Bioinformatics Training & Education Program

Global Cancer Research and Control Seminar Series

In this session, Dr. Anant Madabhushi will highlight the development of radiopathomics, an AI-driven framework that integrates radiology and digital pathology to capture tumor heterogeneity across spatial scales for improved diagnosis, prognosis, and therapeutic response prediction. He will present validation studies across multiple cancers demonstrating how these multimodal biomarkers can inform treatment selection, anticipate resistance, and enable more precise, personalized oncology care.

    Note: We highly recommend taking the Getting Started with AI Productivity Double Feature and From Prompt to Process classes prior to this.   What if you could create an AI assistant that understands your work and helps you complete recurring tasks faster and more consistently? In this session, you will learn how to transform effective prompts and workflows into reusable AI assistants using custom GPTs and agent-style tools. Participants will explore how to design assistants that can draft communications, analyze documents, guide processes, and support common NIH workflows—reducing repetitive work and improving productivity. By the end of the session, you will understand when to build a custom assistant, how to structure its instructions and guardrails, and how to deploy AI helpers that save time while keeping human expertise in control.

The second session of the Python Introductory Education Series covers basic Python concepts, including data types, structures, variables, conditionals, loops, and iterators. Prior experience is not needed. Access to NIH's High Performance Computing System (Biowulf) is recommended for the hands-on exercises; if unavailable, one of the 30 in-class use only accounts will be provided to the participant. Please email instructor at wuz8@nih.gov if you need a Biowulf student account.

Advanced ChatGPT training is part 3 of a three-part series. 

This 90-minute online training, led by OpenAI experts, is for those who have completed the ChatGPT 101 and 102 trainings. The training will focus on leveraging two of ChatGPT Enterprise's most powerful features: Custom GPTs and Data Analysis. Attendees will learn how to create specialized GPTs tailored for specific NIH tasks and how to use the Data Analysis feature to upload, interpret, and visualize data sets for deeper insights. This training is designed to provide the skills needed to apply these advanced tools to complex, enterprise-level projects. 

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

• Build and deploy Custom GPTs tailored to specific NIH workflows. 

• Use the Data Analysis feature to upload, analyze, and visualize data. 

• Apply advanced techniques to solve complex problems using ChatGPT Enterprise. 

Attendees are expected to be able to utilize ChatGPT to be successful in this training.  

M365 Copilot in Action: Supercharge Your Workday!

This class of the Python Introductory Education Series will introduce participants to working with and wrangling tabular data using the package, Pandas. Experience with Python is not needed for attendance.  Access to NIH's High Performance Computing System (Biowulf) is recommended for the hands-on exercises; if unavailable, one of the 30 in-class use only accounts will be provided to the participant. Please email instructor at wuz8@nih.gov if you need a Biowulf student account.

This interactive workshop introduces participants to the use of virtual reality (VR) in UCSF ChimeraX for immersive visualization of protein structures. VR can provide a unique inside-out view of the structures that can reveal insights not easily observable otherwise. Attendees will learn how to load, manipulate, and analyze macromolecular models in a VR environment, gaining an intuitive understanding of protein architecture, ligand binding sites, and molecular interactions. We refer to this as “Molecular Spelunking” as the experience gives an analogous sensation to cave exploration. The session will cover hardware requirements, navigation tools, and practical use cases in research and education, with live demonstrations and guided practice. By the end of the workshop, participants will be equipped to integrate VR-based molecular visualization into their own structural biology workflows and training activities. Previous familiarity with ChimeraX will be very helpful but not required.

This 90-minute online training led by Google experts is the capstone session for power users who want to push the boundaries of AI in biomedical research. This session showcases advanced agentic workflows and complex comparative analysis. The training will feature a demo on building sophisticated research assistant agents with Agent Designer and will demonstrate additional NotebookLM use cases for research. 

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

• Design a complex, multi-agent system in Agent Designer capable of automating a research sub-task, such as finding and comparing experimental protocols. 
• Apply advanced NotebookLM techniques to perform complex comparative analysis on diverse scientific data sources. 
• Develop strategies for using AI to analyze a portfolio of grants and publications to identify alignment with NIH strategic priorities. 

Attendees are expected to be able to independently utilize Gemini to be successful in this training.  Gemini for Government can be accessed at: https://go.hhs.gov/gemini  

This BTEP Coding Club will demonstrate the utility of R's GT and GT Summary packages for creating publication quality data tables. Participants will see how to add custom table titles, create summaries, add statistics, and table footnotes. Experience and installation of R, GT, and GT Summary are not required for participation.

Posit AI Capabilities Demo

Dr. Bocks' research utilizes a synergistic "READ, LEARN, WRITE" framework that combines multi-omics profiling, deep learning, and high-throughput CRISPR screening to map, model, and program complex cellular functions. By integrating single-cell technologies to read epigenetic states with advanced neural networks to learn their regulatory circuits, he can systematically design and write new biological instructions into human cells. His group successfully applied this integrated approach to optimize immunotherapy, using large-scale in vivo CRISPR screens to identify and validate gene knockouts that significantly boost the performance of CAR T cells against solid tumors.

