Machine Learning in Structural Biology

Workshop at the 35th Conference on Neural Information Processing Systems

Monday, December 13, 2021

About

Structural biology, the study of proteins and other biomolecules through their 3D structures, is a field on the cusp of transformation. While measuring and interpreting biomolecular structures has traditionally been an expensive and difficult endeavor, recent machine-learning based modeling approaches have shown that it will become routine to predict and reason about structure at proteome scales with unprecedented atomic resolution. This broad liberation of 3D structure within bioscience and biomedicine will likely have transformative impacts on our ability to create effective medicines, to understand and engineer biology, and to design new molecular materials and machinery. Machine learning also shows great promise to continue to revolutionize many core technical problems in structural biology, including protein design, modelling protein dynamics, predicting higher order complexes, and integrating learning with experimental structure determination.

At this inflection point, we hope that the Machine Learning in Structural Biology (MLSB) workshop will help bring community and direction to this rising field. To achieve these goals, this workshop will bring together researchers from a unique and diverse set of domains, including core machine learning, computational biology, experimental structural biology, geometric deep learning, and natural language processing.

To attend the MLSB workshop talks, poster sessions, and virtual hangouts, register for the main NeurIPS conference at neurips.cc.

Call For Papers

We welcome submissions of short papers leveraging machine learning to address problems in structural biology, including but not limited to:

  • Prediction of biomolecular structures, complexes, and interactions
  • Geometric and symmetry-aware deep learning
  • Protein and RNA design
  • Generative models for structure and sequence
  • Experimental structure determination
  • Conformational change, ensembles, and dynamics
  • Function and property prediction
  • Structural systems biology
  • Language models and other representations of proteins

We request anonymized PDF submissions by Friday, September 17th Friday, October 1st, 2021, 11:59PM in the timezone of your choice through our submission website on CMT.

Papers should present novel work that has not been previously accepted at an archival venue at the time of submission. Submissions should be a maximum of 4 pages (excluding references and appendices) in PDF format and fully anonymized as per the requirements of NeurIPS. We request use of the NeurIPS style files. Submissions meeting these criteria will go through a light, double-blind review process. Reviewer comments will be returned to the authors as feedback.

Accepted papers will be invited to present a poster at the virtual workshop, with nominations of spotlight talks at the discretion of the organizers. This workshop is considered non-archival and does not publish proceedings, however authors of accepted contributions will have the option to make their work available through the workshop website. Presentation of work that is concurrently in submission is welcome.

Important Dates

Submission Deadline: Friday, September 17th Friday, October 1st, 2021, 11:59 PM, Anywhere on Earth.

Notification of Acceptance: Friday, October 22nd, 2021.

Workshop Date: Monday, December 13th, 2021.

Invited Speakers

John Jumper

John Jumper

Keynote

Senior Staff Research Scientist at DeepMind.

Show/Hide Bio
Jane Richardson

Jane Richardson

Keynote

Professor of Biochemistry at Duke University.

Show/Hide Bio
Regina Barzilay

Regina Barzilay

Professor of Computer Science at Massachusetts Institute of Technology.

Show/Hide Bio
Michael Bronstein

Michael Bronstein

Professor of Machine Learning at Imperial College London and Head of Graph Learning at Twitter.

Show/Hide Bio
Cecilia Clementi

Cecilia Clementi

Professor of Computational Biophysics at Freie Universität Berlin.

Show/Hide Bio
Lucy Colwell

Lucy Colwell

Faculty in Chemistry at University of Cambridge and Research Scientist at Google.

Show/Hide Bio
Amy Keating

Amy Keating

Professor of Biology at Massachusetts Institute of Technology.

Show/Hide Bio
Derek Lowe

Derek Lowe

Director in Chemical Biology at Novartis Institutes for BioMedical Research.

Show/Hide Bio

Schedule (EST)

09:00Opening Remarks
09:10Invited Talk - Michael Bronstein
09:20
09:30Invited Talk - Cecilia Clementi
09:40
09:50Invited Talk - Lucy Colwell
10:00
10:10Contributed Talk:

Structure-aware generation of drug-like molecules (Pavol Drotar, Arian R. Jamasb, Ben J. Day, Catalina Cangea, Pietro Lió)

10:20Contributed Talk:

Learning physics confers pose-sensitivity in structure-based virtual screening (Pawel Gniewek, Bradley Worley, Kate Stafford, Brandon Anderson, Henry van den Bedem)

10:30Contributed Talk:

Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs (Dan Rosenbaum, Marta Garnelo, Michal Zielinski, Charlie Beattie, Ellen Clancy, Andrea Huber, Pushmeet Kohli, Andrew Senior, John Jumper, Carl Doersch, S. M. Ali Eslami, Olaf Ronneberger, Jonas Adler)

10:40Contributed Talk:

Weakly Supervised Learning for Joint Image Denoising and Protein Localization in Cryo-EM (Qinwen Huang, Alberto Bartesaghi, Ye Zhou, Hsuan-fu Liu)

10:50Keynote - John Jumper:

Highly accurate protein structure prediction with AlphaFold

11:00
11:10
11:20
11:30Poster Session

Held on gather.town

11:40
11:50
12:00
12:10
12:20
12:30Panel Discussion

John Jumper, Jane Richardson, Cecelia Clementi, Lucy Colwell, Derek Lowe

12:40
12:50
01:00
01:10
01:20
01:30Keynote - Jane Richardson:

The Very Early Days of Structural Biology before ML

01:40
01:50
02:00
02:10Break
02:20Contributed Talk:

Predicting cryptic pocket opening from protein structures using graph neural networks (Artur Meller, Michael Ward, Meghana Kshirsagar, Felipe Oviedo Perhavec, Jonathan Borowsky, Juan M Lavista Ferres, Greg Bowman)

02:30Contributed Talk:

End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman (Samantha Petti, Nicholas Bhattacharya, Roshan Rao, Justas Dauparas, Neil Thomas, Juannan Zhou, Alexander Rush, Peter K. Koo, Sergey Ovchinnikov)

02:40Contributed Talk:

Function-guided protein design by deep manifold sampling (Vladimir Gligorijevic, Stephen Ra, Daniel Berenberg, Richard Bonneau, Kyunghyun Cho)

02:50Contributed Talk:

Deciphering antibody affinity maturation with language models and weakly supervised learning (Jeffrey A. Ruffolo, Jeffrey Gray, Jeremias Sulam)

03:00Contributed Talk:

Deep generative models create new and diverse protein structures (Zeming Lin, Tom Sercu, Alexander Rives)

03:10Poster Session

Held on gather.town

03:20
03:30
03:40
03:50
04:00
04:10Invited Talk - Derek Lowe
04:20
04:30Invited Talk - Regina Barzilay
04:40
04:50Invited Talk - Amy Keating
05:00
05:10Closing Remarks
05:20Social Hour

Held on gather.town

Accepted Papers

  • Simple End-to-end Deep Learning Model for CDR-H3 Loop Structure Prediction

    NataliaZenkova, Ekaterina Sedykh, Timofei Ermak, Tatiana Shugaeva, Vladislav Strashko, Aleksei Shpilman

    [paper] [arXiv]

  • MOLUCINATE: A Generative Model for Molecules in 3D Space

    Michael Arcidiacono, David Koes

    [paper] [arXiv]

  • Predicting cryptic pocket opening from protein structures using graph neural networks

    Artur Meller, Michael Ward, Meghana Kshirsagar, Felipe Oviedo Perhavec, Jonathan Borowsky, Juan M Lavista Ferres, Greg Bowman

    [paper]

  • Active site sequence representation of human kinases outperforms full sequence for affinity prediction

    Jannis Born, Tien Huynh, Astrid Stroobants, Wendy Cornell, Matteo Manica

    [paper] [ChemRxiv] [publication]

  • Interpretable Pairwise Distillations for Generative Protein Sequence Models

    Christoph Feinauer, Barthélémy Meynard, Carlo Lucibello

    [paper] [bioRxiv]

  • Dock2D: Toy datasets for the molecular recognition problem

    Georgy Derevyanko, Siddharth Bhadra-Lobo, Guillaume Lamoureux

  • Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs

    Dan Rosenbaum, Marta Garnelo, Michal Zielinski, Charlie Beattie, Ellen Clancy, Andrea Huber, Pushmeet Kohli, Andrew Senior, John Jumper, Carl Doersch, S. M. Ali Eslami, Olaf Ronneberger, Jonas Adler

    [arXiv]

  • Studying signal peptides with attention neural networks informs cleavage site predictions

    Patrick Bryant, Arne Elofsson

    [paper]

  • Protein sequence sampling and prediction from structural data

    Gabriel A Orellana, Javier Caceres-Delpiano, Roberto Ibanez, Michael Dunne, Leonardo Alvarez

    [paper] [bioRxiv]

