Timezone: »

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 12 08:00 AM -- 06:00 PM (PST) @ None
Event URL: http://mlsb.io »

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.

Sat 8:00 a.m. - 8:10 a.m.
Opening Remarks (Talk)
Raphael Townshend
Sat 8:12 a.m. - 8:50 a.m.
Keynote -- Michael Levitt (Talk)
Michael Levitt
Sat 8:51 a.m. - 9:10 a.m.
Invited Talk - Charlotte Deane: Predicting the conformational ensembles of proteins (Talk)   
Charlotte Deane
Sat 9:11 a.m. - 9:30 a.m.
Invited Talk - Frank Noe: Deep Markov State Models versus Covid-19 (Talk)   
Frank Noe
Sat 9:31 a.m. - 9:50 a.m.
Invited Talk - Andrea Thorn: Finding Secondary Structure in Cryo-EM maps: HARUSPEX (Talk)   
Andrea Thorn
Sat 9:50 a.m. - 10:20 a.m.
Sat 10:22 a.m. - 11:00 a.m.
Keynote - David Baker: Rosetta design of COVID antivirals and diagnostics (Talk)   
David Baker
Sat 11:00 a.m. - 12:00 p.m.
Morning Poster Session (Poster Session)  link » Ellen Zhong
Sat 12:01 p.m. - 12:11 p.m.
Contributed Talk - Predicting Chemical Shifts with Graph Neural Networks (Talk)   
Ziyue Yang
Sat 12:11 p.m. - 12:21 p.m.
Contributed Talk - Cryo-ZSSR: multiple-image super-resolution based on deep internal learning (Talk)   
Wendy Huang · Reed Chen · Cynthia Rudin
Sat 12:21 p.m. - 12:31 p.m.
Contributed Talk - Wasserstein K-Means for Clustering Tomographic Projections (Talk)   
Rohan Rao · Amit Moscovich
Sat 12:30 p.m. - 2:00 p.m.
Lunch + Panel Discussion on Future of ML for Structural Biology (Starts at 1pm) (Lunch)
Raphael Townshend
Sat 2:01 p.m. - 2:20 p.m.
Invited Talk - Possu Huang (Talk)
Possu Huang
Sat 2:20 p.m. - 2:21 p.m.
Contributed talks intro (Intro)
Roshan Rao
Sat 2:21 p.m. - 2:31 p.m.
Contributed Talk - ProGen: Language Modeling for Protein Generation (Talk)   
Ali Madani · Bryan McCann · Nikhil Naik · reguchi · Possu Huang · Richard Socher
Sat 2:31 p.m. - 2:41 p.m.
Contributed Talk - Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences (Talk)   
Alexander Rives · Siddharth Goyal · Joshua Meier · Zeming Lin · Demi Guo · Myle Ott · Larry Zitnick · Rob Fergus
Sat 2:41 p.m. - 2:51 p.m.
Contributed Talk - SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning (Talk)   
Jonathan King · Dave Koes
Sat 2:51 p.m. - 3:01 p.m.
Contributed Talk - Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models (Talk)   
Tomohide Masuda · Matthew Ragoza · Dave Koes
Sat 3:01 p.m. - 3:11 p.m.
Contributed Talk - Learning from Protein Structure with Geometric Vector Perceptrons (Talk)   
Bowen Jing · Stephan Eismann · Patricia Suriana · Raphael Townshend · Ron Dror
Sat 3:11 p.m. - 4:10 p.m.
Afternoon Poster Session (Poster Session)  link » Roshan Rao
Sat 4:11 p.m. - 4:30 p.m.
Invited Talk - Mohammed AlQuraishi: (Nearly) end-to-end differentiable learning of protein structure (Talk)   
Mohammed AlQuraishi
Sat 4:31 p.m. - 4:50 p.m.
Invited Talk - Chaok Seok: Ab initio protein structure prediction by global optimization of neural network energy: Can AI learn physics? (Talk)   
Chaok Seok
Sat 4:50 p.m. - 5:00 p.m.
Concluding Remarks (Talk)
Raphael Townshend
Sat 5:00 p.m. - 6:00 p.m.
Happy Hour
Raphael Townshend
Sat 6:00 p.m. - 6:00 p.m.
GEFA: Early Fusion Approach in Drug-Target Affinity Prediction (Poster Session)   
Tri Nguyen Minh · Thin Nguyen · Thao M Le · Truyen Tran
Sat 6:00 p.m. - 6:00 p.m.
Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning (Poster Session)
