Workshop
Sat Dec 03 06:30 AM -- 03:00 PM (PST) @ Room 288 - 289 None
Machine Learning in Structural Biology Workshop
[ Contact: workshopmlsb@gmail.com ]
In only a few years, structural biology, the study of the 3D structure or shape of proteins and other biomolecules, has been transformed by breakthroughs from machine learning algorithms. Machine learning models are now routinely being used by experimentalists to predict structures that can help answer real biological questions (e.g. AlphaFold), accelerate the experimental process of structure determination (e.g. computer vision algorithms for cryo-electron microscopy), and have become a new industry standard for bioengineering new protein therapeutics (e.g. large language models for protein design). Despite all this progress, there are still many active and open challenges for the field, such as modeling protein dynamics, predicting higher order complexes, pushing towards generalization of protein folding physics, and relating the structure of proteins to the in vivo and contextual nature of their underlying function. These challenges are diverse and interdisciplinary, motivating new kinds of machine learning systems and requiring the development and maturation of standard benchmarks and datasets.
In this exciting time for the field, our workshop, “Machine Learning in Structural Biology” (MLSB), seeks to bring together relevant experts, practitioners, and students across a broad community to focus on these challenges and opportunities. We believe the union of these communities, including the geometric and graph learning communities, NLP researchers, and structural biologists with domain expertise at our workshop can help spur new ideas, spark collaborations, and advance the impact of machine learning in structural biology. Progress at this intersection promises to unlock new scientific discoveries and the ability to design novel medicines.
| Opening Remarks (Remarks) | |
| Invited Speaker (Talk) | |
| Latent Space Diffusion Models of Cryo-EM Structures (Oral) | |
| Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models (Oral) | |
| Predicting conformational landscapes of known and putative fold-switching proteins using AlphaFold2 (Oral) | |
| Break | |
| Invited Speaker (Talk) | |
| SWAMPNN: End-to-end protein structures alignment (Oral) | |
| DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (Oral) | |
| Dynamic-backbone protein-ligand structure prediction with multiscale generative diffusion models (Oral) | |
| Poster Session | |
| Lunch (Break) | |
| Invited Speaker (Talk) | |
| EquiFold: Protein Structure Prediction with a Novel Coarse-Grained Structure Representation (Oral) | |
| Predicting Ligand – RNA Binding Using E3-Equivariant Network and Pretraining (Oral) | |
| Invited Speaker (Talk) | |
| Seq2MSA: A Language Model for Protein Sequence Diversification (Oral) | |
| Metal3D: Accurate prediction of transition metal ion location via deep learning (Oral) | |
| Panel Session (Discussion Panel) | |
| Poster Session / Happy Hour (Poster Session) | |
| Closing Remarks (Remarks) | |
| T-cell receptor specific protein language model for prediction and interpretation of epitope binding (ProtLM.TCR) (Poster) | |
| What is hidden in the darkness? Characterization of AlphaFold structural space (Poster) | |
| ContactNet: Geometric-Based Deep Learning Model for Predicting Protein-Protein Interactions (Poster) | |
| Deep Local Analysis estimates effects of mutations on protein-protein interactions (Poster) | |
| So ManyFolds, So Little Time: Efficient Protein Structure Prediction With pLMs and MSAs (Poster) | |
| Learning Free Energy Pathways through Reinforcement Learning of Adaptive Steered Molecular Dynamics (Poster) | |
| Does Inter-Protein Contact Prediction Benefit from Multi-Modal Data and Auxiliary Tasks? (Poster) | |
| Explainable Deep Generative Models, Ancestral Fragments, and Murky Regions of the Protein Structure Universe (Poster) | |
| APPRAISE: ranking engineered proteins by target binding propensity using pair-wise, competitive structure modeling and physics-informed analysis (Poster) | |
| Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC (Poster) | |
| Holographic-(V)AE: an end-to-end SO(3)-Equivariant (Variational) Autoencoder in Fourier Space (Poster) | |
| Protein-Protein Docking with Iterative Transformer (Poster) | |
| RL Boltzmann Generators for Conformer Generation in Data-Sparse Environments (Poster) | |
| Visualizing DNA reaction trajectories with deep graph embedding approaches (Poster) | |
| Predicting interaction partners using masked language modeling (Poster) | |
| Fast protein structure searching using structure graph embeddings (Poster) | |
| A Federated Learning benchmark for Drug-Target Interaction (Poster) | |
| Physics aware inference for the cryo-EM inverse problem: anisotropic network model heterogeneity, global 3D pose and microscope defocus (Poster) | |
| Conditional neural processes for molecules (Poster) | |
| Towards automated crystallographic structure refinement with a differentiable pipeline (Poster) | |
