Classes & Events

This lesson reviews many of the standard steps in a scRNA-Seq workflow: QC filtering, normalization, scaling, and clustering. 

To register to attend, you must log in to your SITC Cancer Immunotherapy CONNECT account. Don’t have an account? Create a free one.

Join Dr. Mullin of the Roswell Park Comprehensive Cancer Center and Dr. Bao of the UPMC Hillman Cancer Center as they talk about artificial intelligence’s (AI’s) role in real-time monitoring of patients who are receiving immunotherapy for immune-related adverse events (irAE).

If you attend, you’ll learn about:

• the current application of AI in irAE monitoring and detection.
• future applications of these technologies across the field.

This webinar is the first of the 2024 SITC-NCI Computational Immuno-oncology Webinar Series, which focuses on the application of AI in immuno-oncology. It consists of nine free webinars to help individual research labs overcome computational challenges while analyzing and integrating different assay data throughout the immuno-oncology spectrum using AI. The annual series aims to educate early-career scientists, increase participants’ awareness of and engagement in NCI-supported Cancer Moonshot℠ Immunotherapy Networks, and fulfill the Blue Ribbon Panel’s goal of accelerating progress in cancer research.

The explosion of biomedical big data and information in the past decade or so has created new opportunities for discoveries to improve the treatment and prevention of human diseases. As such, the field of medicine is undergoing a paradigm shift driven by AI-powered analytical solutions. This talk explores the benefits (and risks) of AI and ChatGPT, highlighting their pivotal roles in revolutionizing biomedical discovery, patient care, diagnosis, treatment, and medical research. By demonstrating their uses in some real-world applications such as improving biomedical literature searches (Nature Biotechnology 2018; Nature 2020; Nature Genetics 2023), accelerating patient trial matching (TrialGPT, in collaboration with NCI clinicians), and assisting gene set analysis (GeneAgent, in collaboration with NCI researchers), we underscore the potential of AI and ChatGPT in enhancing clinical decision-making, personalizing patient experiences, and accelerating knowledge discovery.

Alternative Meeting Information: Meeting number: 2300 950 8025 Password: qiQsnDx?923 Join by video system Dial 23009508025@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2300 950 8025  

Have you been looking for ways to use artificial intelligence (AI) in clinical practice but not sure where to start? Attend this webinar for tips from Dr. Anant Madabhushi on applying AI in precision oncology. He’ll describe how AI can be affordable, easy to interpret, and help ensure more equitable care for every patient. Specifically, Dr. Madabhushi will discuss efforts by his group to develop AI-based approaches for measuring:

• alterations in the immune architecture underlying diseases (i.e., collagen disorder) using AI and pathology images, and
• changes in tumor blood vessels (vessel tortuosity) using AI and radiologic scans.

He’ll describe how biomarkers like these can help you predict how well a patient will respond to treatment, as well as monitor their response.

Dr. Madabhushi has been on the forefront of translating lab-created technologies into clinical practice. He’s pioneered the use of AI in precision oncology, offering new solutions for diagnosing cancers (i.e., breast, prostate, lung) and predicting how patients will respond to cancer treatments, such as chemotherapy, immunotherapy, and protein inhibitors (i.e., cyclin-dependent kinase 4 and 6).

The Cancer Imaging Program is part of NCI’s Division of Cancer Treatment & Diagnosis. The program hosts this monthly NCI Imaging Community Webinar Series for scientists and clinicians interested in advancing cancer imaging. If you want to learn about upcoming opportunities for engagement, interdisciplinary collaboration, and current research showcases, you can explore upcoming events on the webinar series’ webpage.

Dr. Anant Madabhushi is the Robert W. Woodruff Professor of Biomedical Engineering and serves on the faculty of the departments of pathology, biomedical informatics, urology, radiation oncology, radiology and imaging sciences, global health and computer and information sciences, all at Emory University. He’s also a research career scientist at the Atlanta Veterans Administration Medical Center. And he’s director of the Emory Empathetic AI for Health Institute at Emory University. Dr. Madabhushi has authored more than 500 peer-reviewed scientific publications and holds (or has pending) over 200 patents in the areas of AI, radiomics, medical image analysis, computer-aided diagnosis, and computer vision.

Macros are ways to use code to substitute in a value, and using macros makes a code in SAS easier to read, easier to edit, less prone to errors,  and often allows it to run more efficiently. This intermediate class will provide an overview of what is a macro and how macros work in SAS, including the macro facility. Examples of macro code will be made available to class participants for modification and later use.

