Workshop: Machine Learning for Structural Biology

Raphael Townshend, Stephan Eismann, Ron Dror, Ellen Zhong, Namrata Anand, John Ingraham, Wouter Boomsma, Sergey Ovchinnikov, Roshan Rao, Per Greisen, Rachel Kolodny, Bonnie Berger

Sat, Dec 12th @ 16:00 GMT – Sun, Dec 13th @ 02:00 GMT
Abstract: Spurred on by recent advances in neural modeling and wet-lab methods, structural biology, the study of the three-dimensional (3D) atomic structure of proteins and other macromolecules, has emerged as an area of great promise for machine learning. The shape of macromolecules is intrinsically linked to their biological function (e.g., much like the shape of a bike is critical to its transportation purposes), and thus machine learning algorithms that can better predict and reason about these shapes promise to unlock new scientific discoveries in human health as well as increase our ability to design novel medicines.

Moreover, fundamental challenges in structural biology motivate the development of new learning systems that can more effectively capture physical inductive biases, respect natural symmetries, and generalize across atomic systems of varying sizes and granularities. Through the Machine Learning in Structural Biology workshop, we aim to include a diverse range of participants and spark a conversation on the required representations and learning algorithms for atomic systems, as well as dive deeply into how to integrate these with novel wet-lab capabilities.

Video

Chat

Chat is not available.