This 30-minute online training provides a high-level overview of recent developments in artificial intelligence (AI). Each session highlights emerging trends, tools, and use cases in the evolving AI landscape, with an emphasis on practical relevance and responsible use. Whether you're just getting started or looking to stay current, this training offers timely insights in a concise format.  

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

• Summarize key trends and developments in AI 

• Identify new tools, capabilities, or applications relevant to their work 

• Describe considerations for ethical and responsible use of AI technologies 

Attendees are not expected to have any prior knowledge to be successful in this training. 

The NIAID's Bioinformatics and Computational Bioscience Branch (BCBB) is presenting a webinar for anyone wanting to become proficient in running common statistical analyses using the R language. 

Background: Introduction to statistical testing in R, with hands-on practice using biological data. Topics include one-sample and two-sample t-tests, ANOVA, multiple comparisons, linear regression, and and tests for categorical data such as the chi-square test.

This class will wrap up the Python Introductory Education Series by showing participants how to create data visualizations. Experience with Python is not needed for attendance. Access to NIH's High Performance Computing System (Biowulf) is recommended for the hands-on exercises; if unavailable, one of the 30 in-class use only accounts will be provided to the participant. Please email instructor at wuz8@nih.gov if you need a Biowulf student account.

Slide Smarter: M365 Copilot for PowerPoint

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.

This one hour online training, presented by speakers from NIH Cloud Lab, will provide an overview of the generative artificial intelligence (AI) services across three major cloud service providers (CSPs), including Amazon Web Services (AWS), Microsoft Azure, and Google Cloud, and the steps to follow for setting up AI chatbots in cloud environments. This training will also offer time for a question-and-answer session, where participants can ask the speakers questions about development of AI chatbots using large language models (LLMs) in a cloud environment and use of NIH Cloud Lab. 

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

• Compare/contrast the capabilities of generative AI services across the three major cloud service providers (CSPs) 
• Evaluate (informally) the experience in setting up chatbot functionality with the cloud environments 
• Highlight relative strengths, weaknesses, and optimal use cases for each CSP’s generative AI offerings 

Attendees are not expected to have any prior knowledge of generative AI to be successful in this training

AI tools are generating measurable time savings for clinicians, yet those savings rarely return to the healthcare provider. Health systems convert efficiency into expanded capacity while bureaucratic demands that AI cannot touch continue to grow. This talk examines the forces driving that gap, from Jevons Paradox to the "reverse centaur" dynamic in which workers serve the machine rather than the other way around, and asks what a genuinely human-centered model of clinical AI would require. It closes with a provocation drawn from fiction: that the real promise of AI is not more productivity, but the permission to attend to what medicine was always supposed to be about.

This one and a half-hour online training covers the basic principles of FAIR (Findable, Accessible, Interoperable, Reusable) data and why it is important to make your data FAIR.  

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

• Define FAIR data   

• Explain what purpose FAIR data serves 

• Apply FAIR data principles to make data findable, accessible, interoperable, and reusable 

This is an introductory level training. 

This 90-minute online training led by Google experts will introduce the foundational features of Gemini for Government, tailored specifically to accelerate research and enhance productivity within NIH workflows. This training will focus on immediate, high-impact use cases that solve everyday challenges, from drafting manuscripts to communicating scientific findings more effectively. Attendees will learn how to leverage Gemini for Government's secure, AI-powered tools to streamline tasks and will get a first look at the future of research automation with agents. 

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

• Utilize Gemini for Government to accelerate daily tasks, including drafting manuscript sections and analyzing meeting notes. 
• Transform a text-based research summary into a clear and effective visual concept for an infographic. 
• Perform natural language semantic searches to instantly find and synthesize information from scientific publications. 
• Describe the potential of agents to automate research workflows. 

Attendees are not expected to have any prior knowledge of the tool to be successful in this training. Gemini for Government can be accessed at: https://go.hhs.gov/gemini  

This two-hour virtual roundtable discussion will explore the evolving role of artificial intelligence (AI) in research impact analysis. The program will begin with brief presentations by our panelists, followed by an open discussion. Research impact analysis uses quantitative and qualitative approaches to examine publications, citations, collaboration networks, and other indicators of scientific contribution. With the rapid advancement of generative AI and machine learning tools, new methods are emerging to enhance content analysis, trend identification, visualization, and interpretation of research outputs.  

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

• Describe how AI-driven techniques can enhance research impact analysis in the biomedical field 

• Identify emerging AI tools and methods for citation, content, and trend analysis 

• Provide examples of how AI-informed research impact analysis can support planning, evaluation, and reporting at NIH  

Attendees are not expected to have any prior knowledge of research impact analysis techniques or tools.  