Galaxy is a scientific workflow, data integration, data analysis, and publishing platform that makes computational biology accessible to research scientists that do not have computer programming experience. This workshop will introduce RNA-seq data analysis followed by tutorials showing the use of popular RNA-seq analysis packages and preparing participants to independently run basic RNA-Seq analysis for expression profiling. The hands-on exercises will run on the Galaxy platform using Illumina paired-end RNA-seq data. The workshop will be taught by NCI staff and is open to NIH and HHS staff.

Presented as part of the Sequencing Strategies for Population and Cancer Epidemiology Studies (SeqSPACE) Webinar Series

Dr. Philip Lupo is a professor of pediatrics and hematology-oncology at Baylor College of Medicine. His lab focuses on the molecular epidemiology of pediatric disease and conditions. His areas of interest include understanding the risk of cancer among children with structural birth defects, determining inherited genes underlying susceptibility to rhabdomyosarcoma, phenomic and genomic studies of structural birth defects, and addressing disparities in acute lymphoblastic leukemia susceptibility and outcomes. In this webinar, Dr. Lupo will be presenting on leveraging population-based registries for genomic studies of pediatric cancer.

For more information, contact Leah Mechanic.

If you’re a researcher, clinician, informaticist, commercial partner, or policy maker interested in cancer data science, register to attend this Cancer Data Exchange Summit.

You’ll have the opportunity to hear (and take part in) discussions around current opportunities and challenges with the following topics:

• How to use a patient’s data to determine their eligibility for clinical trials
• How to identify and develop data standards to detect immune-related adverse events
• Ways to enhance the efficiency and timeliness of the collection of cancer registry data
• Ways to support patient access, interoperability, and data sharing

You can also help identify cancer-specific elements; develop implementation guides; and define requirements to build large language models for extracting data.

The participant group will comprise researchers, clinicians, informatics/data scientists, patient advocates, standard-setting organizations (such as HL7/FHIR), policymakers, EHR vendors, and industry partners. Their collaborative efforts will focus on identifying current opportunities, challenges, and essential oncology-specific data requirements for the USCDI+ Cancer use cases (1) using real-world data to determine patient eligibility for clinical trials; (2) identifying immune-related adverse events; (3) enhancing the efficiency and timeliness of cancer registry data.

Qlucore Omics Explorer is a point-and-click software that enables analysis of RNA sequencing (bulk and single cell), proteomics and metabolomics data. It’s machine learning capabilities also allow for classification of cell types. This software is available to NCI CCR scientists. In this session, participants will learn to analyze bulk RNA sequencing data using Qlucore Omics Explorer. Topics discussed include experimental design, data import, normalization, differential expression analysis, and biological interpretation in and outside Qlucore (i.e. GSEA, pathway visualization, biological networks, GO enrichment). Experience using this software is not required to attend. Participants are encouraged to install Qlucore Omics Explorer by submitting a ticket with the NCI computer service desk (service.cancer.gov) prior to the event.

Meeting link:
https://cbiit.webex.com/cbiit/j.php?MTID=mbcf05ad560604862467c52417b2c399b
Meeting number:
2303 382 3263
Password:
NTmpQhY@733

Join by video system
Dial 23033823263@cbiit.webex.com
You can also dial 173.243.2.68 and enter your meeting number.

Join by phone
1-650-479-3207 Call-in number (US/Canada)
Access code: 2303 382 3263

This one-hour session will introduce attendees to the world of Artificial Intelligence (AI) as we explore the fundamentals, applications, and ethical considerations of this transformative technology. Key topics will include machine learning, deep learning, data handling, and real-world AI applications across various industries. We'll delve into the ethical implications of AI and offer insights on how to become AI literate. Whether you're a seasoned professional or just starting your AI journey, this session will equip you with essential knowledge to navigate the AI landscape effectively and make informed decisions in our data-driven world.

This is the first class in the NIH Library Introduction to R Series. This class provides a basic overview of the functionality of R programming language and RStudio. R is a programming language and open source environment for statistical computing and graphics. The R class series is a comprehensive collection of training sessions offered by the NIH Library Data Services and Bioinformatics programs that is designed to teach non-programmers how to write modular code and to introduce best practices for using R for data analysis and data visualization. Each class uses both evidence-based best practices for programming and practical hands-on lessons.

By the end of this class, students should be able to: list reasons for using R; describe the purpose of the RStudio Script, Console, Environment, and Plots panes; describe the various methods for finding help on R and RStudio; organize files and directories for a set of analyses as an R Project; define the following terms as they relate to R: object, assign, comment, call, function, and arguments; and assign values to objects in R.

