DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
read the original abstract
Predicting the binding structure of a small molecule ligand to a protein -- a task known as molecular docking -- is critical to drug design. Recent deep learning methods that treat docking as a regression problem have decreased runtime compared to traditional search-based methods but have yet to offer substantial improvements in accuracy. We instead frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses. To do so, we map this manifold to the product space of the degrees of freedom (translational, rotational, and torsional) involved in docking and develop an efficient diffusion process on this space. Empirically, DiffDock obtains a 38% top-1 success rate (RMSD<2A) on PDBBind, significantly outperforming the previous state-of-the-art of traditional docking (23%) and deep learning (20%) methods. Moreover, while previous methods are not able to dock on computationally folded structures (maximum accuracy 10.4%), DiffDock maintains significantly higher precision (21.7%). Finally, DiffDock has fast inference times and provides confidence estimates with high selective accuracy.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
Generative Modeling with Flux Matching
Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices be...
-
EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning
EpiFormer improves epitope prediction F1 score by over 40% via early-fusion cross-attention in GNN layers and sparsity-aware objectives, while recovering known biology as emergent behavior.
-
DGLD: Domain-Gated Latent Diffusion for the Discovery of Novel Energetic Materials
DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baseline...
-
Hierarchical generative modeling for the design of multi-component systems
A closed-loop framework jointly optimizes molecular composition and geometry in multi-component systems, demonstrated by a 30% reduction in activation barrier for a Claisen rearrangement via post-hoc validation.
-
Toward Better Geometric Representations for Molecule Generative Models
LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% sta...
-
MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
MolClaw deploys a hierarchical skill system (tool, workflow, and discipline levels) to achieve state-of-the-art results on MolBench tasks requiring 8 to 50+ sequential tool calls in drug discovery.
-
D-Flow: Multi-modality Flow Matching for D-peptide Design
D-Flow applies multi-modality flow matching and a mirror-image data augmentation to generate D-peptides with 10.2% higher sequence identity and 24.31% top affinity on the PepMerge benchmark.
-
Benchmarking open-source tools for in silico antiviral drug discovery
Boltz-2 and fine-tuned DrugFormDTA lead ML-based binding prediction while GNINA leads docking tools on a cleaned antiviral dataset, with performance varying by viral protein.
-
MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
MolClaw deploys a hierarchical skill architecture to reach state-of-the-art results on a new benchmark of multi-step drug discovery tasks.
-
Benchmarking Single-Pose Docking, Consensus Rescoring, and Supervised ML on the LIT-PCBA Library: A Critical Evaluation of DiffDock, AutoDock-GPU, GNINA, and DiffDock-NMDN
On LIT-PCBA, supervised ML re-ranking reaches median EF1% of 4.49 while AutoDock-GNINA scores 2.14 and consensus does not exceed the best single scorer.
-
Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
Review of quantum neural networks on gate-based quantum computers for molecular property prediction and generation in drug discovery.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.