EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022-02-07T00:00:00.000000Z)

TL;DR

A novel and fast fine-tuning model that adjusts torsion angles of a ligand's rotatable bonds based on closed-form global minima of the von Mises angular distance to a given input atomic point cloud, avoiding previous expensive differential evolution strategies for energy minimization.

Abstract

Predicting how a drug-like molecule binds to a specific protein target is a core problem in drug discovery. An extremely fast computational binding method would enable key applications such as fast virtual screening or drug engineering. Existing methods are computationally expensive as they rely on heavy candidate sampling coupled with scoring, ranking, and fine-tuning steps. We challenge this paradigm with EquiBind, an SE(3)-equivariant geometric deep learning model performing direct-shot prediction of both i) the receptor binding location (blind docking) and ii) the ligand's bound pose and orientation. EquiBind achieves significant speed-ups and better quality compared to traditional and recent baselines. Further, we show extra improvements when coupling it with existing fine-tuning techniques at the cost of increased running time. Finally, we propose a novel and fast fine-tuning model that adjusts torsion angles of a ligand's rotatable bonds based on closed-form global minima of the von Mises angular distance to a given input atomic point cloud, avoiding previous expensive differential evolution strategies for energy minimization.

Authors

T. Jaakkola

14 papers

R. Barzilay

24 papers

O. Ganea

5 papers

TL;DR

Abstract

Authors

References70 items

Multi-Scale Representation Learning on Proteins

MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design

InteractionGraphNet: A Novel and Efficient Deep Graph Representation Learning Framework for Accurate Protein-Ligand Interaction Predictions.

Side-chain Packing Using SE(3)-Transformer

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking

Structure-aware generation of drug-like molecules

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

The impact of cross-docked poses on performance of machine learning classifier for protein–ligand binding pose prediction

Geometric and Physical Quantities improve E(3) Equivariant Message Passing

Protein complex prediction with AlphaFold-Multimer

Faculty Opinions recommendation of Accurate prediction of protein structures and interactions using a three-track neural network.

Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity

Highly accurate protein structure prediction with AlphaFold

GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles

Structure-based protein function prediction using graph convolutional networks

DeepPocket: Ligand Binding Site Detection and Segmentation using 3D Convolutional Neural Networks

DeepBSP - a Machine Learning Method for Accurate Prediction of Protein-Ligand Docking Structures

Learning Gradient Fields for Molecular Conformation Generation

Deep generative design with 3D pharmacophoric constraints

A geometric deep learning approach to predict binding conformations of bioactive molecules

Protein interaction interface region prediction by geometric deep learning

SE(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials

Learning Neural Generative Dynamics for Molecular Conformation Generation

E(n) Equivariant Graph Neural Networks

GNINA 1.0: molecular docking with deep learning

E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials

Fast end-to-end learning on protein surfaces

Hierarchical, rotation‐equivariant neural networks to select structural models of protein complexes

InstaDock: A single-click graphical user interface for molecular docking-based virtual high-throughput screening

Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models

Learning from Protein Structure with Geometric Vector Perceptrons

Emulating Docking Results Using a Deep Neural Network: A New Perspective for Virtual Screening

SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks

EDock: blind protein–ligand docking by replica-exchange monte carlo simulation

Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning

Combining Docking Pose Rank and Structure with Deep Learning Improves Protein-Ligand Binding Mode Prediction over a Baseline Docking Approach

Computational methods and tools for binding site recognition between proteins and small molecules: from classical geometrical approaches to modern machine learning strategies

Predicting Drug-Target Interaction Using a Novel Graph Neural Network with 3D Structure-Embedded Graph Representation

Graph Matching Networks for Learning the Similarity of Graph Structured Objects

Graph Convolutional Neural Networks for Predicting Drug-Target Interactions

Comprehensive assessment of flexible‐ligand docking algorithms: current effectiveness and challenges

High precision protein functional site detection using 3D convolutional neural networks

Hybrid receptor structure/ligand-based docking and activity prediction in ICM: development and evaluation in D3R Grand Challenge 3

End-to-End Learning on 3D Protein Structure for Interface Prediction

Interpretable Drug Target Prediction Using Deep Neural Representation

DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks

Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds

Protein-Ligand Blind Docking Using QuickVina-W With Inter-Process Spatio-Temporal Integration

DeepSite: protein‐binding site predictor using 3D‐convolutional neural networks

Ligand-biased ensemble receptor docking (LigBEnD): a hybrid ligand/receptor structure-based approach

A systematic analysis of atomic protein–ligand interactions in the PDB

Forging the Basis for Developing Protein-Ligand Interaction Scoring Functions.

Group Equivariant Convolutional Networks

Insights into Protein–Ligand Interactions: Mechanisms, Models, and Methods

Better Informed Distance Geometry: Using What We Know To Improve Conformation Generation

AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery

Adam: A Method for Stochastic Optimization

Lessons Learned in Empirical Scoring with smina from the CSAR 2011 Benchmarking Exercise

Exploring chemical space for drug discovery using the chemical universe database.

AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading

DOCK 6: combining techniques to model RNA-small molecule complexes.

eHiTS: a new fast, exhaustive flexible ligand docking system.

Glide: a new approach for rapid, accurate docking and scoring. 2. Enrichment factors in database screening.

Announcing the worldwide Protein Data Bank

Predicting Molecular Conformation via Dynamic Graph Score Matching

Three-Dimensional Convolutional Neural Networks and a Cross-Docked Data Set for Structure-Based Drug Design

Protein-Ligand Scoring with Convolutional Neural Networks

Rdkit: Open-source cheminformatics software, 2016

Open Babel development team

BIOINFORMATICS ORIGINAL PAPER

Field of Study

Venue Information

Name

Type

URL

Alternate Names