Classes & Events

This session of the Cancer AI Conversations is an opportunity to highlight how knowledge graphs are advancing AI for biomedical research from multiple perspectives.

Dr. Haitham Elmarakeby has expertise in machine learning and data mining with a special interest in applying cutting-edge computational techniques to better understand progression and drug resistance in cancer. His machine learning models integrate multiple data modalities such as gene expression, mutations, copy number variations, and methylations to accurately predict outcomes in real patients and cell lines models.

Dr. Benjamin Gyori’s research combines computational modeling, machine learning, natural language processing, and human–machine interaction to improve our understanding of complex human biology, opening doors to advances in healthcare. His interest in the interdisciplinary field of computational systems biology stems from his fascination with mathematical and computational models of natural systems.

Dr. Jonathan Silverstein is internationally known for his expertise and research in the application of advanced computing architectures to biomedicine. Dr. Silverstein’s research interests include clinical informatics, imaging/visualization/virtual reality, vocabularies, virtual organizations, learning health systems and oncology informatics.

This talk shares a practical, experience-based account of using agentic AI on FRCE to support computational pathology workflows. I will explain how agentic AI differs from ordinary prompting, then show how it helped with reproducible HPC jobs, long GPU runs, debugging, QC, handoff notes, and result summaries. I will also discuss where agentic AI is useful, where it needs guardrails, and why human scientific judgment remains essential.

This fast paced, 90 minute class introduces you to using leading AI tools to quickly turn ideas into effective visuals. You'll learn how to craft prompts that generate diagrams, concept sketches, workflow illustrations, and explanatory graphics using Copilot, ChatGPT, Gemini, and Claude. The session highlights each model’s strengths and demonstrates practical workflows for enhancing communication, presentations, and problem solving. No design experience is required—just curiosity and a willingness to experiment with AI powered creativity.

Partek Flow is a point-and-click platform for building analysis workflows for Next Generation Sequences (NGS). Available to NCI researchers through an institutional license, DNA, bulk and single-cell RNA, spatial transcriptomics, ATAC, and ChIP analysis, helping scientists avoid learning to code. 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.

This one-hour online training, is the first of a two-part series, which introduces participants to cleaning and exploring a patient health dataset using Python and pandas. Attendees will load tabular data, inspect structure and data types, summarize columns, and identify common data quality problems such as missing values, inconsistent formats, and duplicate records. They will then apply practical fixes, including standardizing height and weight units, parsing and normalizing dates of birth, splitting combined fields, and using Boolean masks to flag or correct implausible values.​

By the end of this session students will be able to:

• Import CSV data into pandas DataFrames and quickly understand column types, basic statistics, and overall data quality.​
• Identify duplicate or repeated patient records and decide whether to keep, correct, or remove them.​
• Detect and handle missing or inconsistent values using methods such as isna, fillna, filtering, and conditional replacement.​
• Standardize mixed formats (for example, heights with and without units, date strings in different formats, and numeric values embedded in text).​
• Create derived columns such as systolic and diastolic blood pressure, and use logical conditions to flag questionable or out-of-range values.​

Attendees are expected to have:

• Basic Python coding knowledge
• Familiarity with an IDE and loading script and data files into the IDE. (Colab, Jupyter Notebooks) 

Requirements: 

• Participants will receive a script file and data files prior to the training. These should be loaded and ready to use before the training session begins.

This one-hour online training shows attendees how to use generative AI to accelerate scientific discovery and streamline data analysis. This training, open to all disciplines, demonstrates how AI-assisted coding can quickly turn ideas into functional analysis tools with minimal manual effort.  

By the end of this training, attendees will be able to:  
• Understand how MATLAB supports low-code, reproducible research while remaining flexible for advanced customization using MATLAB Copilot  
• Apply generative AI tools to accelerate data analysis while maintaining scientific rigor and reproducibility  
• Integrate generative AI into existing MATLAB workflows to reduce development time while preserving transparency and control  

Attendees should be familiar with basic MATLAB functions to succeed in this training.

