arXiv 2604.215082026-04-23cs.AIq-bio.BM

BioMiner：一种用于从文献中自动挖掘蛋白质-配体生物活性数据的多模态系统

BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（中国科学技术大学认知智能国家重点实验室）；Princeton University（普林斯顿大学）；Huazhong University of Science and Technology（华中科技大学）；Infinite Intelligence Pharma（无限智能制药）

Jiaxian Yan, Jintao Zhu, Yuhang Yang, Qi Liu, Kai Zhang, Zaixi Zhang, Xukai Liu, Boyan Zhang, Kaiyuan Gao, Jinchuan Xiao, Enhong Chen

备注：: 20 pages, 5 figures, 1 table

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

BioMiner通过多模态框架提取生物活性数据，解决手动整理与文献增长不匹配的问题，其核心方法结合直接推理和化学结构解析，实现生物活性三元组的高准确率提取。

摘要：

英文摘要：

Protein-ligand bioactivity data published in the literature are essential for drug discovery, yet manual curation struggles to keep pace with rapidly growing literature. Automated bioactivity extraction remains challenging because it requires not only interpreting biochemical semantics distributed across text, tables, and figures, but also reconstructing chemically exact ligand structures (e.g., Markush structures). To address this bottleneck, we introduce BioMiner, a multi-modal extraction framework that explicitly separates bioactivity semantic interpretation from ligand structure construction. Within BioMiner, bioactivity semantics are inferred through direct reasoning, while chemical structures are resolved via a chemical-structure-grounded visual semantic reasoning paradigm, in which multi-modal large language models operate on chemically grounded visual representations to infer inter-structure relationships, and exact molecular construction is delegated to domain chemistry tools. For rigorous evaluation and method development, we further establish BioVista, a comprehensive benchmark comprising 16,457 bioactivity entries curated from 500 publications. BioMiner validates its extraction ability and provides a quantitative baseline, achieving an F1 score of 0.32 for bioactivity triplets. BioMiner's practical utility is demonstrated via three applications: (1) extracting 82,262 data from 11,683 papers to build a pre-training database that improves downstream models performance by 3.9%; (2) enabling a human-in-the-loop workflow that doubles the number of high-quality NLRP3 bioactivity data, helping 38.6% improvement over 28 QSAR models and identification of 16 hit candidates with novel scaffolds; and (3) accelerating protein-ligand complex bioactivity annotation, achieving a 5.59-fold speed increase and 5.75% accuracy improvement over manual workflows in PoseBusters dataset.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。