NSF-NIH Joint Workshop on Emerging AI in Biology
Virtual Event
NSF-NIH Joint Workshop on Emerging AI in Biology
The virtual workshop is an invitation-only event June 8–9, 2023. The goal of the two-day workshop is to bring together a select group of world-recognized researchers to discuss current and emerging research on new, fundamental AI technologies that address problems in biology.
The workshop aims to promote discussion around emerging questions in the following themes and their application in biological and health challenges:
- Fairness, Reliability, Social Effects of AI.
- Federated Learning.
- Generative Deep Learning Models.
- Scalability of AI.
- Privacy and Security in AI.
- Hyperparameter Optimization, Automated Algorithm Design.
- Explainable AI and Causality.
- Active Learning, Automated Science, Reinforcement Learning.
- Transfer Learning, Meta Learning.
- Incorporating Prior Knowledge.
Unlike a traditional "talks-only" workshop, we expect the workshop to provide robust and interactive discussion among the experts. The breakout sessions will be structured to encourage discussion, and we anticipate that participants will be co-authors on a perspective paper resulting from the workshop that surveys some of the emerging areas. Video of the talks will be hosted on YouTube.
Thursday, June 8, 2023 | 9 a.m.–5 p.m. EDT
Friday, June 9, 2023 | 9 a.m.–4 p.m. EDT
Event Host: Carl Kingsford
Herbert A. Simon Professor of Computer Science, Computational Biology Department at Carnegie Mellon University
Carl received his Ph.D. from Princeton University in 2005. The main focus of his research involves applying algorithms to extract insight from biological data. His research currently focuses on classes of problems including genomics and genome assembly, chromatin structure and function, and automatically learning algorithms. Carl's interests include computational biology, genomics, machine learning and artificial intelligence.
Carl is co-founder and CEO of Ocean Genomics, the Intelligent Transcriptome company, which partners with cutting-edge drug developers to supply insights and evidence that enable data-driven decisions, provide confidence in the underlying biology, and increase the probability of technical and clinical success at every step.
Speakers
Roni Rosenfeld
Professor and Head, Machine Learning Department
School of Computer Science, Carnegie Mellon University
Smita Krishnaswamy
Associate Professor of Genetics and Computer Science, Yale School of Medicine and Computer Science Department, Yale University
Emma Pierson
Aassistant Professor of Computer Science, Jacobs Technion-Cornell Institute at Cornell Tech and the Technion; Computer Science Field Member, Cornell University; Assistant Professor of Population Health Sciences, Weill Cornell Medical College.
Anshul Kundaje
Associate Professor of Genetics and Computer Science, Stanford University
Marinka Zitnik
Assistant Professor of Biomedical Informatics, Blavatnik Institute of Biomedical Informatics, Harvard Medical School, Harvard University
Su-In Lee
Professor, Paul G. Allen School of Computer Science and Engineering; Adjunct Professor of Genome Sciences, Electrical and Computer Engineering, and Biomedical Informatics and Medical Education; Director, Computational Molecular Biology Program, University of Washington, Seattle
Ziv Bar-Joseph
FORE Systems Professor of Computer Science, Machine Learning Department and Computational Biology Department, School of Computer Science, Carnegie Mellon University; Head, R&D Data and Computational Sciences, Sanofi
Fei Wang
Associate Professor of Population Health Sciences, Weill Cornell Medicine, Cornell University
David Koes
Associate Professor, Department of Computational and Systems Biology, University of Pittsburgh; Associate Director of the Joint Carnegie Mellon-University of Pittsburgh Ph.D. Program in Computational Biology
James Zou