| Ligand-aware protein sequence design using protein self contacts (Poster) | |
| Improving Molecular Pretraining with Complementary Featurizations (Poster) | |
| Using domain-domain interactions to probe the limitations of MSA pairing strategies (Poster) | |
| Seq2MSA: A Language Model for Protein Sequence Diversification (Poster) | |
| Latent Space Diffusion Models of Cryo-EM Structures (Poster) | |
| Improving Molecule Properties Through 2-Stage VAE (Poster) | |
| Improving Protein Subcellular Localization Prediction with Structural Prediction & Graph Neural Networks (Poster) | |
| EquiFold: Protein Structure Prediction with a Novel Coarse-Grained Structure Representation (Poster) | |
| Representation of missense variants for predicting modes of action (Poster) | |
| Reconstruction of polymer structures from contact maps with Deep Learning (Poster) | |
| Large-scale self-supervised pre-training on protein three-dimensional structures (Poster) | |
| Allele-conditional attention mechanism for HLA-peptide complex binding affinity prediction (Poster) | |
| A Benchmark Framework for Evaluating Structure-to-Sequence Models for Protein Design (Poster) | |
| Predicting Immune Escape with Pretrained Protein Language Model Embeddings (Poster) | |
| Lightweight Equivariant Graph Representation Learning for Protein Engineering (Poster) | |
| Metal3D: Accurate prediction of transition metal ion location via deep learning (Poster) | |
| Predicting conformational landscapes of known and putative fold-switching proteins using AlphaFold2 (Poster) | |
| Dynamic-backbone protein-ligand structure prediction with multiscale generative diffusion models (Poster) | |
| Predicting Ligand – RNA Binding Using E3-Equivariant Network and Pretraining (Poster) | |
| DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (Poster) | |
| SWAMPNN: End-to-end protein structures alignment (Poster) | |
| Masked inverse folding with sequence transfer for protein representation learning (Poster) | |
| ExpressUrself: A spatial model for predicting recombinant expression from mRNA sequence (Poster) | |
| Adversarial Attacks on Protein Language Models (Poster) | |
| The geometry of hidden representations of protein language models (Poster) | |
| Membrane and microtubule rapid instance segmentation with dimensionless instance segmentation by learning graph representations of point clouds (Poster) | |
| 3D Reconstruction of Protein Complex Structures Using Synthesized Multi-View AFM Images (Poster) | |
| Protein structure generation via folding diffusion (Poster) | |
| Pretrained protein language model transfer learning: is the final layer representation what we want? (Poster) | |
| Training self-supervised peptide sequence models on artificially chopped proteins (Poster) | |
| Protein Sequence Design in a Latent Space via Model-based Reinforcement Learning (Poster) | |
| Contrasting drugs from decoys (Poster) | |
| Learning from physics-based features improves protein property prediction (Poster) | |
| 3D alignment of cryogenic electron microscopy density maps by minimizing their Wasserstein distance (Poster) | |
| End-to-end accurate and high-throughput modeling of antibody-antigen complexes (Poster) | |
| Investigating graph neural network for RNA structural embedding (Poster) | |
| Structure-based Drug Design with Equivariant Diffusion Models (Poster) | |
| Representation Learning on Biomolecular Structures using Equivariant Graph Attention (Poster) | |
| Peptide-MHC Structure Prediction With Mixed Residue and Atom Graph Neural Network (Poster) | |
| ZymCTRL: a conditional language model for the controllable generation of artificial enzymes (Poster) | |
| Conditional Invariances for Conformer Invariant Protein Representations (Poster) | |
| Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models (Poster) | |
| MLPfold: Identification of transition state ensembles in molecular dynamics simulations using machine learning (Poster) | |
| Identifying endogenous peptide receptors by combining structure and transmembrane topology prediction (Poster) | |
| Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization (Poster) | |
| Agile Language Transformers for Recombinant Protein Expression Optimization (Poster) | |
| ModelAngelo: Automated Model Building in Cryo-EM Maps (Poster) | |
| Unsupervised language models for disease variant prediction (Poster) | |
| Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem (Poster) | |
| Online Inference of Structure Factor Amplitudes for Serial X-ray Crystallography (Poster) | |
| Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness (Poster) | |
| Fast and Accurate Antibody Structure Prediction without Sequence Homologs (Poster) | |
| Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction (Poster) | |
| Investigating the conformational landscape of AlphaFold2-predicted protein kinase structures (Poster) | |
| Heterogeneous reconstruction of deformable atomic models in Cryo-EM (Poster) | |
| EvoOpt: an MSA-guided, fully unsupervised sequence optimization pipeline for protein design (Poster) | |
| ChemSpacE: Interpretable and Interactive Chemical Space Exploration (Poster) | |