Students are encouraged to install R and RStudio before the class so that they can follow along with the instructor. Please bring your laptop with R and RStudio installed.

This in-person workshop will focus on data wrangling using tidy data principles. Tidy data describes a standard way of storing data that facilitates analysis and visualization within the tidyverse ecosystem. There will be a discussion of what makes data "tidy," and methods for reshaping your data using dplyr and tidyr functions. Prior to attending this class, you will need to have:

1. Installed R and RStudio
2. Taken the Introduction to R and RStudio class. If not, here are some resources for getting started:
   1. Introduction to R
   2. Introduction to RStudio
   3. Introduction to Scripts in RStudio

By the end of this class, attendees will be able to demonstrate how to describe the purpose of the dplyr and tidyr packages, select certain columns in a data frame, select certain rows in a data frame according to filtering conditions, and add new columns to a data frame that are functions of existing columns.

Note on Technology

The NIH Library has 24 pre-configured Windows laptops that you are welcome to use during this training on a first come, first served basis. You are also welcome to bring your own laptop (PC or Mac). NIH Staff bringing their own NIH-laptop can easily connect to the staff Wi-Fi. If participants are bringing a personal laptop, they are restricted to using the NIH-Guest-Network Wi-Fi.

Registrants will receive an email with information and instructions to install and verify access to R and RStudio before the class.  If you register the day before the class, you may not have time to download and properly install the necessary software. If you do not have the software installed, this training will be demo only.

Participants will learn how to develop artificial intelligence (AI) applications using MATLAB, even if they do not have a formal background in machine and deep learning. The goal of this course is to introduce tools and fundamental approaches for developing predictive models on biomedical signals. The course will cover the entire AI pipeline, from signal exploration to deployment, including: annotating time series biomedical signals automatically, creating deep learning models using Convolutional Neural Networks (CNNs) and Long Short-Term Memories (LSTMs) for biomedical signal data, creating machine learning models for biomedical signal data, applying advanced signal pre-processing techniques for automated feature extraction, and automatically generating code for edge deployment of AI models.

This is an introductory level class. No installation of MATLAB is necessary.

To register to attend, you must log in to your SITC Cancer Immunotherapy CONNECT account. Don’t have an account? Create a free one.

Join Dr. Karchin of the Johns Hopkins School of Medicine and Dr. Krieg of the Medical University of South Carolina as they discuss the novel use of artificial intelligence (AI) in immunotherapy target discovery.

Attend this webinar to learn how:

• AI advances could quickly improve clinical care.
• you can use AI to better analyze large-scale data sets for biomarkers that can enhance immunotherapy research.

This webinar is part of the 2024 SITC-NCI Computational Immuno-oncology Webinar Series, which focuses on the application of AI in immuno-oncology. This is the second of nine free webinars to help individual research labs overcome computational challenges while analyzing and integrating different assay data throughout the immuno-oncology spectrum using AI. The annual series aims to educate early-career scientists, increase participants’ awareness of and engagement in NCI-supported Cancer Moonshot℠ Immunotherapy Networks, and fulfill the Blue Ribbon Panel’s goal of accelerating progress in cancer research.

Generalist repositories offer NIH researchers a flexible, trusted resource to share data for which there is no appropriate discipline specific repository as well as to share many other research outputs valuable for reproducibility and open science. This webinar, presented by participants of the NIH Generalist Repository Ecosystem Initiative (GREI) (Dataverse, Dryad, Figshare, Mendeley Data, Open Science Framework, Vivli, and Zenodo) will share generalist repository use cases and best practices for sharing and finding data in generalist repositories. It will describe how generalist repositories fit into the NIH data repository landscape for intramural researchers and can be part of meeting the new NIH Data Management and Sharing Policy requirements. It will present both the key common features of generalist repositories that meet the NIH desirable repository characteristics as well as the unique features of these repositories that make them suited to specific types of data. 

This course 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 this course, participants will have an understanding of data management best practices, data management tools, and resources that enable data sharing.

This is an introductory two-part course for those who want to learn about research data management and sharing, or for those who are interested in a refresher. Part 1 of this training will cover understanding research data, how to manage research data, and how to work with data. Audience: Researchers, fellows, post-docs, and trainees. You must register separately for Part 2 of this class.

Qiagen CLC Genomics Workbench is a point-and-click bioinformatics software that runs on a personal computer and enables bulk RNA sequencing, ChIP sequencing, long reads, and variant analysis. This software is available to NCI scientists.

