面向临床医生的药物重定位基础模型
研究提出TxGNN图基础模型,基于医学知识图谱实现零样本药物重定位,为17080种疾病排序潜在适应证和禁忌证。在严格零样本评估下,相比8种方法,适应证预测准确率提升49.2%,禁忌证提升35.1%。Explainer模块提供多跳医学知识路径解释,预测与大型医疗系统中临床医生超说明书用药一致。
要点
- TxGNN是图基础模型,可为零样本药物重定位排序17080种疾病的适应证和禁忌证。
- 严格零样本评估下,适应证预测准确率较8种方法提升49.2%,禁忌证提升35.1%。
- Explainer模块提供多跳医学知识路径,人体评估显示预测和解释在多个维度表现令人鼓舞。
核心结论
- TxGNN的药物重定位预测准确,与超说明书用药一致,并可通过多跳可解释理由供人类专家研究。
研究设计与样本
- 研究提出TxGNN图基础模型,在医学知识图谱上训练,使用图神经网络和度量学习模块,对17080种疾病排序药物作为潜在适应证和禁忌证。
- 模型与8种方法进行基准比较,采用严格零样本评估。
主要发现
- 在严格零样本评估下,TxGNN对适应证预测准确率较8种方法提升49.2%,对禁忌证预测准确率提升35.1%。
- TxGNN的Explainer模块提供多跳医学知识路径作为预测理由,人体评估显示预测和解释在准确率之外的多个性能轴上表现令人鼓舞。
- TxGNN的许多新预测与临床医生在大型医疗系统中先前做出的超说明书处方一致。
关键数值与推荐
- 适应证预测准确率提升49.2%,禁忌证预测准确率提升35.1%,均为严格零样本评估下与8种方法比较。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Drug repurposing-identifying new therapeutic uses for approved drugs-is often a serendipitous and opportunistic endeavour to expand the use of drugs for new diseases. The clinical utility of drug-repurposing artificial intelligence (AI) models remains limited because these models focus narrowly on diseases for which some drugs already exist. Here we introduce TxGNN, a graph foundation model for zero-shot drug repurposing, identifying therapeutic candidates even for diseases with limited treatment options or no existing drugs. Trained on a medical knowledge graph, TxGNN uses a graph neural network and metric learning module to rank drugs as potential indications and contraindications for 17,080 diseases. When benchmarked against 8 methods, TxGNN improves prediction accuracy for indications by 49.2% and contraindications by 35.1% under stringent zero-shot evaluation. To facilitate model interpretation, TxGNN's Explainer module offers transparent insights into multi-hop medical knowledge paths that form TxGNN's predictive rationales. Human evaluation of TxGNN's Explainer showed that TxGNN's predictions and explanations perform encouragingly on multiple axes of performance beyond accuracy. Many of TxGNN's new predictions align well with off-label prescriptions that clinicians previously made in a large healthcare system. TxGNN's drug-repurposing predictions are accurate, consistent with off-label drug use, and can be investigated by human experts through multi-hop interpretable rationales.
引用
- Huang K, Chandak P, Wang Q, et al. A foundation model for clinician-centered drug repurposing. Nat Med. 2024. PMID: 39322717. doi:10.1038/s41591-024-03233-x
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。