Structure-based drug discovery with deep learning
Not on the map. Why?
Abstract (arXiv)
Artificial intelligence (AI) in the form of deep learning bears promise for drug discovery and chemical biology, textite.g., to predict protein structure and molecular bioactivity, plan organic synthesis, and design molecules textitde novo. While most of the deep learning efforts in drug discovery have focused on ligand-based approaches, structure-based drug discovery has the potential to tackle unsolved challenges, such as affinity prediction for unexplored protein targets, binding-mechanism elucidation, and the rationalization of related chemical kinetic properties. Advances in deep learning methodologies and the availability of accurate predictions for protein tertiary structure advocate for a textitrenaissance in structure-based approaches for drug discovery guided by AI. This review summarizes the most prominent algorithmic concepts in structure-based deep learning for drug discovery, and forecasts opportunities, applications, and challenges ahead.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 48 of its 189 references that are in the map. First posted on arXiv 26 Dec 2022.
Builds on
48 of 189 references.
References · 48
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
- 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
- 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
- 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
- 2018MolGAN: An implicit generative model for small molecular graphscited by 393
- 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 351
- 2020ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Predictioncited by 337
- 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 313
- 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 297
36 more
- 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 267
- 2018Learning Deep Generative Models of Graphscited by 229
- 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 217
- 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
- 2017Learning to Plan Chemical Synthesescited by 179
- 2018DeepDTA: Deep Drug-Target Binding Affinity Predictioncited by 173
- 2020ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computingcited by 162
- 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
- 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 144
- 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 122
- 2020Drug discovery with explainable artificial intelligencecited by 118
- 2021Geometric Deep Learning on Molecular Representationscited by 113
- 2022Conditional Antibody Design as 3D Equivariant Graph Translationcited by 75
- 2021Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Modelscited by 73
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
- 2018NeVAE: A Deep Generative Model for Molecular Graphscited by 67
- 2016Protein-Ligand Scoring with Convolutional Neural Networkscited by 57
- 2018DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networkscited by 52
- 2022Multi-Scale Representation Learning on Proteinscited by 52
- 2018PotentialNet for Molecular Property Predictioncited by 46
- 2018DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequencescited by 46
- 2015AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discoverycited by 38
- 2021Learning to design drug-like molecules in three-dimensional space using deep generative modelscited by 37
- 2022E3Bind: An End-to-End Equivariant Network for Protein-Ligand Dockingcited by 35
- 2019WideDTA: prediction of drug-target binding affinitycited by 30
- 2019Self-Attention Based Molecule Representation for Predicting Drug-Target Interactioncited by 22
- 2020DeepSurf: A surface-based deep learning approach for the prediction of ligand binding sites on proteinscited by 17
- 2019Improving detection of protein-ligand binding sites with 3D segmentationcited by 15
- 2019Combining docking pose rank and structure with deep learning improves protein-ligand binding mode predictioncited by 10
- 2022Exploiting Pretrained Biochemical Language Models for Targeted Drug Designcited by 10
- 2018PADME: A Deep Learning-based Framework for Drug-Target Interaction Predictioncited by 8
- 2022Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexescited by 6
- 2020Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Taskscited by 4
- 2022De novo design of protein target specific scaffold-based Inhibitors via Reinforcement Learningcited by 4
- 2022PGMG: A Pharmacophore-Guided Deep Learning Approach for Bioactive Molecular Generationcited by 2
- 20223D pride without 2D prejudice: Bias-controlled multi-level generative models for structure-based ligand designcited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 2.
3 papers.