Schedule

16:00 – 16:10 GMT
Opening Remarks
Raphael Townshend
16:10 – 16:12 GMT
Michael Levitt intro
Raphael Townshend
16:12 – 16:50 GMT
Keynote -- Michael Levitt
Michael Levitt
16:50 – 16:51 GMT
Charlotte Deane Intro
Stephan Eismann
16:51 – 17:10 GMT
Invited Talk 1 -- Charlotte Deane
Charlotte Deane
17:10 – 17:11 GMT
Frank Noe Intro
Wouter Boomsma
17:11 – 17:30 GMT
Invited Talk 5 -- Frank Noe
Frank Noe
17:30 – 17:31 GMT
Andrea Thorn Intro
Ellen Zhong
17:31 – 17:50 GMT
Invited Talk 2 -- Andrea Thorn
Andrea Thorn
17:50 – 18:20 GMT
Break
18:20 – 18:22 GMT
David Baker Intro
Namrata Anand
18:22 – 19:00 GMT
Keynote -- David Baker
David Baker
19:00 – 20:00 GMT
Morning Poster Session
Ellen Zhong
20:00 – 20:01 GMT
Contributed Talks Intro
Ellen Zhong
3 min each
20:01 – 20:11 GMT
Contributed Talk - Predicting Chemical Shifts with Graph Neural Networks
Ziyue Yang
20:11 – 20:21 GMT
Contributed Talk - Cryo-ZSSR: multiple-image super-resolution based on deep internal learning
Wendy Huang, Reed Chen, Cynthia Rudin
20:21 – 20:31 GMT
Contributed Talk - Wasserstein K-Means for Clustering Tomographic Projections
Rohan Rao, Amit Moscovich
20:30 – 22:00 GMT
Lunch
Raphael Townshend
22:00 – 22:01 GMT
Possu Huang intro
Namrata Anand
22:01 – 22:20 GMT
Invited Talk 4 -- Possu Huang
Possu Huang
22:20 – 22:21 GMT
Contributed talks intro
Roshan Rao
22:21 – 22:31 GMT
Contributed Talk - ProGen: Language Modeling for Protein Generation
Ali Madani, Bryan McCann, Nikhil Naik, , Possu Huang, Richard Socher
22:31 – 22:41 GMT
Contributed Talk - Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
Alexander Rives, Siddharth Goyal, Zeming Lin, Demi Guo, Myle Ott, Larry Zitnick, Rob Fergus
22:41 – 22:51 GMT
Contributed Talk - SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
Jonathan King, Dave Koes
22:51 – 23:01 GMT
Contributed Talk - Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models
Tomohide Masuda, Matthew Ragoza, Dave Koes
23:01 – 23:11 GMT
Contributed Talk - Learning from Protein Structure with Geometric Vector Perceptrons
Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael Townshend, Ron Dror
Sat, Dec 12th @ 23:11 GMT – Sun, Dec 13th @ 00:10 GMT
Afternoon Poster Session
Roshan Rao
00:10 – 00:11 GMT
Mohammed AlQuraishi intro
Raphael Townshend
00:11 – 00:30 GMT
Invited Talk 3 -- Mohammed AlQuraishi
Mohammed AlQuraishi
00:30 – 00:31 GMT
Chaok Seok intro
Sergey Ovchinnikov
00:31 – 00:50 GMT
Invited Talk 6 -- Chaok Seok
Chaok Seok
00:50 – 01:00 GMT
Concluding Remarks
Raphael Townshend
01:00 – 02:00 GMT
Happy Hour
Raphael Townshend
02:00 – 02:00 GMT
Fast and adaptive protein structure representations for machine learning
Janani Durairaj, Aalt van Dijk
02:00 – 02:00 GMT
The structure-fitness landscape of pairwise relations in generative sequence models
dylan marshall, Peter Koo, Sergey Ovchinnikov
02:00 – 02:00 GMT
Conservative Objective Models: A Simple Approach to Effective Model-Based Optimization
Brandon Trabucco, Aviral Kumar, XINYANG GENG, Sergey Levine
02:00 – 02:00 GMT
Exploring generative atomic models in cryo-EM reconstruction
Ellen Zhong, Adam Lerer, , Bonnie Berger
02:00 – 02:00 GMT
Combining variational autoencoder representations with structural descriptors improves prediction of docking scores
Miguel Garcia Ortegon, Carl Edward Rasmussen, Hiroshi Kajino
02:00 – 02:00 GMT
Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks
Modestas Filipavicius
02:00 – 02:00 GMT
DHS-Crystallize: Deep-Hybrid-Sequence based method for predicting protein Crystallization
Azadeh Alavi
02:00 – 02:00 GMT
Learning Super-Resolution Electron Density Map of Proteins using 3D U-Net
BAISHALI MULLICK, Yuyang Wang, Amir Barati Farimani
02:00 – 02:00 GMT
Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Jesse Vig, Ali Madani
02:00 – 02:00 GMT
Protein model quality assessment using rotation-equivariant, hierarchical neural networks
Stephan Eismann, Patricia Suriana, Bowen Jing, Raphael Townshend, Ron Dror
02:00 – 02:00 GMT
Sequence and stucture based deep learning models for the identification of peptide binding sites
Osama Abdin, Han Wen
02:00 – 02:00 GMT
Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning
Nicolas Lopez Carranza, Thomas PIERROT, Joe Phillips, Alex Laterre, Amine Kerkeni, Karim Beguir
02:00 – 02:00 GMT
Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models
Matthew Ragoza, Tomohide Masuda, Dave Koes
02:00 – 02:00 GMT
Cross-Modality Protein Embedding for Compound-Protein Affinity and Contact Prediction
Yuning You, Yang Shen
02:00 – 02:00 GMT
MXMNet: A Molecular Mechanics-Driven Neural Network Based on Multiplex Graph for Molecules
Shuo Zhang, Yang Liu
02:00 – 02:00 GMT
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
Brandon Trabucco, Aviral Kumar, XINYANG GENG, Sergey Levine
02:00 – 02:00 GMT
Is Transfer Learning Necessary for Protein Landscape Prediction?
David Belanger, David Dohan
02:00 – 02:00 GMT
ESM-1b: Optimizing Evolutionary Scale Modeling
Jason Liu, Zeming Lin, Naman Goyal, Myle Ott, Alexander Rives
02:00 – 02:00 GMT
GEFA: Early Fusion Approach in Drug-Target Affinity Prediction
Tri Nguyen Minh, Thin Nguyen, Thao M Le, Truyen Tran