Research map / Probabilistic and scientific modeling / Molecules and proteins
DS-ProGen: A Dual-Structure Deep Language Model for Functional Protein Design
Yanting Li, Zikang Wang, Jiyue Jiang, Ziqian Lin, Dongchen He, Yuheng Shan, Yanruisheng Shao, Jiayi Li, Xiangyu Shi, Jiuming Wang, Yanyu Chen, Yimin Fan and 2 more
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 surface encoder to backbone encoder (dual-structure) (ablation) | DS-ProGen · PRIDE (80k pretraining) | recovery rate (%): 50.71 -> 61.47 | Improved |
| add backbone encoder to surface encoder (ablation) | DS-ProGen · PRIDE (80k pretraining) | recovery rate (%): 31.06 -> 61.47 | Improved |
| add large-scale structure-sequence pretraining (ablation) | DS-ProGen (backbone-only) · PRIDE test set | recovery rate (%): 33.62 -> 52.61 | Improved |
| add surface features to short proteins (ablation) | DS-ProGen · PRIDE test set (length 0-100) | recovery rate (%): 43.14 -> 63.50 | Improved |
| DS-ProGen backbone-only versus InstructPLM on short proteins | backbone-only DS-ProGen · PRIDE test set (length 0-100) | recovery rate (%): 45.07 -> 43.14 | Hurt |
| DS-ProGen versus PiFold and ESM-IF on foldability | DS-ProGen · AlphaFold3 refolding TM-Score | mean TM-Score (%): 88.43 -> 87.30 | Hurt |
| DS-ProGen versus ESM-IF on refolding RMSD | DS-ProGen · AlphaFold3 refolding RMSD | mean RMSD (A): 1.652 -> 1.401 | Improved |
| add surface encoder (ablation) | DS-ProGen · AlphaFold3 refolding RMSD | mean RMSD (A): 1.780 -> 1.401 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PiFold — PiFold: Toward effective and efficient protein inverse folding (ICLR 2023) · better on 1 of 2 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
- Protein Design with Dynamic Protein Vocabulary (NeurIPS 2025 · similarity 0.91)
- ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search (NeurIPS 2025 · similarity 0.89)
- SurfPro: Functional Protein Design Based on Continuous Surface (ICML 2024 · similarity 0.89)
- Elucidating the Design Space of Multimodal Protein Language Models (ICML 2025 · similarity 0.88)
- DPLM-2: A Multimodal Diffusion Protein Language Model (ICLR 2025 · similarity 0.88)
- Protein Inverse Folding From Structure Feedback (NeurIPS 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.
