Pith. sign in

REVIEW 16 cited by

Structure-based Drug Design with Equivariant Diffusion Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2210.13695 v3 pith:MXT6ALUO submitted 2022-10-24 q-bio.BM cs.LG

classification q-bio.BMcs.LG
keywords designdiffusiondrugmodelsdataligandsmethodsprotein
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets. Generative SBDD methods leverage structural data of drugs in complex with their protein targets to propose new drug candidates. These approaches typically place one atom at a time in an autoregressive fashion using the binding pocket as well as previously added ligand atoms as context in each step. Recently a surge of diffusion generative models has entered this domain which hold promise to capture the statistical properties of natural ligands more faithfully. However, most existing methods focus exclusively on bottom-up de novo design of compounds or tackle other drug development challenges with task-specific models. The latter requires curation of suitable datasets, careful engineering of the models and retraining from scratch for each task. Here we show how a single pre-trained diffusion model can be applied to a broader range of problems, such as off-the-shelf property optimization, explicit negative design, and partial molecular design with inpainting. We formulate SBDD as a 3D-conditional generation problem and present DiffSBDD, an SE(3)-equivariant diffusion model that generates novel ligands conditioned on protein pockets. Our in silico experiments demonstrate that DiffSBDD captures the statistics of the ground truth data effectively. Furthermore, we show how additional constraints can be used to improve the generated drug candidates according to a variety of computational metrics. These results support the assumption that diffusion models represent the complex distribution of structural data more accurately than previous methods, and are able to incorporate additional design objectives and constraints changing nothing but the sampling strategy.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Boltzmann-Expected Molecular Design with Decoupled Annealing Flows

    stat.ML 2026-07 conditional novelty 7.0 of 10

    A two-flow simulated-annealing loop makes ensemble statistics—means, variances, and skewness of 3D properties—the objective of molecular graph design.

  2. Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule

    q-bio.BM 2025-05 conditional novelty 7.0 of 10

    MolPilot optimizes the variational lower bound over joint continuous/discrete noise schedules in Bayesian Flow Networks for protein-ligand generation, improving PoseBusters validity on CrossDock and PoseBusters benchmarks.

  3. Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks

    q-bio.BM 2024-11 conditional novelty 7.0 of 10

    MolJO applies joint gradient guidance to Bayesian Flow Networks, achieving state-of-the-art success rate (51.3%) in structure-based molecule optimization on CrossDocked2020.

  4. Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation via xTB-Reward Reinforcement Learning

    physics.comp-ph 2026-07 conditional novelty 6.0 of 10

    A plain causal transformer that tokenizes atom positions in local frames generates 3D molecules directly; RL against an xTB relaxation reward lifts topology-preserving valid yield from ~50% to ~95%.

  5. FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction

    q-bio.BM 2025-10 conditional novelty 6.0 of 10

    A flow-matching model jointly generates pocket-aware 3D ligands and predicts their binding affinities, reporting state-of-the-art generation and competitive affinity accuracy with a speed advantage.

  6. Multi-domain Distribution Learning for De Novo Drug Design

    cs.LG 2025-08 conditional novelty 6.0 of 10

    DrugFlow, a flow-matching plus Markov-bridge generative model, reports state-of-the-art distributional fidelity for structure-based drug design and adds uncertainty, size adaptation, side-chain flexibility, and prefer...

  7. FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation

    cs.LG 2025-08 conditional novelty 6.0 of 10

    Combining self-conditioning, fake atoms, and late-stage geometry distortion lets a compact flow-matching model generate nearly always valid 3D drug-like molecules and match training-data chemistry better than existing...

  8. Applications of Modular Co-Design for De Novo 3D Molecule Generation

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A new transformer architecture with joint continuous and discrete denoising improves 3D molecule generation and moves generated structures closer to low-energy physical minima.

  9. Generating 3D Binding Molecules Using Shape-Conditioned Diffusion Models with Guidance

    cs.LG 2025-02 conditional novelty 6.0 of 10

    DiffSMol generates novel 3D binding molecules conditioned on ligand shape embeddings, and with shape or pocket guidance it reports substantial benchmark improvements over existing methods.

  10. 3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery

    cs.CE 2025-02 conditional novelty 6.0 of 10

    A dual-channel transformer that reads and writes 3D coordinates as continuous numbers alongside chemical tokens achieves state-of-the-art docking and pocket-aware molecule generation.

  11. Pharmacophore-guided de novo drug design with diffusion bridge

    q-bio.BM 2024-12 conditional novelty 6.0 of 10

    PharmacoBridge, an SE(3)-equivariant diffusion bridge, generates valid 3D drug-like molecules directly from pharmacophore point clouds and outperforms pocket-based baselines in pharmacophore matching and docking affin...

  12. Exploring Discrete Flow Matching for 3D De Novo Molecule Generation

    cs.LG 2024-11 conditional novelty 6.0 of 10

    FlowMol-CTMC, using discrete-state continuous-time Markov chain flows, generates 3D molecules with higher stability and validity than prior 3D generation models while using far fewer parameters.

  13. On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

    cs.LG 2026-07 conditional novelty 5.5 of 10

    Online fine-tuning of discrete diffusion models with complementary acquisition, CVaR shaping, density-entropy debiasing, replay, and validity control finds better molecules under fixed oracle budgets than offline fine...

  14. TABASCO: A Fast, Simplified Model for Molecular Generation with Improved Physical Quality

    cs.LG 2025-07 conditional novelty 5.0 of 10

    TABASCO achieves 0.92 PoseBusters validity on GEOM-Drugs with a 59M-parameter non-equivariant transformer, no bond modeling, and post-hoc RDKit bond recovery, while sampling about 10x faster than SemlaFlow.

  15. BoKDiff: Best-of-K Diffusion Alignment for Target-Specific 3D Molecule Generation

    q-bio.BM 2025-01 conditional novelty 5.0 of 10

    BoKDiff fine-tunes a diffusion model for 3D ligand generation on the highest-scoring candidates using QED, SA, and Vina rewards, and shows that best-of-N sampling alone improves property metrics.

  16. Graph Neural Networks in Modern AI-aided Drug Discovery

    q-bio.BM 2025-06 conditional novelty 1.0 of 10

    A comprehensive model-centric review of graph neural network methods and applications in AI-aided drug discovery, from molecular representation to synthesis planning.

Pith tools