Research map / Probabilistic and scientific modeling / Molecules and proteins
Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace MCMC-based autoregressive sampling with direct tractable position distribution (GMM) and joint bond/element prediction | Pocket2Mol vs AR sampler · CrossDocked | Vina Score and generation time: Vina -7.288 vs -6.215; time 2503.51 s vs 19658.56 s | Helped |
| Pocket2Mol architecture and sampler (vs CVAE and AR) | Generated molecules · CrossDocked | QED, SA, LogP, Lipinski: QED 0.563 vs 0.502 (AR); SA 0.765 vs 0.675 | Helped |
| Pocket2Mol sampler vs AR and CVAE | Generated molecules · CrossDocked | Diversity: 0.688 vs 0.742 (AR) | Hurt |
| Joint bond prediction with atom placement (bond-aware generation) instead of adding bonds with OpenBabel afterward | Generated ring structures · CrossDocked ring-size distribution | fraction of three-membered rings vs test set (0.033): 0.002 vs 0.361 (CVAE) and 0.484 (AR) | Helped |
| Pocket2Mol generative model vs baselines on conformer validity | Generated 3D conformers · CrossDocked RMSD to RDKit conformers | mean RMSD (Å, lower better): 0.46 vs 0.84 (AR) and 1.38 (CVAE) | Helped |
Closest papers by meaning
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.88)
- Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation (ICLR 2024 · similarity 0.88)
- Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation (AAAI 2025 · similarity 0.88)
- Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space (NeurIPS 2025 · similarity 0.87)
- BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning (AAAI 2025 · similarity 0.87)
- Generalized Protein Pocket Generation with Prior-Informed Flow Matching (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.