This hands-on training will guide participants through bulk RNA sequencing analysis using CLC Genomics Workbench. After the class, participants will be able to

• Import files and illumina reads
• Import and associate metadata with samples
• Download reference genome and annotation
• Obtain RNA sequencing expression counts and perform differential expression analysis
• Construct PCA and heatmap to visualize RNA sequencing data

 

To get the most of this hands-on session, please reach out to the NCI service desk (https://service.cancer.gov/ncisp) to get this software installed, preview the tutorial (https://resources.qiagenbioinformatics.com/tutorials/RNASeq-droso.pdf), and download the example dataset (http://resources.qiagenbioinformatics.com/testdata/RNA_Seq_Droso2.zip) prior to attending.

Meeting link:
https://cbiit.webex.com/cbiit/j.php?MTID=m07f826d16b67d3c3b8a86e275ebac5a5
Meeting number:
2300 281 6121
Password:
e7aEqhpy@34

Join by video system
Dial 23002816121@cbiit.webex.com
You can also dial 173.243.2.68 and enter your meeting number.

Join by phone
1-650-479-3207 Call-in number (US/Canada)
Access code: 2300 281 6121

The NIH Artificial Intelligence (AI) Symposium will take place on Friday, May 17th, 2024, in Masur Auditorium in Building 10 on the Bethesda NIH campus. This event is open to all NIH members - registration and abstract submission are now open https://forms.microsoft.com/g/4WpdBXcEu6

Biomedical science is in a technological revolution, driven by innovations in deep learning architecture and computational power. These cutting-edge techniques are being applied to every sub-field of the biological sciences, and with ground-breaking advancements arriving constantly it is challenging for researchers to stay up to speed on what is possible. This one-day NIH AI Symposium will bring together researchers from a broad range of disciplines to share their AI-related research, with the goal of disseminating the newest AI research, providing an opportunity to network, and to cross-pollinate ideas across disciplines in order to advance AI research in biomedicine.

Keynote speakers James Zou, Ph.D. (Stanford University) and Hari Shroff, Ph.D. (Janelia Research Campus) will share their research, and also participate in a Panel Discussion on the current and future potential of AI in biomedical sciences. There will also be short talks and posters from researchers on campus who are developing or using AI approaches.

The NIH AI Symposium is sponsored by NHLBI, in partnership with FAES. Registration and abstract submission are open to all NIH members, including experts in AI-related fields and novices interested in gaining more exposure.

Important dates:

March 15th - Abstract submission deadline

April 5th - Abstract notifications

May 3rd – Registration deadline

Sign language interpreting and CART services are available upon request to participate in this event. Individuals needing either of these services and/or other reasonable accommodations should contact Ryan O’Neill (oneillrs@nih.gov).

Questions can be directed to Lead Organizer Ryan O’Neill, Ph.D. (oneillrs@nih.gov).

This course 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 this course, participants will have an understanding of data management best practices, data management tools, and resources that enable data sharing.

This is an introductory two-part course for those who want to learn about research data management and sharing, or for those who are interested in a refresher. During Part 2 of this training, participants will learn about sharing and archiving data. Audience: Researchers, fellows, post-docs, and trainees. You must register separately for Part 1 of this class.

This seminar provides an overview of differential expression testing workflows with Seurat.

Are you attending the 2024 AMIA Clinical Informatics Conference? Join NCI Fellow, Austin Fitts, as he presents on the National Childhood Cancer Registry (NCCR) during the May 22 afternoon sessions. The NCCR links cancer registry data with harmonized real-world data for population-level research in childhood cancer. He will also share how NCCR’s harmonization process allows for more longitudinal studies and can serve as a model for similar data harmonization initiatives. There are future plans to publish the NCCR data model and make an initial harmonized data set available to the cancer research community through the upcoming NCCR Data Platform.

Session Title: Advancing the Usability of Healthcare Data

Austin Fitts, Pharm.D., is a post-doctoral fellow at NCI’s Surveillance Research Program. He completed his Doctor of Pharmacy degree from University of Mississippi School of Pharmacy in 2021. Dr. Fitts completed residencies in hospital pharmacy at North Mississippi Medical Center and pharmacy informatics at Vanderbilt University Medical Center. His current professional interests include pharmacy informatics, pediatric oncology, and pharmacoepidemiology.

