精确肿瘤学
精密医学
计算生物学
医学
重新调整用途
临床试验
药物重新定位
计算机科学
生物信息学
医学物理学
模式
瓶颈
特征(语言学)
一致性
虚拟病人
转化研究
匹配(统计)
药物开发
可扩展性
伴生诊断
治疗方式
临床实习
构造(python库)
肿瘤科
药物发现
免疫疗法
免疫原性
作者
Zhongyi Hu,Yanrong Sun,Jiao Yuan,Tong Su,Yuxin Wang,Jie Huang,Eleanor Taranto,Junjie Jiang,Junjie Nie,Meixiao Long,Jennifer Q. Zhang,Janos Laszlo Tanyi,Yi Fan,Ravi K. Amaravadi,Jeffrey Kaufman,Josh Sommer,Nicole Spardy Burr,Daniel M. Freed,Enjun Yang,Christopher R. Cabanski
标识
DOI:10.1158/2159-8290.cd-26-1021
摘要
The rapid expansion of antibody therapeutics is shifting the clinical bottleneck from drug availability to precise patient selection. We systematically characterize 87 clinically actionable tumor-associated antigens across solid tumors by integrating transcriptomic, proteomic, spatial, and single-cell profiles from more than 32,000 specimens to define expression prevalence, intratumoral heterogeneity, immune contexture, internalization and payload-sensitivity pathways, and translational relevance. We establish ANCHOR, a coordinate reference framework for standardizing patient RNA-seq data, and develop ReSort, a two-tiered scoring system for scalable target prioritization. ReSort enables virtual basket and umbrella trial matching, demonstrates concordance with clinical assays, predicts therapeutic response in patient-derived models, and identifies repurposing opportunities in rare malignancies. We develop an AI-based decision-support agent for antibody trial matching and construct a multimodal feature space integrating tumor- and protein-intrinsic attributes to guide systematic target discovery and prioritization. This work provides a scalable, clinically actionable approach for precision antibody-based therapies and next-generation target development.
科研通智能强力驱动
Strongly Powered by AbleSci AI