Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets

2022/05/15 by Xingang Peng, Shitong Luo, Peng, Xingang +9 · 30 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Biomolecules (q-bio.BM) #Computational Drug Discovery Methods #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Materials Science #Protein Structure and Dynamics

paper · pdf · doi:10.48550/arxiv.2205.07249

openalex publication_date 2022/05/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep generative models have achieved tremendous success in designing novel drug molecules in recent years. A new thread of works have shown the great potential in advancing the specificity and success rate of in silico drug design by considering the structure of protein pockets. This setting posts fundamental computational challenges in sampling new chemical compounds that could satisfy multiple geometrical constraints imposed by pockets. Previous sampling algorithms either sample in the graph space or only consider the 3D coordinates of atoms while ignoring other detailed chemical structures such as bond types and functional groups. To address the challenge, we develop Pocket2Mol, an E(3)-equivariant generative network composed of two modules: 1) a new graph neural network capturing both spatial and bonding relationships between atoms of the binding pockets and 2) a new efficient algorithm which samples new drug candidates conditioned on the pocket representations from a tractable distribution without relying on MCMC. Experimental results demonstrate that molecules sampled from Pocket2Mol achieve significantly better binding affinity and other drug properties such as druglikeness and synthetic accessibility.

Cited by

• ReACT-Drug: Reaction-Template Guided Reinforcement Learning for de novo Drug Design
• SynCraft: Guiding Large Language Models to Predict Edit Sequences for Molecular Synthesizability Optimization
• Machine learning for RNA-targeting drug design
• Toward Closed-loop Molecular Discovery via Language Model, Property Alignment and Strategic Search
• MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
• NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
• OMTRA: A Multi-Task Generative Model for Structure-Based Drug Design
• FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble
• Unified all-atom molecule generation with neural fields
• SculptDrug : A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design
• SiDGen: Structure-informed Diffusion for Generative modeling of Ligands for Proteins
• Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein Binding
• Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
• MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design
• ODesign: A World Model for Biomolecular Interaction Design
• Antibacterial Drug Discovery: Deep Learning Successes and Challenges through the Structural Biology Lens
• Foundation models in bioinformatics
• ExMolRL: Phenotype-Target Joint Generation of De Novo Molecules via Multi-Objective Reinforcement Learning
• A Genetic Algorithm for Navigating Synthesizable Molecular Spaces
• MSCoD: An Enhanced Bayesian Updating Framework with Multi-Scale Information Bottleneck and Cooperative Attention for Structure-Based Drug Design
• Multi-domain Distribution Learning for De Novo Drug Design
• Synthetic Protein-Ligand Complex Generation for Deep Molecular Docking
• SOLD: SELFIES-based Objective-driven Latent Diffusion
• Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number
• Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration
• FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
• IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data
• FROGENT: An End-to-End Full-process Drug Design Agent
• Chem3DLLM: 3D Multimodal Large Language Models for Chemistry
• ActivityDiff: A diffusion model with Positive and Negative Activity Guidance for De Novo Drug Design

Related

• Structure-aware generation of drug-like molecules
• A 3D Generative Model for Structure-Based Drug Design
• Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein Binding
• Generation of 3D Molecules in Pockets via Language Model
• In-Pocket 3D Graphs Enhance Ligand-Target Compatibility in Generative Small-Molecule Creation