Versioning enables researchers to track changes in coding projects. This Coding Club introduces Git (https://git-scm.com), an open-source software used to perform versioning on a personal computer. At the end of this class, participants will:

Versioning enables researchers to track changes in coding projects. This Coding Club introduces Git (https://git-scm.com), an open-source software used to perform versioning on a personal computer. At the end of this class, participants will:

• Understand the importance of versioning
• Describe Git
• Know how to access Git
  • Be aware of resources that helps with Git installation on personal computer
  • Be aware of the availability of Git on Biowulf, the NIH high performance computing system
• Define repository
• Know the steps involved in the versioning process including
  • Initiating a new repository
  • Understanding the difference between tracked and untracked files
  • Excluding files from being tracked
  • Staging files with changes
  • Commiting changes and writing commit messages
  • Viewing commit logs
• Compare between versions of code
• Revert to a previous version of code

Meeting link: https://cbiit.webex.com/cbiit/j.php?MTID=m8d56b3aff91ddd2e6df839d05dda6a8f   Meeting number: 2319 013 9531 Password: dnAnqfP$642 Join by video system Dial 23190139531@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2319 013 9531

An exciting opportunity at the intersection of the biomedical sciences and machine learning stems from the growing availability of large-scale multi-modal data (imaging-based and sequencing-based, observational and perturbational, at the single-cell level, tissue-level, and organism-level). Traditional representation learning methods, although often highly successful in predictive tasks, do not generally elucidate underlying causal mechanisms. Dr. Uhler will present initial ideas towards building a statistical and computational framework for causal representation learning and its applications towards identifying novel disease biomarkers as well as inferring gene regulation in health and disease.

Alternative Meeting Information: Meeting number: 2312 523 4308 Password: rgE4DbPX$65 Join by video system Dial 23125234308@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2312 523 4308  

The symposium's goals are to explore the integration of AI in understanding and managing immunological data, foster a paradigm shift in how immunologists leverage AI to propel their research forward, and inform NIAID about existing AI resources, needs, and future directions to support DAIT. The symposium will:

• Present stimulating use cases covering AI for immunology, e.g., concrete examples where AI has already made significant contributions to immunology
• Identify near-term and long-term challenges and barriers, e.g., address current limitations and challenges facing the integration of AI in immunology
• Discuss the scientific and clinical opportunities empowered by the AI revolution, e.g., how it could revolutionize our understanding of the immune system, lead to groundbreaking treatments, and influence public health policy. 

This is a hybrid meeting where attendees can choose to attend in-person or via Zoom Government.

Speakers and Moderators who are part of this program are expected to attend in person.

In-person registration is required by Tuesday, May 21, 2024

https://web.cvent.com/event/b1808ba5-fb93-4bf9-a253-dc63938869a9/summary

For programmatic questions, please contact dait_ai_workshop@mail.nih.gov.

For meeting logistical questions, please contact Heather Leonard, Lumina Corps, at EventsNIAID@luminacorps.com.

NCI is launching the virtual Cancer AI Conversations series featuring multiple perspectives on timely topics and themes in artificial intelligence for cancer research! 

Each event features short talks from 2-4 subject matter experts offering diverse views on the session topic. These talks will be followed by a moderated panel discussion.

“Cancer AI Conversations” are bimonthly, 1-hour virtual events featuring timely topics related to the application of artificial intelligence in cancer research. Each event features short talks from 2-4 subject matter experts offering diverse perspectives on the session topic. 

All of the Cancer AI Conversations will be recorded and posted for future viewing.

This class provides an overview of options for customizing a ggplot graph. This class will focus on methods for creating small multiples, options for customizing a graph, and how to apply ggplot themes. You must have taken Data Visualization in R: ggplot class to be successful in this class.

By the end of this class, participants should be able to describe options for time series data, create a line plot in ggplot, learn how to facet a plot, demonstrate options for customizing the title and axis, and apply different ggplot themes.

This 90-minute course equips participants with essential knowledge and skills for effective interactions with Large Language Models (LLMs), such as ChatGPT. Explore the intricacies of prompt engineering and its pivotal role in optimizing the conversational capabilities of LLMs. Emphasizing best practices and practical applications, this course features live demonstrations and group discussion, and provides valuable skills for the effective use of LLMs. Attendees are encouraged to register for a free ChatGPT account prior to taking this class. 

Galaxy is a scientific workflow, data integration, data analysis, and publishing platform that makes computational biology accessible to research scientists that do not have computer programming experience. This training will introduce ChIP sequencing data analysis followed by a tutorial showing ChIP-seq analysis workflow.  This workshop will be taught by NCI staff and is open to NIH and HHS staff.