Presenters:

• Joelle Mornini, NIH Library 
  Using ChatGPT to Create Visualizations
• Troy Zarcone, NIGMS  
  Surviving the AI Bubble: Staying on the Cutting Edge While Avoiding the Bleeding Edge
• Comfort Kai, OD 
  Lauren Oliveira Hashiguchi, NINR 
  Esther Yui, NINR  
  Research to Insights: Prompting AI to Summarize Impact
• Hua Ou, MD, Ph.D., OD 
  Lessons from Using Local LLMs (ChIRP) for Annual Portfolio Analysis
• James McClain, OD 
  Evan Ochsenfaber, OD 
  Overview of the All of Us Research Program's LLM Pipeline to Automatically Ingest, Authenticate, Categorize, and Synthesize Journal Publications by Researchers
• Vanessa Barnes, M.S., OD  
  More Than MeSH: AI-Powered Topic Mapping of Publications from the Kids First Program

Claude 101 is part 1 of a two-part series. 

This hour and half online training led by Anthropic will cover the fundamentals of using Claude effectively in your daily NIH workflows. Attendees will learn to navigate the Claude interface, apply best practices for prompt writing, and utilize key features such as working with documents, Projects, and Artifacts. The training will also demonstrate real-world use cases relevant to NIH staff for improving productivity, and highlight security and responsible-use considerations tailored for federal environments. 

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

• Navigate the Claude interface and use foundational features, including working with documents, Projects, and Artifacts. 

• Apply effective prompting strategies to generate accurate, useful outputs for NIH-specific tasks. 

• Identify everyday NIH use cases and understand best practices for responsible use of generative AI tools like Claude. 

Attendees are not expected to have any prior knowledge of the tool to be successful in this training. 

This 90-minute online training led by Google experts will dive into intermediate features, including agent creation and code generation, with Gemini for Government. The training will focus on hands-on applications, including building a simple agent with Agent Designer, using vibe-coding for data analysis, and leveraging NotebookLM as a personal research assistant. Attendees will also learn how to create more sophisticated, data-driven infographics to communicate their findings. 

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

• Build a simple, custom agent using Agent Designer to automate a research-related task, such as monitoring new publications. 
• Generate Python scripts using natural language (vibe-coding) to clean and analyze data. 
• Utilize NotebookLM to upload source materials, ask targeted questions across documents, and organize research insights. 
• Create a data-driven infographic that transforms raw data into a compelling visual story. 

Attendees are expected to be familiar with the basic functions of Gemini to be successful in this training (gained by attending Gemini for Government 101), attending another relevant training, and/or using Gemini previously).  Gemini for Government can be accessed at: https://go.hhs.gov/gemini  

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, Illumina scientist will illustrate how to obtain insights to regulation of gene expression from bulk RNA and ATAC sequencing data. No prior experience or access to Partek Flow is required. Attendance is limited to NIH staff.

Claude 201 is part 2 of a two-part series. 

This hour and half online training led by Anthropic will dive deeper into intermediate and advanced strategies for maximizing Claude in NIH workflows. Building on the fundamentals from Claude 101, this training will focus on structured and multi-step prompting, working effectively with longer documents and datasets, and using Projects to organize ongoing work and build reusable context. Attendees will also learn how to integrate Claude into specialized NIH tasks and optimize outputs for research, administrative, and policy workflows. 

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

• Use structured and multi-step prompting techniques to handle complex tasks and improve output quality. 

• Work effectively with documents, longer-form content, and data inside Claude to support research and analysis workflows. 

• Set up and use Projects to organize ongoing work, build reusable context, and collaborate on NIH-specific initiatives. 

Attendees are expected to be familiar with the basic functions of Claude to be successful in this training (gained by attending Claude 101, attending another relevant training, and/or using Claude previously). 

This 90-minute online training led by Google experts is the capstone session for power users who want to push the boundaries of AI in biomedical research. This session showcases advanced agentic workflows and complex comparative analysis. The training will feature a demo on building sophisticated research assistant agents with Agent Designer and will demonstrate additional NotebookLM use cases for research. 

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

• Design a complex, multi-agent system in Agent Designer capable of automating a research sub-task, such as finding and comparing experimental protocols. 
• Apply advanced NotebookLM techniques to perform complex comparative analysis on diverse scientific data sources. 
• Develop strategies for using AI to analyze a portfolio of grants and publications to identify alignment with NIH strategic priorities. 

Attendees are expected to be able to independently utilize Gemini to be successful in this training.  Gemini for Government can be accessed at: https://go.hhs.gov/gemini  

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. This class is demonstration-only. Starting from single cell RNA expression matrix, Illumina scientist will illustrate how to conduct QC, perform cell type classification, obtain differential expression results, and generate visualizations. No prior experience or access to Partek Flow is required. Attendance is limited to NIH staff.