arXiv 2602.040582026-02q-bio.GN

RareCollab: 一种基于大语言模型的多模态推理框架，用于孟德尔疾病诊断

RareCollab: an LLM-powered framework for multimodal reasoning in Mendelian disease diagnosis

Baylor College of Medicine（贝勒医学院）；Stanford University School of Medicine（斯坦福大学医学院）

Guantong Qi, Jiasheng Wang, Mei Ling Chong, Zahid Shaik, Shenglan Li, Shinya Yamamoto, Maura R. Z. Ruzhnikov, Devon E. Bonner, Jennefer N. Carter, Kevin S. Smit… 展开作者

Guantong Qi, Jiasheng Wang, Mei Ling Chong, Zahid Shaik, Shenglan Li, Shinya Yamamoto, Maura R. Z. Ruzhnikov, Devon E. Bonner, Jennefer N. Carter, Kevin S. Smith, Matthew T. Wheeler, Stephen B. Montgomery, Jonathan A. Bernstein, Sasidhar Pasupuleti, Undiagnosed Diseases Network, Pengfei Liu, Hu Chen, Zhandong Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

RareCollab通过整合基因组、表型和转录组证据，提升孟德尔疾病诊断的多模态推理能力，其在890名患者中实现了对94%诊断基因的高优先级识别，优于现有方法。

摘要：

罕见疾病诊断日益依赖整合基因组、表型和转录组证据，但这些信号仍难以在统一的解释框架中整合。本文提出RareCollab，一种基于大语言模型的多模态推理框架，整合超过100种诊断证据信号，包括DNA、RNA、表型、已整理的变异水平知识和计算机模拟的致病性证据。该设计使大语言模型能够作为校准且可解释的推理模块，而非单一端到端排序器。RareCollab应用于三个队列中的890名患者，包括119名未确诊疾病网络病例，其配对DNA和RNA数据构成大规模系统基准。在真实世界多模态基准中，RareCollab在前10名中优先考虑了94%的诊断基因。在召回率阈值从前1到前10的范围内，它在平均上比专有表型驱动的LLM基线（包括Claude Sonnet 4.6和GPT-5-mini）高出25%以上，并超越了现有最先进的变异优先级方法11%-24%。RareCollab还重塑了RNA证据的诊断贡献，在42/119个病例中帮助优先考虑诊断基因。这些结果确立了RareCollab作为多模态罕见疾病诊断的可扩展且可解释的框架。

英文摘要：

Rare disease diagnosis increasingly relies on integrating genomic, phenotypic and transcriptomic evidence, yet these signals remain difficult to reconcile within a common interpretive framework. Here we present RareCollab, an LLM-powered framework for multimodal reasoning in Mendelian disease diagnosis that integrates more than 100 diagnostic evidence signals across DNA, RNA, phenotype, curated variant-level knowledge, and in-silico pathogenicity evidence. This design enables large language models to operate as calibrated, interpretable reasoning modules rather than as a single end-to-end ranker. We applied RareCollab to 890 patients from three cohorts, including 119 Undiagnosed Diseases Network probands with paired DNA and RNA data, constituting a large systematic benchmark for multimodal rare disease diagnosis under paired genomic and transcriptomic evaluation. In this real-world multimodal benchmark, RareCollab prioritized 94% of diagnostic genes within the top 10. Across recall thresholds from top 1 to top 10, it consistently outperformed proprietary phenotype-driven LLM baselines including Claude Sonnet 4.6 and GPT-5-mini by more than 25% on average and surpassed established state-of-the-art variant prioritization methods by 11%-24%. RareCollab also reshapes the diagnostic contribution of RNA evidence, which contributes to prioritization of the diagnostic gene in 35% of cases (42/119). Together, these results establish RareCollab as a scalable and interpretable framework for multimodal rare disease diagnosis.

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。