Research map / Probabilistic and scientific modeling / Molecules and proteins
Apo2Mol: 3D Molecule Generation via Dynamic Pocket-Aware Diffusion Models
Xinzhe Zheng, Shiyu Jiang, Gustavo Seabra, Chenglong Li, Yanjun Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add hierarchical complex graph (four edge types) (ablation) | Apo2Mol · Apo2Mol benchmark, ablation (apo input) | Vina min (avg): -6.18 -> -6.79 | Improved |
| add hierarchical complex graph (four edge types) (ablation) | Apo2Mol · Apo2Mol benchmark, ablation (apo input) | QED (avg): 0.524 -> 0.587 | Improved |
| use quaternions instead of rotation vectors (ablation) | Apo2Mol · Apo2Mol benchmark, ablation (apo input) | Vina min (avg): -6.51 -> -6.79 | Improved |
| use quaternions instead of rotation vectors (ablation) | Apo2Mol · Apo2Mol benchmark, ablation (apo input) | QED (avg): 0.523 -> 0.587 | Improved |
| jointly generate refined holo pocket from apo input vs best baseline IPDiff | Apo2Mol · Apo2Mol benchmark, ligand generation from apo pockets (478 test) | Vina min (avg): -6.40 -> -6.79 | Improved |
| jointly generate refined holo pocket from apo input vs best baseline IPDiff | Apo2Mol · Apo2Mol benchmark, ligand generation from apo pockets (478 test) | High Affinity (%): 34.3% -> 42.7% | Improved |
| Apo2Mol from apo inputs, evaluated on native holo pockets, vs IPDiff trained on holo | Apo2Mol · Apo2Mol benchmark, ligand generation, baselines on holo pockets (478 test) | Vina min (avg): -7.09 -> -7.86 | Improved |
| generate from apo vs baseline Pocket2Mol (synthetic accessibility) | Apo2Mol · Apo2Mol benchmark, ligand generation from apo pockets (478 test) | SA (avg): 0.85 -> 0.61 | Hurt |
| give baseline IPDiff native holo pocket instead of apo pocket (ablation) | IPDiff · Apo2Mol benchmark | Vina min (avg): -6.40 -> -7.09 | Improved |
| give baseline DecompDiff native holo pocket instead of apo pocket (ablation) | DecompDiff · Apo2Mol benchmark | Vina min (avg): -6.37 -> -6.39 | No clear effect |
| give baseline DecompDiff native holo pocket instead of apo pocket (ablation) | DecompDiff · Apo2Mol benchmark | High Affinity (%): 34.3% -> 31.9% | Hurt |
| give baseline TargetDiff native holo pocket instead of apo pocket (ablation) | TargetDiff · Apo2Mol benchmark | Vina min (avg): -5.19 -> -5.50 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DecompDiff — DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design (ICML 2023) · better on 7 of 7 shared results
- Pocket2Mol — Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets (ICML 2022) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows (ICLR 2025 · similarity 0.91)
- FlashMol: High-Quality Molecule Generation in as Few as Four Steps (NeurIPS 2026 · similarity 0.89)
- BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning (AAAI 2025 · similarity 0.88)
- Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration (NeurIPS 2025 · similarity 0.88)
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.88)
- 3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery (ICLR 2025 · similarity 0.88)
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.
