患者特异性生物分子指令微调
Patient-specific Biomolecular Instruction Tuning
AI总结：
针对患者特异性蛋白质组学缺乏指令数据与适配架构的问题，本文构建 CPTAC-PROTSTRUCT 数据集并提出 graph-LLM 框架 KRONOS，以提升临床分子推理性能。
摘要：
蛋白质组学数据对于理解疾病表型的致病机制至关重要。在癌症中，对分子特征进行分析可通过识别驱动个体化肿瘤进展、治疗耐药性和临床异质性的生物学过程来实现精准医学。多模态大型语言模型（LLM）的最新进展展现出跨异构数据模态进行整合与推理的卓越能力。然而，面向患者特异性蛋白质组学的分子理解来执行多模态语言建模仍是一项重大挑战，原因在于两大障碍：（1）缺乏能够从蛋白质组学数据进行临床解读的指令微调数据集；（2）缺乏旨在捕捉分子数据丰富异质性的语言建模架构。在本研究中，我们推出 CPTAC-PROTSTRUCT，这是首个用于肿瘤学分子理解的指令微调数据集，包含超过 40 万个开放式示例，这些示例源自从最大的全国性蛋白质组学癌症研究（CPTAC）中整理的个体化蛋白质组学图谱。此外，我们提出 KRONOS（Knowledge Representation of patient Omics Networks in Oncology via Structured tuning，即通过结构化微调对肿瘤学中患者组学网络进行知识表示），这是一种新颖的 graph-LLM 框架，利用分子相互作用拓扑结构与蛋白质组学来学习患者特异性图表示，以增强临床推理能力。我们表明，KRONOS 在多项基准临床任务中取得了具有竞争力的性能，包括基于蛋白质组学数据的分子分类、时间轨迹建模和肿瘤分期预测。最终，该方法使 LLM 能够理解患者层面的发病机制，通过更准确的诊断、预后和治疗分层推进精准医学。
英文摘要：
Proteomics data is essential to pathogenic understanding of a disease phenotype. In cancer, analysis of molecular signatures enables precision medicine through the identification of biological processes that drive individualized tumor progression, therapeutic resistance, and clinical heterogeneity. Recent advances in multimodal large language models (LLMs) have shown remarkable capacity to integrate and reason across heterogeneous data modalities. However, performing multi-modal language modeling for molecular understanding of patient-specific proteomics remains a significant challenge due to two barriers: (1) the lack of instruction-tuning datasets that enable clinical interpretation from proteomics data, and (2) the absence of language modeling architectures designed to capture the rich heterogeneity of molecular data. In this work, we introduce CPTAC-PROTSTRUCT, the first instruction tuning dataset for molecular understanding of oncology, comprising over 400k open-ended examples derived from individualized proteomic profiles curated from the largest national proteomics cancer study (CPTAC). Additionally, we propose KRONOS (Knowledge Representation of patient Omics Networks in Oncology via Structured tuning), a novel graph-LLM framework that leverages molecular interaction topology with proteomics to learn patient-specific graph representations for enhanced clinical reasoning. We show that KRONOS achieves competitive performance across benchmark clinical tasks, including molecular classification, temporal trajectory modeling, and tumor stage prediction from proteomics data. Ultimately, this approach empowers LLMs to understand patient-level pathogenesis, advancing precision medicine through more accurate diagnosis, prognosis, and treatment stratification.
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。