  • Structure-aware generation of drug-like molecules

    Pavol Drotar, Arian R. Jamasb, Ben J Day, Catalina Cangea, Pietro Lió

    [paper] [arXiv]

  • Turning high-throughput structural biology into predictive drug design

    Kadi L Saar, Daren Fearon, John Chodera, Frank von Delft, Alpha Lee

    [bioRxiv]

  • DLA-Ranker: Evaluating protein docking conformations with many locally oriented cubes

    Yasser Mohseni Behbahani, Élodie Laine, Alessandra Carbone

    [paper] [bioRxiv]

  • Predicting single-point mutational effect on protein stability

    Kit Sang Chu, Justin Siegel

    [paper]

  • Exploring ∆∆G prediction with Siamese Networks

    Andrew McNutt, David Koes

    [paper]

  • Residue characterization on AlphaFold2 protein structures using graph neural networks

    Nasim Abdollahi

    [paper]

  • A kernel for continuously relaxed, discrete Bayesian optimization of protein sequences

    Yevgen Zainchkovskyy, Simon Bartels, Soren Hauberg, Jes Frellsen, Wouter Krogh Boomsma

  • Deciphering antibody affinity maturation with language models and weakly supervised learning

    Jeffrey A Ruffolo, Jeffrey Gray, Jeremias Sulam

    [paper] [arXiv]

  • HelixGAN: A bidirectional Generative Adversarial Network with search in latent space for generation under constraints

    Xuezhi Xie, Philip Kim

    [paper]

  • Weakly Supervised Learning for Joint Image Denoising and Protein Localization in Cryo-EM

    QinwenHuang, Alberto Bartesaghi, Ye Zhou, Hsuan-fu Liu

    [paper]

  • Deep generative models create new and diverse protein structures

    Zeming Lin, Tom Sercu, yann lecun, Alex Rives

    [paper]

  • Adapting protein language models for rapid DTI prediction

    Samuel Sledzieski, Rohit Singh, Lenore Cowen, Bonnie Berger

    [paper]

  • Generative Language Modeling for Antibody Design

    Richard W. Shuai, Jeffrey A Ruffolo, Jeffrey Gray

    [paper] [bioRxiv]

  • End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman

    Samantha Petti, Nicholas Bhattacharya, Roshan M Rao, Justas Dauparas, Neil Thomas, Juannan Zhou, Alexander Rush, Peter K. Koo, Sergey Ovchinnikov

    [paper] [bioRxiv]

  • TERMinator: A Neural Framework for Structure-Based Protein Design using Tertiary Repeating Motifs

    AlexLi, Vikram Sundar, Gevorg Grigoryan, Amy Keating

    [paper]

  • Learning physics confers pose-sensitivity in structure-based virtual screening

    Pawel Gniewek, Bradley Worley, Kate Stafford, Brandon Anderson, Henry van den Bedem

    [arXiv]

  • MSA-Conditioned Generative Protein Language Models for Fitness Landscape Modelling and Design

    Alex Hawkins-Hooker, David T. Jones, Brooks Paige

    [paper]

  • Real-valued Sidechain Dihedrals Prediction Using Relation-Shape Convolution

    Xiyao Long, Roland Dunbrack, Maxim Shapovalov

    [paper]

  • AutoFoldFinder: An Automated Adaptive Optimization Toolkit for De Novo Protein Fold Design

    Shuhao Zhang, Xu Youjun, Jianfeng Pei, Luhua Lai

    [paper]

  • Function-guided protein design by deep manifold sampling

    Vladimir Gligorijevic, Stephen Ra, Daniel Berenberg, Richard Bonneau, Kyunghyun Cho

    [paper] [bioRxiv]

Organizers

Namrata
Anand

Photo of Namrata Anand
Stanford University

Bonnie
Berger

Photo of Bonnie Berger
MIT

Wouter
Boomsma

Photo of Wouter Boomsma
University of Copenhagen

Erika
DeBenedictis

Photo of Erika DeBenedictis
University of Washington

Stephan
Eismann

Photo of Stephan Eismann
Stanford University

John
Ingraham

Photo of John Ingraham
Generate Biomedicines

Sergey
Ovchinnikov

Photo of Sergey Ovchinnikov
Harvard University

Roshan
Rao

Photo of Roshan Rao
UC Berkeley

Raphael
Townshend

Photo of Raphael Townshend
Stanford University

Ellen
Zhong

Photo of Ellen Zhong
MIT

Sponsors

Atomic Logo
Deepmind Logo
Generate Bio Logo