BTEP Generative AI in Bioinformatics Seminar Series

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.

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.

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 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.