Research map / Probabilistic and scientific modeling / Molecules and proteins
Geometric Pocket-Centric Protein Encoding for Polypharmacology-Guided Multi-Target Drug Design
Haoran liu, Xiaoli Lin, Jing Hu, Yu Zou, Xiaolong Zhang
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 |
|---|---|---|---|
| train from epoch 1 to epoch 4 | Ours · Property control Set 1 | MAE HBD: 0.03 -> 0.01 | Improved |
| train from epoch 1 to epoch 4 | Ours · Property control Set 1 | MAE RotB: 0.17 -> 0.09 | Improved |
| train from epoch 1 to epoch 4 | Ours · Property control Set 1 | MAE NumA: 0.16 -> 0.05 | Improved |
| train from epoch 1 to epoch 4 | Ours · Property control Set 5 | MAE HBD: 0.36 -> 0.22 | Improved |
| compare later property sets (Set 5) with Set 1 | Ours · Property control, Epoch 4 | MAE HBD: 0.01 -> 0.22 | Hurt |
| use multimodal pocket-centric model instead of Zhou | Zhou · COVID-19 Mpro docking | Vina affinity (kcal/mol): -10.3 -> -11.4 | Improved |
| use multimodal pocket-centric model instead of Zhou | Zhou · COVID-19 Epro docking | Vina affinity (kcal/mol): -10.9 -> -12.3 | Improved |
| use multimodal pocket-centric model instead of Lu | Lu · SCZ TAAR1 docking | Vina affinity (kcal/mol): -6.2 -> -13.3 | Improved |
| use multimodal pocket-centric model instead of Lu | Lu · SCZ 5HT2C docking | Vina affinity (kcal/mol): -6.8 -> -12.1 | Improved |
| use multimodal pocket-centric model instead of Yuan | Yuan · Tumour MEK1 docking | Vina affinity (kcal/mol): -11.9 -> -12.5 | Improved |
| use multimodal pocket-centric model instead of Yuan | Yuan · Tumour mTOR docking | Vina affinity (kcal/mol): -14.1 -> -11.6 | Hurt |
| use multimodal pocket-centric model instead of Munson | Munson · Tumour MEK1 docking | Vina affinity (kcal/mol): -7.4 -> -12.5 | Improved |
Closest papers by meaning
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.87)
- Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment (ICLR 2024 · similarity 0.86)
- Generalized Protein Pocket Generation with Prior-Informed Flow Matching (NeurIPS 2024 · similarity 0.86)
- 3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery (ICLR 2025 · similarity 0.85)
- UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design (ICML 2025 · similarity 0.85)
- Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule (ICML 2025 · similarity 0.84)
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.
