Research map / Probabilistic and scientific modeling / Molecules and proteins
TerraBind: Fast and Accurate Binding Affinity Prediction through Coarse Structural Representations
Matteo Rossi, Ryan Pederson, Miles Wang-Henderson, Ben Kaufman, Edward C. Williams, Carl Underkoffler, Owen Lewis Howell, Adrian Layer, Stephan Thaler, Narbe Mardirossian, John Anthony Parkhill
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 TerraBind pairformer training instead of Boltz-1 Trunk with same coordinate optimization | TerraBind · pose benchmarks | ligand RMSD and LDDT-PLI success | Improved |
| use TerraBind instead of Boltz-1 Trunk | pairformer · ligand-protein entropy | mean H_LP: 0.576 -> 0.491 | Improved |
| replace diffusion with coordinate optimization on pocket context | TerraBind Pocket · pose sampling | seconds per complex: 27.8 -> 1.045 | Improved |
| use more than 5 pose samples (ablation) | TerraBind · pose success | success rate | No clear effect |
| add structural fine-tuning on a few proprietary crystals (ablation) | TerraBind affinity module · Targets X and Y | Pearson correlation | Improved |
| add continual learning to greedy selection | TerraBind-Greedy · simulated DMTA Target I | gap to best pIC50 | Improved |
| add EMAX acquisition with continual learning | Continual TerraBind-Greedy · simulated DMTA Target I | IC50 improvement: 6x | Improved |
| add Stage 3 PDB-only fine-tuning (ablation) | TerraBind pairformer · validation distogram entropy | entropy | Improved |
| use E1 protein encoder instead of ESM-2 or MSA encoding (ablation) | TerraBind · protein RMSD < 2A | success rate | Improved |
Closest papers by meaning
- Protein-ligand binding representation learning from fine-grained interactions (ICLR 2024 · similarity 0.87)
- Towards precision protein-ligand affinity prediction benchmark: A Complete and Modification-Aware DAVIS Dataset (NeurIPS 2025 · similarity 0.86)
- 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)
- Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization (ICML 2025 · similarity 0.85)
- DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking (NeurIPS 2024 · similarity 0.85)
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.