Nicolas Lopez Carranza · Thomas PIERROT · Joe Phillips · Alex Laterre · Amine Kerkeni · Karim Beguir
Sat 6:00 p.m. - 6:00 p.m.
MXMNet: A Molecular Mechanics-Driven Neural Network Based on Multiplex Graph for Molecules (Poster Session)
Shuo Zhang · Yang Liu
Sat 6:00 p.m. - 6:00 p.m.
Protein model quality assessment using rotation-equivariant, hierarchical neural networks (Poster Session)   
Stephan Eismann · Patricia Suriana · Bowen Jing · Raphael Townshend · Ron Dror
Sat 6:00 p.m. - 6:00 p.m.
Is Transfer Learning Necessary for Protein Landscape Prediction? (Poster Session)
David Belanger · David Dohan
Sat 6:00 p.m. - 6:00 p.m.
Fast and adaptive protein structure representations for machine learning (Poster Session)   
Janani Durairaj · Aalt van Dijk
Sat 6:00 p.m. - 6:00 p.m.
DHS-Crystallize: Deep-Hybrid-Sequence based method for predicting protein Crystallization (Poster Session)
Azadeh Alavi
Sat 6:00 p.m. - 6:00 p.m.
Cross-Modality Protein Embedding for Compound-Protein Affinity and Contact Prediction (Poster Session)
Yuning You · Yang Shen
Sat 6:00 p.m. - 6:00 p.m.
Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models (Poster Session)   
Matthew Ragoza · Tomohide Masuda · Dave Koes
Sat 6:00 p.m. - 6:00 p.m.
Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models (Poster Session)
Jesse Vig · Ali Madani
Sat 6:00 p.m. - 6:00 p.m.
Exploring generative atomic models in cryo-EM reconstruction (Poster Session)
Ellen Zhong · Adam Lerer · jhdavis · Bonnie Berger
Sat 6:00 p.m. - 6:00 p.m.
Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks (Poster Session)
Modestas Filipavicius
Sat 6:00 p.m. - 6:00 p.m.
Sequence and stucture based deep learning models for the identification of peptide binding sites (Poster Session)   
Osama Abdin · Han Wen
Sat 6:00 p.m. - 6:00 p.m.
ESM-1b: Optimizing Evolutionary Scale Modeling (Poster Session)
Joshua Meier · Jason Liu · Zeming Lin · Naman Goyal · Myle Ott · Alexander Rives
Sat 6:00 p.m. - 6:00 p.m.
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization (Poster Session)   
Brandon Trabucco · Aviral Kumar · XINYANG GENG · Sergey Levine
Sat 6:00 p.m. - 6:00 p.m.
Conservative Objective Models: A Simple Approach to Effective Model-Based Optimization (Poster Session)   
Brandon Trabucco · Aviral Kumar · XINYANG GENG · Sergey Levine
Sat 6:00 p.m. - 6:00 p.m.
Learning Super-Resolution Electron Density Map of Proteins using 3D U-Net (Poster Session)
BAISHALI MULLICK · Yuyang Wang · Amir Barati Farimani
Sat 6:00 p.m. - 6:00 p.m.
The structure-fitness landscape of pairwise relations in generative sequence models (Poster Session)
dylan marshall · Peter Koo · Sergey Ovchinnikov
Sat 6:00 p.m. - 6:00 p.m.
Combining variational autoencoder representations with structural descriptors improves prediction of docking scores (Poster Session)
Miguel Garcia Ortegon · Carl Edward Rasmussen · Hiroshi Kajino

Author Information

Raphael Townshend (Stanford University)
Stephan Eismann (Stanford University)
Ron Dror (Stanford)
Ellen Zhong (Massachusetts Institute of Technology)
Namrata Anand (Stanford University)
John Ingraham (Generate Biomedicines)
Wouter Boomsma (University of Copenhagen)
Sergey Ovchinnikov (Harvard)
Roshan Rao (UC Berkeley)
Per Greisen (Novo Nordisk)
Rachel Kolodny (Haifa University)
Bonnie Berger (MIT)

More from the Same Authors