use your NIH email when registering. 

Join Allen Institute scientists for a one-day, hands-on workshop at NIH focused on helping researchers explore and use cell type taxonomy data and tools from the Brain Knowledge Platform. The workshop will begin with an accessible overview of what cell types are and how they are defined, followed by guided tutorials and interactive exercises using resources for exploring open datasets such as the Allen Brain Cell Atlas. Designed to be highly interactive and applicable across experience levels, the workshop will combine short presentations with individual and guided hands-on time to help participants build practical skills and confidence in applying these tools to their own research and teaching. 

Breakfast, coffee/tea, and lunch will be provided. Registration is free, but required. There is a hybrid option for lectures only, please still register if you need the remote option.

Agenda:
9:00-9:30 Check-in / breakfast

9:30-9:40 Welcome, logistics, overview of the Allen Institute 9:40-10:05 Cell typing at the Allen Institute: taxonomies, data sets, and use cases 10:05-10:30 Deep-dive into the human and mammalian brain atlas 10:30-10:40 Break 10:40-11:05 Localizing cell types with spatial transcriptomics 11:05-11:30 Cell-type targeted enhancer development 11:30-11:55 Deep-dive into the Seattle Alzheimer's disease brain cell atlas 11:55-12:10 Overview of Brain Knowledge Platform tools and resources 12:10-12:15 Preview of afternoon tracks 12:15-1:15 Lunch --- Breakout session 1: Connecting multimodal data to brain cell types 1:15-1:35 Defining and using common coordinate frameworks  1:35-1:55 Patch-seq overview and tools for analysis  1:55-2:30 Additional multimodal datasets from Allen  --- Breakout session 2: Analysis of your own sequencing data using Allen Institute resources 1:15-1:45 Cell type analysis, taxonomy creation, and mapping  1:45-2:10 Cross-species alignment and comparative analyses  2:10-2:30 Other interactive tools for -omics data exploration   --- 2:30-2:40 Break 2:40-3:00 ABC Atlas demo & external use case examples 3:00-3:30 User exploration of Allen Institute tools  3:30-3:45 Tool feedback and Discussion 3:45-4:00 Workshop Survey / closing of formal program 4:00-5:00 Additional time for user exploration

AI-ready science is constrained less by model sophistication than by the shortage of high-quality, well-described data and by infrastructure that cannot keep pace with evolving methods. Drawing on experiences with FaceBase and the Deriva platform across craniofacial, hearing, and ophthalmology research, we argue that FAIR data largely subsumes "AI-ready" data, and that sustainable repositories follow SCALE principles: Self-service curation, domain-Agnostic platforms, Lightweight models, and Evolvable systems.

As large language model agents become the layer through which researchers interact with data, a further question arises: what makes a repository agent-ready? We propose three architectural requirements—documented service interfaces with full coverage, FAIR metadata annotated with community ontologies, and an introspectable data model with an LLM-aligned query interface—and show how an agent built on them can mediate the full research lifecycle, from discovery through citable dataset assembly to curation of results back into the repository, capturing experimental context that artifact-level reproducibility alone cannot.

Partek Flow is a point-and-click platform for building analysis workflows for Next Generation Sequences (NGS), including DNA, bulk and single-cell RNA, spatial transcriptomics, ATAC, and ChIP, helping scientists avoid the steep learning curve of code-based NGS analysis. In this demonstration-only class, an Illumina scientist will show steps for spatial transcriptomics analysis including QC, exploratory analysis, batch effect removal, integration of spatial and gene expression information, as well as differential expression and pathway analysis.  No prior experience or access to Partek Flow is required. Attendance is limited to NIH staff.

This one-hour and thirty minute online training is part one of an introductory two-part series for those who want to learn about research data management and sharing, or for those who are interested in a refresher. The series provides detailed information on managing and sharing data from the first data planning stage, through the data life cycle, to data archiving, and finally to selecting an appropriate repository for data preservation.   

By the end of part one of this training series, attendees will be able to:   

• Understand data management best practices   

• Become familiar with data management tools  

• Have a solid knowledge of the resources, enabling data sharing  

During Part 2, attendees will learn about sharing and archiving data. You must register separately for Part 2 of this training. This training is introductory, no prior knowledge required.  

This hour and half online training is part two of an introductory two-part series for those who want to learn about research data management and sharing, or for those who are interested in a refresher. The series provides detailed information on managing and sharing data from the first data planning stage, through the data life cycle, to data archiving, and finally to selecting an appropriate repository for data preservation.  

By the end of part two of this training series, attendees will be able to:   

• Have a solid knowledge of the resources, enabling data sharing  

• Understand how data is archived and preserved  

Part 1 of this training covers understanding research data, how to manage research data, and how to work with data. During Part 2, attendees learn about sharing and archiving data. This training is introductory, no prior knowledge required.  

You must register separately for Part 1 of this training.