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, modeling 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.
| Opening remarks | |
| Invited Talk 1: Michael Bronstein: Geometric deep learning for functional protein design (Invited talk) | |
| Invited Talk 2: Cecilia Clementi: Designing molecular models by machine learning and experimental data (Invited talk) | |
| Invited Talk 3: Lucy Colwell: Using deep learning to annotate the protein universe (Invited talk) | |
| Structure-aware generation of drug-like molecules (Oral) | |
| Learning physics confers pose-sensitivity in structure-based virtual screening (Oral) | |
| Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs (Oral) | |
| Weakly Supervised Learning for Joint Image Denoising and Protein Localization in Cryo-EM (Oral) | |
| Keynote 1: John Jumper: Highly accurate protein structure prediction with AlphaFold (Keynote speaker) | |
| Poster Session 1 (Poster Session) | |
| Panel Discussion | |
| Keynote 2: Jane Richardson: The Very Early Days of Structural Biology before ML (Keynote speaker) | |
| Break | |
| Predicting cryptic pocket opening from protein structures using graph neural networks (Oral) | |
| End-to-end learning of multiple sequence alignmentswith differentiable Smith-Waterman (Oral) | |
| Function-guided protein design by deep manifold sampling (Oral) | |
| Deciphering antibody affinity maturation with language models and weakly supervised learning (Oral) | |
| Deep generative models create new and diverse protein structures (Oral) | |
| Poster Session 2 (Poster Session) | |
| Invited Talk 4: Derek Lowe: AI and ML in Drug Discovery, a Chemist’s perspective. (Invited talk) | |
| Invited Talk 5: Regina Barzilay: Infusing biology into molecular models for property prediction (Invited talk) | |
| Invited Talk 6: Amy Keating: Navigating landscapes of protein interaction specificity using data-driven models (Invited talk) | |
| Closing remarks | |
| Social hour | |
| DLA-Ranker: Evaluating protein docking conformations with many locally oriented cubes (Poster) | |
| Adapting protein language models for rapid DTI prediction (Poster) | |
| Generative Language Modeling for Antibody Design (Poster) | |
| Real-valued Sidechain Dihedrals Prediction Using Relation-Shape Convolution (Poster) | |
| Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs (Poster) | |
| Function-guided protein design by deep manifold sampling (Poster) | |
| Simple End-to-end Deep Learning Model for CDR-H3 Loop Structure Prediction (Poster) | |
| MOLUCINATE: A Generative Model for Molecules in 3D Space (Poster) | |
| Active site sequence representation of human kinases outperforms full sequence for affinity prediction (Poster) | |
| Dock2D: Toy datasets for the molecular recognition problem (Poster) | |
| Protein sequence sampling and prediction from structural data (Poster) | |
| Predicting single-point mutational effect on protein stability (Poster) | |
| Exploring ∆∆G prediction with Siamese Networks (Poster) | |
| Residue characterization on AlphaFold2 protein structures using graph neural networks (Poster) | |
| HelixGAN: A bidirectional Generative Adversarial Network with search in latent space for generation under constraints (Poster) | |
| TERMinator: A Neural Framework for Structure-Based Protein Design using Tertiary Repeating Motifs (Poster) | |
| MSA-Conditioned Generative Protein Language Models for Fitness Landscape Modelling and Design (Poster) | |
| AutoFoldFinder: An Automated Adaptive Optimization Toolkit for De Novo Protein Fold Design (Poster) | |
| Studying signal peptides with attention neural networks informs cleavage site predictions (Poster) | |
| Structure-aware generation of drug-like molecules (Poster) | |
| Interpretable Pairwise Distillations for Generative Protein Sequence Models (Poster) | |
| A kernel for continuously relaxed, discrete Bayesian optimization of protein sequences (Poster) | |
| Predicting cryptic pocket opening from protein structures using graph neural networks (Poster) | |
| Deciphering antibody affinity maturation with language models and weakly supervised learning (Poster) | |
| Weakly Supervised Learning for Joint Image Denoising and Protein Localization in Cryo-EM (Poster) | |
| Deep generative models create new and diverse protein structures (Poster) | |
| End-to-end learning of multiple sequence alignmentswith differentiable Smith-Waterman (Poster) | |
| Learning physics confers pose-sensitivity in structure-based virtual screening (Poster) | |
| Turning high-throughput structural biology into predictive drug design (Poster) | |