The 2nd workshop on Generative AI and Biology


Welcome to the GenBio Workshop! Join us as we explore the exciting intersection of artificial intelligence and biology. Discover how generative AI is revolutionizing protein research, RNA analysis, molecular design, drug discovery, and more. This workshop is designed to be interactive and practical, equipping you with the skills to utilize generative AI tools in your own biological research. Engage in stimulating discussions and collaborate with experts from diverse backgrounds. Together, let's unlock the potential of generative AI for biology.

Stay tuned by following us on Twitter.




Overview

Over the past year, generative AI models have led to tremendous breakthroughs, from image and text generation, to protein folding and design. These recent successes illustrate the incredible potential of generative AI not only for digital applications, but also for basic science and healthcare. We are now able to predict protein structure from sequence alone; to characterize the function and interactions of biomolecules; to design such molecules never-before-seen in nature; and more. The impacts are profound: through generative AI, we can systematically understand and reprogram biology at an unprecedented level.

The goals of this workshop are to bridge the gap between the machine learning and biological communities; to connect leading researchers from both industry and academia; and to gain critical insights into the future of generative-AI-driven biology. We look forward to your participation in this exciting discourse on the future of biology and AI.

Call for Papers

We invite researchers, scientists, students, and industry professionals working in the domains of artificial intelligence, machine learning, computational biology, bioinformatics, and related areas to submit their original research or review papers. The scope of this workshop includes, but not limited to, the following topics.

Designing and optimizing novel and useful biomolecules
  • Rational protein design: Prediction and optimization of protein sequences and/or structures, incorporating constraints and prior knowledge
  • Small molecule drug design: Discovery and optimization of novel and effective small molecule therapeutics, incorporating information about the biological context
  • Next frontiers of de-novo design: Designing other biomolecules including peptides, oligonucleotides, antibodies, or targeted degraders
From first principles: generative modeling for biological data
  • Sequence-based methods: large language models for protein / genomic sequences, sequence-based molecular design
  • Graph-based methods: generative learning on biological graphs and networks, e.g., molecular graphs, protein-protein interaction networks, genome-wide association graphs
  • Geometric deep learning: generative modeling of biological structures as point clouds, surfaces, and other geometric objects
Open challenges in generative AI and biology (Special Track)
  • Large language models for scientific discovery: literature summarization, structured information extraction, identifying knowledge gaps and uncovering novel connections, formulation of scientific hypotheses
  • Finding common ground: systematic barriers, biological experiment design with GenerativeAI-in-the-loop
  • Identifying the right problems: pressing challenges in biology that are difficult to address via traditional means, gap between biological need and existing generative algorithms

Confirmed (Tentative) Speaker

David Baker
Prof.
David Baker

University of Washington
Jennifer Listgarten
Prof.
Jennifer Listgarten

UC Berkeley
James J. Collins
Prof.
James J. Collins

MIT
Mengdi Wang
Prof.
Mengdi Wang

Princeton
Marinka Zitnik
Prof.
Marinka Zitnik

Harvard
Ge Liu
Prof.
Ge Liu

UIUC
Frank Noé
Dr.
Frank Noé

Microsoft Research

Organizers

Minkai Xu
Minkai Xu
Stanford
Zhenqiao Song
Zhenqiao Song
CMU
Tingyang Yu
Tingyang Yu
EPFL
Wenxian Shi
Wenxian Shi
MIT
Seul Lee
Seul Lee
KAIST
Maria Brbic
Prof.
Maria Brbic

EPFL
Aditi S. Krishnapriyan
Prof.
Aditi S. Krishnapriyan

UC Berkeley
Lei Li
Prof.
Lei Li

CMU
Stefano Ermon
Prof.
Stefano Ermon

Stanford
Regina Barzilay
Prof.
Regina Barzilay

MIT

Sponsors