This session introduces researchers to generative AI and large language models (LLMs), covering how these tools work, what distinguishes the major platforms available at NIH, and how to choose the right tool for a given task. Participants will learn the difference between chat-based and agentic AI tools and gain a clear understanding of how foundational expertise in biology and bioinformatics shapes the appropriate and responsible use of AI-generated outputs. No prior experience with AI is required.

This one-hour online training, the second session of the two-part series,  focuses on reshaping and enriching the cleaned patient dataset to prepare it for analysis and reporting. Attendees will practice splitting and recombining columns (for example, separating full names into first and last names), converting columns to appropriate data types, and engineering new fields such as outlier indicators and blood pressure status labels. The session also covers merging multiple tables (patient details, contact information, and subsets of records) and filtering or subsetting data to answer specific analytical questions.​

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

• Reshape and restructure data by splitting and combining columns, changing data types, and reordering or selecting relevant fields.​
• Engineer clinically useful features, including z-score–based outlier flags, hypertension indicators, and combined status columns for downstream models or dashboards.​
• Merge and join DataFrames using common keys (such as patient ID) to bring together core data with supplemental tables like contact information.​
• Filter and subset records based on multiple conditions (for example, patients with diabetes and abnormal blood pressure) to create analysis-ready datasets.​

Attendees are expected to have:

• To have attended Intro to Data Wrangling Using Python - Part 1 of the series
• Basic Python coding knowledge

Familiarity with an IDE and loading script and data files into the IDE. (Colab, Jupyter Notebooks) 

Requirements: 

• Participants will receive a script file and data files prior to the training. These should be loaded and ready to use before the training session begins. 

Learn about Geneious Prime—a powerful collection of tools for transforming raw DNA and protein sequence data into meaningful visualizations.

The instructor will:

• provide a general overview of the intuitive, user-friendly software.
• highlight some exciting new features.
• give tips and tricks for you to work more efficiently.

Geneious Prime is packed with fundamental bioinformatics tools (e.g., assembly, alignment, tree building, and more), and you can automate and streamline analyses without the need to code.

Microsoft Visual Studio Code (VS Code) is an integrated development environment (IDE) for writing scripts and viewing as well as organizing output from coding projects. It is compatible with languages and tools including R, Python, Jupyter Notebook, Quarto, Julia, C++, Matlab, HTML, and markdown. After attending, participants will know the benefits of using VS Code including AI assistance and Git project versioning integration, how to start coding projects, and how to access VS Code. Experience is not needed to participate.

This one-hour online training introduces attendees to modeling and simulation of biological systems using MATLAB’s SimBiology and BioPipeline Designer toolboxes. SimBiology is a versatile toolbox for modeling, simulating, and analyzing dynamic biological systems such as metabolic pathways, signaling cascades, and pharmacokinetics/pharmacodynamics (PK/PD) models. BioPipeline Designer complements this by streamlining workflows for integrating biological data and automating computational analyses. 

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

• Describe the capabilities and applications of SimBiology and BioPipeline Designer for modeling and analyzing biological systems. 

• Construct and parameterize basic models of biological processes using SimBiology’s graphical and programmatic interfaces. 

• Simulate dynamic behaviors of biological systems, such as time-course analyses, and interpret simulation results. 

• Automate and streamline data integration workflows using BioPipeline Designer to enhance reproducibility and efficiency. 

• Access and utilize resources for further learning, including tutorials, user guides, and MATLAB community forums 

Attendees are expected to be familiar with the basic functions of the MATLAB to be successful in this training. 

This 90-minute online roundtable explores practical applications of artificial intelligence (AI) in statistics and data analysis across the NIH research landscape. Brief presentations from panelists representing statistical, data science, and research perspectives will be followed by an open moderated discussion. Attendees will come away able to identify real-world AI use cases in research workflows, describe the opportunities and limitations of AI-assisted methods, and discuss how AI may shape the future of statistical practice, biomedical research, and decision-making at NIH and HHS. The discussion will also touch on considerations of bias, reproducibility, and responsible AI use within federally-funded research contexts.

