Leveraging Foundational Models in Computational Biology: Validation, Understanding, and Innovation

Brett Beaulieu-Jones & Steven E. Brenner

Large Language Models (LLMs) have demonstrated immense potential within and outside of the biomedical domain but currently have substantial limitations when applied to biomedical research. These models promise a new paradigm for data analysis, interpretation and hypothesis generation, but it is not clear how fully this promise will be fulfilled. LLMs are just one class of foundational models, and while they have already made a significant impact to computational biology, it is unlikely that a singular architecture geared at processing natural language will be the ideal framework for general learning in computational biology. This workshop aims to provide an understanding of the state of the art today, current challenges in the application or development of models tailored to computational biology, as well as to start a discussion of what the future holds for our community.

Workshop Program:

Presenter Affiliation Time Title
Brett Beaulieu-Jones & Steven E. Brenner UChicago
University of California, Berkeley		 1:30-1:40 Welcome and Introduction
Predrag Radivojac Northeastern University 1:40-2:00 Assessment and failure-modes of generative models
Emily Alsentzer Stanford University 2:00-2:20 Foundational Models for Few-Shot Learning
Geena Wu UChicago 2:20-2:45 Foundational models in Genetics: 8 Most Interesting Papers from 2024
Break 2:45-2:55
Michael Burkhart UChicago 2:55-3:20 Foundational models in Biomedicine: 8 Most Interesting Papers from 2024
Ben Brown Lawrence Berkeley National Laboratory / Arva Intelligence 3:20-3:40 Foundation models in environmental and biomedical science -- and paths toward overcoming trust issues in high-risk domains
Jonathan Chen Stanford University 3:40-4:00 Foundation Models in Medical Reasoning - Fountain of Creativity or Pandora's Box?
Break 4:00-4:10
Panel / Open Discussion 4:10-4:30 What needs to happen for transformative as opposed to iterative progression?