Machine Learning in Genomics: Tools, Resources, Clinical Applications and Ethics
Event Details
The NHGRI Genomic Data Science Working Group of the National Advisory Council for Human Genome Research hosted the Machine Learning in Genomics virtual workshop on April 13 - April 14, 2021.
Additional Information
The primary purpose of the workshop is to stimulate discussion around the opportunities and obstacles underlying the application of machine learning (ML) methods to basic genome sciences and genomic medicine, to define the key scientific topic areas in genomics that could benefit from ML analyses and NHGRI’s unique role at the convergence of genomic and ML research.
The data-intensive fields of genomics and ML are in an early stage of convergence. This workshop will include a combination of lectures from ML, genomics, and ethics researchers with substantial time set aside for virtual Q&A sessions in which all attendees, irrespective of expertise and background, are encouraged to participate. Topics of interest within genomics cover the full spectrum of basic and clinical research. The workshop will also focus on the ethical aspects of ML applications to genomics data. ML scientists without any connection to genomics are as welcome to join as those already applying their analytical methods to genomic data.
Day 1 Agenda
All slides are in PDF format
-
April 13, 2021
11:00 a.m. – 5:00 p.m. EDT - 11:00 a.m. - Welcome
Co-chairs:
Trey Ideker, Ph.D., University of California San Diego
Mark Craven, Ph.D., University of Wisconsin
Speaker:
Eric Green, M.D., Ph.D., Director, National Human Genome Research Institute - Keynote Session: What are the opportunities and challenges for ML in genomics research?
Moderator:
Shannon McWeeney, Ph.D., Oregon Health and Sciences University
11:10 a.m. - Eric Topol, M.D., Scripps Research
Genomics in the Machine Learning Space
11:40 a.m. - Brad Malin, Ph.D., Vanderbilt University Medical Center
Challenges and Opportunities for Machine Learning in Genomics
12:10 p.m. - Q&A Session- 12:40 p.m. - Break
- Session 1: Algorithm development and machine learning approaches in genomics
Moderators:
Trey Ideker, Ph.D., University of California San Diego
Anthony Philippakis, M.D., Ph.D., Broad Institute
1:00 p.m. - Jian Peng, Ph.D., University of Illinois at Urbana-Champaign
Machine learning algorithms for structural and functional genomics
1:25 p.m. - Sara Mathieson, Ph.D., Haverford College
Automatic evolutionary inference using Generative Adversarial Networks
1:50 p.m. - Christina Leslie Ph.D., Memorial Sloan-Kettering Cancer Center
The 3D genome and predictive gene regulatory models
2:15 p.m. - Q&A Session- 2:45 p.m. - Break
- Session 2: Ethical, Legal and Social Implications (ELSI) of machine learning in genomics
Moderators:
Dave Kaufman, Ph.D., NHGRI
Eimear Kenny, Ph.D., Icahn School of Medicine at Mount Sinai
3:10 p.m. - Pamela Sankar, Ph.D., University of Pennsylvania
Machine learning: broadening the scope of ethical questions
3:35 p.m. - Varoon Mathur, AI Now Institute
Considerations for building ethical and socially responsible AI systems in Health Care
4:00 p.m. - Danton Char, M.D., Stanford University
Identifying and Anticipating Ethical Challenges with Machine Learning for Genomics
4:25 p.m. - Q&A Session- 4:55 p.m. - Day 1 Wrap-up
Co-chairs:
Trey Ideker, Ph.D., University of California San Diego
Mark Craven, Ph.D., University of Wisconsin - 5:00 p.m. - Adjourn
Day 2 Agenda
All slides are in PDF format
-
April 14, 2021
11:00 a.m. – 4:00 p.m. EDT - 11:00 a.m. - Day 2 Opening
Co-chairs:
Trey Ideker, Ph.D., University of California San Diego
Mark Craven, Ph.D., University of Wisconsin - Session 3: Data and resource needs for machine learning in genomics
Moderators:
Christina Leslie, Ph.D., Memorial Sloan Kettering Cancer Center
Mark Craven, Ph.D., University of Wisconsin
11:10 a.m. - Alexis Battle, Ph.D., Johns Hopkins University
Integrative machine learning for regulatory genomics
11:35 a.m. - Anshul Kundaje, Ph.D., Stanford University
Machine learning for genomic discovery
12:00 p.m. - Gregory Cooper, M.D., Ph.D., University of Pittsburgh
Personalized Causal Machine Learning Using Genomic Data
12:25 p.m. - Q&A Session- 12:55 p.m. - Break
- Session 4: Machine learning in clinical genomics
Moderators:
Casey Overby Taylor, Ph.D., Johns Hopkins University
Eric Boerwinkle, Ph.D., University of Texas Health Science Center
2:00 p.m. - Su-In Lee, Ph.D., University of Washington
Explainable AI for cancer precision medicine
2:25 p.m. - Sriram Sankararaman, Ph.D., University of California Los Angeles
Machine Learning for large-scale genomics
2:50 p.m. - Russ Altman, M.D., Ph.D., Stanford University
Deep learning to predict the impact of rare variation in drug metabolism genes
3:15 p.m. - Q&A Session- 3:45 p.m. - Day 2 Wrap-up
Co-chairs:
Trey Ideker, Ph.D., University of California San Diego
Mark Craven, Ph.D., University of Wisconsin - 4:00 p.m. - Adjourn
Last updated: November 24, 2021