Generative AI becomes useful for science when it is paired with domain knowledge, explicit context, executable checks, reusable instructions, and human judgment. In this session, we will go on a practical journey from scripts to reproducible AI-assisted bioinformatics, designed for wet-lab scientists and researchers who are early in their computational practice.

This one-hour online training will cover the fundamentals, applications, and ethical considerations of Artificial Intelligence (AI). Attendees will explore key topics such as machine learning, deep learning, data handling, and real-world AI applications across various industries. The session will also delve into the ethical implications of AI and provide insights on becoming 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.

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

• Understand the core concepts of AI 
• Recognize the significance of ethical considerations in AI 
• Begin the journey toward AI literacy

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

This hour and a half online training covers how to analyze and model data using interactive tools in MATLAB. Through live demonstrations and examples, attendees will learn to solve many steps in a data analysis workflow without writing any code. The interactive tools can generate the MATLAB code needed to reproduce the work programmatically. 

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

• Use interactive tools for data visualization, cleaning, and modeling
• Automatically generate code to replicate interactive work
• Capture work in easy-to-write scripts and functions
• Share results by automatically creating reports

This training taught by MathWorks. Attendees are not expected to have any prior knowledge of MATLAB, but experienced users will also benefit from new tools, tips, and tricks from the latest releases. This training is an introductory level; no software installation required.

LC-MS/MS is widely used in exposomics studies. MetaboAnalyst (https://www.metaboanalyst.ca/) is a widely used platform for statistical and functional analysis of metabolomics data. The current MetaboAnalyst 6.0 release incorporates updates to meet the needs of exposomics studies, including improved support for tandem mass spectrometry compound identification, exposome annotation, dose–response analysis and linking to genetics and functions. 

Generative AI models are powerful tools that can enhance research, but they also pose risks that can be detrimental to our work. This session will focus on responsible use of AI tools for Bioinformatics to help researchers get the most out of them while avoiding common pitfalls. We'll cover best practices for AI use in a research setting including reproducibility, documentation, and validation for responsible integration of AI into research workflows.

This one hour and half hour online training will equip attendees with essential knowledge and skills for effective interactions with Large Language Model (LLM) AI chatbots. Explore the intricacies of prompt engineering and its pivotal role in optimizing the conversational capabilities of LLMs. Emphasizing best practices and practical applications, this training features live demonstrations and provides valuable skills for the effective use of LLMs. 

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

• Define LLMs, prompt patterns, and prompt engineering
• Identify potential uses and issues to consider when using LLMs in the biomedical research field
• Use a selection of prompt patterns to improve generated output from LLMs
• Identify resources for learning more about prompt engineering in LLMs 

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

This session will present a case study showing how generative AI can support a real analysis workflow while preserving scientific rigor, validation, and reproducibility. It will also discuss caveats and mistakes to learn from.

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 a bulk ATAC-sequencing workflow starting from FASTQ files through peak and motif detection as well as comparison of peaks found across samples. No prior experience or access to Partek Flow is required. Attendance is limited to NIH staff.

This 45-minute online Lunch and Learn training will help attendees develop their own customized strategy for responsibly incorporating generative artificial intelligence (AI) tools, such as ChatGPT, into their workflows. 

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

• Assess appropriate use cases for generative AI tools within their specific research/work context 

• Develop a customized generative AI usage strategy 

• Document their approach for using generative AI tools 

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

Dr. Jiang’s research focuses on developing data-integration and artificial intelligence frameworks to study intercellular signaling mediated by secreted proteins in anti-tumor immunity. Data-driven analyses estimate that about two thousand human genes encode secreted proteins. Yet, literature mining reveals that 61% of these genes lack known roles in cancer. To address this gap, his lab developed computational methods and applied diverse immunological models to dissect cytokine networks, secreted proteins, and ligand–receptor interactions in cancer. Ultimately, the labs’ goal is to uncover new mechanisms of immune regulation and identify therapeutic opportunities that harness intercellular communication against 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. 

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.