期刊
NATURE CANCER
卷 2, 期 2, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s43018-020-00169-2
关键词
-
类别
资金
- National Cancer Institute [U54CA209891, R01CA204173, K22CA234406]
- National Institute of General Medical Sciences [P41GM103504]
- National Human Genome Research Institute [R01HG009979]
- Israel Science Foundation [715/18]
- National Science Foundation [1652815]
- ZonMw TOP grant COMPUTE CANCER [40-00812-98-16012]
- Cancer Prevention and Research Institute of Texas [CPRIT RR180035]
The study applies few-shot learning to train a versatile neural network model for predicting drug response, which can quickly adapt to different biological contexts and identify critical molecular features.
Ma et al. apply few-shot learning to train a neural network model on cell-line drug-response data, and they subsequently transfer it to distinct biological contexts including different tissues and patient-derived tumor cells and xenografts. Cell-line screens create expansive datasets for learning predictive markers of drug response, but these models do not readily translate to the clinic with its diverse contexts and limited data. In the present study, we apply a recently developed technique, few-shot machine learning, to train a versatile neural network model in cell lines that can be tuned to new contexts using few additional samples. The model quickly adapts when switching among different tissue types and in moving from cell-line models to clinical contexts, including patient-derived tumor cells and patient-derived xenografts. It can also be interpreted to identify the molecular features most important to a drug response, highlighting critical roles for RB1 and SMAD4 in the response to CDK inhibition and RNF8 and CHD4 in the response to ATM inhibition. The few-shot learning framework provides a bridge from the many samples surveyed in high-throughput screens (n-of-many) to the distinctive contexts of individual patients (n-of-one).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据