Research map / Probabilistic and scientific modeling / Molecules and proteins
TANKBind: Trigonometry-Aware Neural NetworKs for Drug-Protein Binding Structure Prediction
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 |
|---|---|---|---|
| TANKBind instead of EquiBind | blind self-docking · PDBbind unseen receptors | % ligand RMSD < 5A: 21.5 -> 55.6 | Helped |
| TANKBind instead of EquiBind | blind self-docking · PDBbind time split | % ligand RMSD < 5A: 39.1 -> 61.7 | Helped |
| P2Rank functional block segmentation instead of random (ablation) | TANKBind · PDBbind | mean ligand RMSD: 9.37 -> 7.43 | Helped |
| add trigonometry module (ablation) | TANKBind · PDBbind | mean ligand RMSD: 8.73 -> 7.43 | Helped |
| sum over both protein and compound nodes vs protein only (ablation) | TANKBind · PDBbind | mean ligand RMSD: 8.47 -> 7.43 | Helped |
| sum over both protein and compound nodes vs compound only (ablation) | TANKBind · PDBbind | mean ligand RMSD: 8.20 -> 7.43 | Helped |
| GVP protein encoder instead of TAPE (ablation) | TANKBind · PDBbind | mean ligand RMSD: 8.81 -> 7.43 | Helped |
| GIN compound encoder instead of GAT (ablation) | TANKBind · PDBbind | % RMSD < 5A: 78.51 -> 77.41 | Mixed |
| TANKBind with contrastive affinity loss vs complex-based IGN | affinity prediction · PDBbind affinity | Pearson: 0.698 -> 0.726 | Helped |
Closest papers by meaning
- DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction (NeurIPS 2025 · similarity 0.86)
- M²N: A Progressive Macro-to-Micro 3D Modeling Scheme for Unveiling Drug-Target Affinity (AAAI 2025 · similarity 0.86)
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.86)
- Binding-Adaptive Diffusion Models for Structure-Based Drug Design (AAAI 2024 · similarity 0.85)
- EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction (ICML 2024 · similarity 0.85)
- UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection (NeurIPS 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.