arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.16655cs.CL
收藏

利用大语言模型与知识图谱加速抗生素发现

Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs

Idiap Research Institute(伊迪亚普研究所);National Biomarker Centre (NBC), CRUK Manchester Institute(英国癌症研究曼彻斯特研究所国家生物标志物中心);Univ. of Manchester(曼彻斯特大学)

Maxime Delmas, Magdalena Wysocka, Danilo Gusicuma, André Freitas

AI总结:

提出基于大语言模型和知识图谱的抗生素发现流程,作为警报系统检测已有证据,防止代价高昂的已知化合物再发现,并在73种生物体上验证其有效性。

摘要:

新型抗生素的发现对于应对日益增长的抗菌素耐药性(AMR)至关重要。然而,制药行业面临高昂成本(超过10亿美元)、漫长周期和高失败率,而已知化合物的再发现使这一问题更加严峻。我们提出了一种基于大语言模型(LLM)的流程,该流程作为警报系统,检测先前抗生素活性的证据,以防止代价高昂的再发现。该系统将生物体和化学文献整合到知识图谱(KG)中,确保分类学解析、同义词处理和多级证据分类。我们在包含73种潜在产抗生素生物体的私有列表上测试了该流程,披露了12个阴性结果以供评估。结果凸显了该流程在证据审查、减少假阴性和加速决策方面的有效性。阴性结果的知识图谱和用于交互式探索的用户界面将公开发布。

英文摘要:

The discovery of novel antibiotics is critical to address the growing antimicrobial resistance (AMR). However, pharmaceutical industries face high costs (over $1 billion), long timelines, and a high failure rate, worsened by the rediscovery of known compounds. We propose an LLM-based pipeline that acts as an alarm system, detecting prior evidence of antibiotic activity to prevent costly rediscoveries. The system integrates organism and chemical literature into a Knowledge Graph (KG), ensuring taxonomic resolution, synonym handling, and multi-level evidence classification. We tested the pipeline on a private list of 73 potential antibiotic-producing organisms, disclosing 12 negative hits for evaluation. The results highlight the effectiveness of the pipeline for evidence reviewing, reducing false negatives, and accelerating decision-making. The KG for negative hits and the user interface for interactive exploration will be made publicly available.

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。

↑