This class is a mixture of lecture and hands-on exercises. By the end of this class, students will be able to: independently run basic ChIP-seq analysis for peak calling, run quality control on ChIP-seq data, map raw reads to a reference genome, generate alignment statistics and check mapping quality, call peaks using MACS, annotate peaks, and visualize the enriched regions.

The Brooks Lab developed a computational tool called FLAIR (Full-Length Alternative Isoform Analysis of RNA) to produce confident transcript isoforms from long-read RNA-seq data with the aim of alternative isoform detection and quantification. With an increase in the usage of long-read RNA-seq, there is a growing need for a systematic evaluation of this approach. We are part of an international community effort called the Long-read RNA-seq Genome Annotation Assessment Project (LRGASP) to perform such an evaluation. The Brooks Lab is extending FLAIR to incorporate sequence variation, RNA editing, and RNA modification in isoform detection as well as detection of complex gene fusions from long-read sequencing data.

  Meeting number: 2311 656 4503 Password: ySkM7uW6B$5 Join by video system Dial 23116564503@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2311 656 4503  

This webinar introduces SimBiology as a modeling environment for mechanistic pharmacokinetic (PK), pharmacodynamic (PD), and quantitative systems pharmacology (QSP) modeling and simulation. Participants will learn how to use the SimBiology Model Builder app to build a mechanistic model and how to use the SimBiology Model Analyzer app to calibrate the model to experimental data, as well as perform model predictions. 

This is an introductory-level class taught by MathWorks. No installation of MATLAB is necessary. 

Large language models (LLMs) are artificial intelligence (AI) algorithms that employ deep learning and extensive data sets to create new content. LLMs offer many possible applications in the biomedical field, such as the development of chatbots for use by clinicians, patients, and researchers. Join this roundtable discussion to learn about current use cases of LLMs at NIH. The program will begin with brief presentations by our panelists, followed by an open discussion:

Alicia Lillich, NIH Library 
Introduction to Large Language Models (LLMs)

Trey Saddler, NIEHS
ToxPipe: Semi-Autonomous AI Integration of Diverse Toxicological Data Streams

Mike A. Nalls, Ph.D., NIA
LLMs to Accelerate Tedious Tasks in Research

Nathan Hotaling, Ph.D., NCATS
Applications of Retrieval Augmented Generative AI to Scientific Discovery, Scientific Management, and Code Development and Maintenance at NCATS

Nicole Sroka, NLM
NLM GenAI Pilot: Customer Response Case Study

Steevenson Nelson, Ph.D., OD
Trans IRP Contract Tool (Updates)

Nick Asendorf, Ph.D., NHLBI
NHLBI Chat

Macros are ways to use code to substitute in a value, and using macros makes a code in SAS easier to read and edit, less prone to errors, and allows it to run more efficiently. This 90-minute advanced class will provide an in-depth look at using and writing macros in SAS. Topics covered in this class include macro function, using SQL and Data Step to create macro variables, indirect references to macro variables, defining and calling a macro, macro variable scope, conditional processing, and iterative processing. 

Python is a programming language used for data science, specifically: data analysis, statistical analysis, and visualization of results. This class will demonstrate integrated development and learning (IDE) platforms for learning Python, the fundamentals of Python coding, and why it is advantageous to develop these skills.  The session will feature the following IDEs: Google Colaboratory: Jupyter Notebook; and Anaconda’s: Spyder, Jupyter Notebook, and JupyterLab.  It will also provide an overview of programming constructs needed to learn Python. Finally, this class will demonstrate why these skills can boost productivity, rigor, and transparency in reporting research findings. 

What are common statistical analyses for continuous data? Can you check whether your continuous outcome is normally distributed? What are the methods when the data are not normal? How do you model the outcome with multiple predictors in regression?

This is a two-hour lecture intended for those doing basic data analysis using R. Basic R programming is a pre-requisite for this course, as is knowledge of basic statistical concepts, such as mean and p-value from statistical hypothesis testing.  This class will be taught by the Clinical Center's Biostatistics and Clinical Epidemiology Service (CC/BCES).

The learning outcomes include: 

• calculating and displaying descriptive statistics, such as center and spread of distribution and boxplots 
• recognizing common continuous probability density functions
• estimating mean and confidence intervals for the center of normally and non-normally distributed data 
• hypothesis testing for one-sample and two-sample 
• linear regression 
• the F-distribution and one-way ANOVA

R code snippets will be shared during the lecture and within lecture notes. The class will be recorded, so you can go back to the material as you begin to do your own modeling. During the class, time will be devoted to explaining the concepts, and code snippets and output and references will be provided for in-depth material. 