Assistant Professor of Biomedical Data Science, Computer Science, and Electrical Engineering, Stanford University
Caroline Uhler
Professor, Department of Electrical Engineering and Computer Science and Institute for Data, Systems and Society, Massachusetts Institute of Technology; Co-Director of the Eric and Wendy Schmidt Center at the Broad Institute of MIT and Harvard
Barbara Englehardt
Professor (Research), Biomedical Data Science, Department of Biomedical Data Science, Stanford University; Senior Investigator, Gladstone Institutes
Bin Yu
Chancellor's Distinguished Professor and Class of 1936 Second Chair, Departments of Statistics and Electrical Engineering and Computer Sciences Biomedical Data Science, UC Berkeley; Chan-Zuckerberg Biohub Investigator Alumnus; Weill Neurohub Investigator
Participants
Serdar Bozdag, University of North Texas
Yana Bromberg, Rutgers University
Dan DeBlasio, University of Texas at El Paso
Purvesh Khatri, Stanford University, Inflammatix
Jie Liu, University of Michigan
Jose Lugo-Martinez, Carnegie Mellon University
Jian Ma, Carnegie Mellon University
Paul Medvedev, Penn State University
Saket Navlakha, University of Maryland College Park
Duc Nguyen, University of Kentucky
Pranav Rajpurkar, Harvard University
Md Masud Rana, University of Kentucky
Ben Raphael, Princeton University
Sushmita Roy, University of Wisconsin-Madison
S. Cenk Sahinalp, National Cancer Institute, NIH
Ritambhara Singh, Brown University
Le Song, Mohamed bin Sayed University of Artificial Intelligence
Le Song, Mohamed bin Sayed University of Artificial Intelligence
Martin Styner, University of North Carolina at Chapel Hill
Jian Tang, Mila-Quebec AI Institute, HEC Montreal
Haohan Wang, University of Illinois Urbana-Champaign
Bo Wang, University of Toronto
Jianhua Xing, University of Pittsburgh
Min Xu, Carnegie Mellon University
Rong Xu, Case Western Reserve University
Detailed Schedule, Thursday June 8
| Time | Topic |
|---|---|
| 9–9:20 a.m. | Welcome and Introduction |
| 9:20-9:45 a.m. | "Deep Geometric Methods for Learning Dynamic Interactions From Cellular Data" |
| 9:45–10:10 a.m. | "Foundational AI for Genomic Medicine and Therapeutic Design" |
| 10:10–10:35 a.m. | "Forecasting the Past, Present and Future of Epidemics" |
| 10:40–11:45 a.m. | Breakout Discussion 1
|
| 11:45 a.m.–12:05 p.m. | Discussion Readout 1 |
| 12:05–12:45 p.m. | Lunch Break |
| 12:45–1:10 p.m. | "Causal Representation Learning in the Context of Perturbation Screens" |
| 1:10–1:35 p.m. | "Explainable AI: Where We Are and How To Move Forward for Cancer Pharmacogenomics" |
| 1:35–2 p.m. | "Multimodal Learning in Biomedicine" |
| 2:05–3:10 p.m. | Breakout Discussion 2
|
| 3:10–3:30 p.m. | Discussion Readout 2 |
| 3:30–4 p.m. | Break |
| 4–5 p.m. | Keynote: "Biomedicine in the Times of Generative AI" |
| 5–5:05 p.m. | Closing |
Detailed Schedule, Friday June 9
| Time | Topic |
|---|---|
| 9–9:10 a.m. | Welcome — Susan Gregurick, Associate Director for Data Science, NIH — Jean X. Gao, Program Director, Division of Biological Infrastructure — Ishwar Chandramouliswaran, Lead, FAIR Data and Resources, NIH |
| 9:10–9:35 a.m. | "Using Machine Learning To Increase Equity in Healthcare and Public Health" Emma Pierson |
| 9:35–10 a.m. | "Deep Learning for Structure-Based Drug Discovery" David Koes |
| 10–10:25 a.m. | "Generative AI and Active Learning in Pharma" Ziv Bar-Joseph |
| 10:30–11:35 a.m. | Breakout Discussion 3
|
| 11:35 a.m.–12:05 p.m. | Discussion Readout 3 |
| 12:05–12:45 p.m. | Lunch Break |
| 12:45–1:10 p.m. | "Machine Learning Models To Create and Annotate Tissue Atlases From Spatial Genomic Data" Barbara Englehardt |
| 1:10–1:35 p.m. | "Deep Learning for Causal Discovery in Regulatory Genomics" Anshul Kundaje |
| 1:40–2:40 p.m. | Breakout Discussion 4
|
| 2:40–3:10 p.m. | Break |
| 3:10–4:10 p.m. | Keynote: "Using Predictability and Stability To Reduce Design Space for Causality" |
| 4:10–4:15 p.m. | Workshop Closing |