arXiv cs.AI· Zhaokang Liang, Mingze Yuan, Quanzheng Li, Wengong Jin·· 14 小时前AI 评分31
DynaReason-Pro：从构象集合预测蛋白质功能并生成自然语言解释
Beyond Static Structures: Linking Protein Dynamics to Function via DynaReason-Pro
AI 导读
DynaReason-Pro 是首个从构象集合联合预测 GO 术语并生成自然语言功能解释的框架，针对内在无序蛋白（IDP）设计。研究团队在基于 Protein Ensemble Database（PED）构建的 IDP 基准上评测，采用序列与结构聚类不相交的划分防止数据泄漏，变异性分层评估显示在高构象变异性区间增益最明显。
正文 · 原文
Abstract:Intrinsically disordered proteins (IDPs) carry out their functions through heterogeneous conformational ensembles that reflect their dynamics, yet most protein function prediction methods rely on sequence or a single static structure. To this end, we introduce DynaReason-Pro, the first framework to jointly predict GO terms from conformational ensembles and generate natural-language functional rationales. We evaluate DynaReason-Pro on a curated IDP benchmark from the Protein Ensemble Database (PED), with sequence- and structure-cluster-disjoint splits to prevent data leakage. Variability-stratified evaluation shows the clearest gains in the high-conformational-variability regime.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33804 [cs.AI] |
| (or arXiv:2610.33804v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33804 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhaokang Liang [view email]
[v1]
Sat, 24 Oct 2026 17:07:51 UTC (2,030 KB)
来源：arXiv cs.AI · arxiv.org