Preclass Requirements: You must take the basic R programming and statistical inference – Part I classes as pre-requisite through the NIH Library or have acquired the equivalent knowledge elsewhere prior to registering for this class.

Statistical Software: We will be using R and RStudio for our statistical analysis. R is open source and free. There are versions for Mac OSX, Windows, and Linux. You can download it from https://cran.r-project.org/. Additionally, we will be using RStudio as a graphical interface for R. RStudio is free for everyone to download at https://posit.co/download/rstudio-desktop/. See above for pre-requisites in R programming.

Dr. Irizarry will share findings demonstrating limitations of current
workflows that are popular in single cell RNA-Seq data analysis.
Specifically, he will describe challenges and solutions to dimension
reduction, cell-type classification, and statistical significance
analysis of clustering. Dr. Irizarry will end the talk describing some of his
work related to spatial transcriptomics. Specifically, he will describe
approaches to cell type annotation that account for presence of
multiple cell-types represented in the measurements, a common
occurrence with technologies such as Visium and SlideSeq. He will
demonstrate how this approach facilitates the discovery of spatially
varying genes. Meeting link: https://cbiit.webex.com/cbiit/j.php?MTID=m9dcd9ce21f4fa6b1a8e2d998a88c2c2b    Meeting number: 2317 712 9095 Password: gUKZzp3u76? Join by video system Dial 23177129095@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2317 712 9095  

This in-person hands-on workshop will introduce the Ingenuity Pathway Analysis (IPA), which is available to access from the NIH Library. IPA can be used identify biological relationships, mechanisms, pathways, functions, and diseases most relevant to experimental datasets.

Upon completion of this workshop, participants will  be to able compare different groups at different time points and treatments, perform Analysis Match to compare user data with public data sources, and generate IPA Networks using genes and diseases of interest. 

Session 1 (IPA): 10:00 AM to 12:00 PM

In this session, participants will learn about bioinformatics resources from the NIH Library and learn how to perform pathway analysis using IPA.

Lunch: 12:00 PM to 12:45 PM

Lunch on your own

Session 2 (IPA): 1:00 PM to 2:30 PM

In this session, participants will extend the learning from Session 1 and learn how to mine IPA database for novel discoveries.

Session 3 (CLC): 2:30 PM to 4:00 PM

In this session, participants will learn about CLC Genomics Workbench, including a live demo of the basic features and main functionalities.

Note on Technology

Participants are expected to bring their own laptops to this training. NIH Staff using an NIH-laptop can easily connect to the staff Wi-Fi. If participants are bringing a personal laptop, they are restricted to using the NIH Public Wi-Fi. 

Registrants will receive an email with information and instructions to install and verify access to IPA before the class.  If you register the day before the class, you may not have time to download and properly install the necessary software. If you do not have the software installed, this training will be demo only.

In this in-person session, participants will have an opportunity to discuss their own research and use of Qiagen products with Qiagen scientists.

Note on Technology

Participants are expected to bring their own laptops to this training. NIH Staff using an NIH-laptop can easily connect to the staff Wi-Fi. If participants are bringing a personal laptop, they are restricted to using the NIH Public Wi-Fi. 

CARD is a collaborative initiative of the National Institute on Aging and the National Institute of Neurological Disorders and Stroke that supports basic, translational, and clinical research on Alzheimer’s disease and related dementias. CARD’s central mission is to initiate, stimulate, accelerate, and support research that will lead to the development of improved treatments and preventions for these diseases.

Alternative Meeting Information:  Meeting number: 2310 497 7985 Password: mjPjjmi$473 Join by video system Dial 23104977985@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2310 497 7985  

During this webinar, participants will enhance their technical skills and proficiency with MATLAB by navigating online MATLAB resources designed to augment the learning experience and problem-solving capabilities, including documentation, examples, and community forums. In addition, this webinar will also present a preview of upcoming webinars, featuring cutting-edge topics and expert insights. 

This is an introductory-level class taught by MathWorks. No installation of MATLAB is necessary. 

Kerry Goetz, Ph.D.

