Research map / Probabilistic and scientific modeling / Molecules and proteins
OpenProteinSet: Training data for structural biology at scale
Gustaf Ahdritz, Nazim Bouatta, Sachin Kadyan, Lukas Jarosch, Dan Berenberg, Ian Fisk, Andrew Martin Watkins, Stephen Ra, Richard Bonneau, Mohammed AlQuraishi
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 OpenFold using OpenProteinSet to reproduce AlphaFold2 | OpenFold · CASP15 all-groups domains (n = 90) | GDT-TS: 73.8 vs 74.6 | No clear effect |
| Add filtered Uniclust30 proteins for full-duration training alongside the PDB tranche | OpenFold · CAMEO validation set (180 unseen proteins) | lDDT-Cα: 0.868 -> 0.907 | Improved |
| Vary the training seed across 15 runs | OpenFold trained on the PDB tranche for 10,000 initial steps · CAMEO validation set (180 unseen proteins) | lDDT-Cα: 0.848 to 0.881; median 0.868 | No clear effect |
Closest papers by meaning
- Evaluating Representation Learning on the Protein Structure Universe (ICLR 2024 · similarity 0.89)
- MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training (NeurIPS 2024 · similarity 0.88)
- SaProt: Protein Language Modeling with Structure-aware Vocabulary (ICLR 2024 · similarity 0.87)
- Training Compute-Optimal Protein Language Models (NeurIPS 2024 · similarity 0.87)
- Protein Structure Tokenization: Benchmarking and New Recipe (ICML 2025 · similarity 0.87)
- MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions (NeurIPS 2024 · similarity 0.86)
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.