Meeting number: 2302 034 0947 Password: juFCdpx$627 Join by video system Dial 23020340947@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2302 034 0947  

The Elemento lab combines Big Data analytics with experimentation to develop entirely new ways to help prevent, diagnose, understand, treat and ultimately cure disease. Our research involves routine use of ultrafast DNA sequencing, proteomics, high-performance computing, mathematical modeling, and artificial intelligence/machine learning. We’re revolutionizing healthcare by developing innovative approaches to better predict, diagnose, treat, and prevent disease to improve clinical care for every patient.  

Alternative Meeting Information: Meeting number: 2319 759 4122 Password: Join by video system Dial 23197594122@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2319 759 4122  

Dr. Mardis is an internationally recognized expert in cancer genomics, with ongoing interests in the integrated characterization of cancer genomes, defining DNA-based somatic and germline interactions and RNA-based pathways, and immune microenvironments that lead to cancer onset and progression, specifically involving pediatric cancers. Most recently, her research has been oriented toward translational aspects of cancer genomics, specifically identifying how the cancer genome changes with treatment, including acquired resistance, the use of genomics in understanding immune therapy response, and the clinical benefit of cancer molecular profiling in the pediatric setting.

Alternative Meeting Information: Meeting number: 2312 714 2024 Password: GrddnZQ*248 Join by video system Dial 23127142024@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2312 714 2024  

Dr. O'Neill's research programs employ molecular genetics, genomics and computational approaches to study the mechanisms that maintain, and disrupt, genome stability with a particular focus on repetitive elements. Projects include studying: retroelement transcription and centromere function; novel small RNA biogenesis pathways; and global chromosome and genome changes during instability (such as in cancer and hybrid dysgenesis). In addition, we use a diverse set of rapidly evolving next generation sequencing (NGS) technologies and novel library preparation and computational methodologies for drafting and characterizing genome sequences in efforts to establish broad eukaryotic species as models for studying genome biology. Recently, Dr. O'Neill's lab has expanded their efforts towards applying broad NGS techniques to both model and non-model systems to understand the dynamic response of the genome to environmental queues, such as global warming.

Meeting number: 2315 524 3558 Password: JEexR5Jq@63 Join by video system Dial 23155243558@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2315 524 3558

The goal of Artificial Intelligence Resource (AIR) is to make AI tools available to Center for Cancer Research (CCR) investigators. The strength of AI is that algorithms can be trained to seek specific information that may be scientifically or clinically important.  AIR will mainly focus on “Computer Vision” which analyzes medical images, such as radiologic, digital pathology, video/endoscopy, and optical imaging among others.  Examples of potential projects include developing better screening, detection methods or predictive markers, or improving procedures among many others. Both clinical and laboratory-based imaging projects will be considered. Please refer to our ongoing projects and prior publications for more information.

Dr. Blackshaw's work examines the molecular basis of neuronal and glial cell fate specification and survival, focusing on characterizing the network of genes that control specification of different cell types within the retina and hypothalamus, two structures that arise from the embryonic forebrain.  The ultimate goal is to use insights gained from learning how individual cell types are specified to understand how these cells contribute to the regulation of behavior, and how they can be replaced in neurodegenerative disease.

Meeting number: 2312 437 6963 Password: bMrGtiA@933 Join by video system Dial 23124376963@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2312 437 6963  

David M. Reif, Ph.D., joined the NIEHS in 2022 as Chief of the Predictive Toxicology Branch (PTB) in the Division of Translational Toxicology (DTT). In this role, he will leverage expertise of the branch in data science, toxicogenomics, spatiotemporal exposures and toxicology, computational methods development, and new approach methods (NAMs) to advance predictive toxicology applications with partners across NIEHS, the interagency Tox21 Program and the Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM).

Meeting number: 2318 207 2771 Password: 5DMpVr5Mt5@ Join by video system Dial 23182072771@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2318 207 2771  

The primary theme of Dr. Bult's personal research program is “bridging the digital biology divide,” reflecting the critical role that informatics and computational biology play in modern biomedical research. Dr. Bult is a Principal Investigator in the Mouse Genome Informatics (MGI) consortium that develops knowledge-bases to advance the laboratory mouse as a model system for research into the genetic and genomic basis of human biology and disease. Recent research initiatives in Dr. Bult's research group include computational prediction of gene function in the mouse and the use of the mouse to understand genetic pathways in normal lung development and disease.

Join information Alternative Meeting Information: Meeting number: 2309 763 3797 Password: GmUAeeZ@236 Join by video system Dial 23097633797@cbiit.webex.com You can also dial 173.243.2.68 and enter your meeting number. Join by phone 1-650-479-3207 Call-in number (US/Canada) Access code: 2309 763 3797