Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients
- 25 January 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Cancer
- Vol. 2 (2), 233-244
- https://doi.org/10.1038/s43018-020-00169-2
Abstract
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).Keywords
Funding Information
- U.S. Department of Health & Human Services | NIH | National Cancer Institute (R01CA204173, K22CA234406, U54CA209891)
- Cancer Prevention and Research Institute of Texas (CPRIT RR180035)
- ZonMw (40-00812-98-16012, 40-00812-98-16012)
- Israel Science Foundation (1652815)
- National Science Foundation (1652815)
- U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences (P41GM103504)
- U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (R01HG009979)
This publication has 46 references indexed in Scilit:
- From Bench to Bedside: Lessons Learned in Translating Preclinical Studies in Cancer Drug DevelopmentJNCI Journal of the National Cancer Institute, 2013
- Unresponsiveness of colon cancer to BRAF(V600E) inhibition through feedback activation of EGFRNature, 2012
- Multiplexed array-based and in-solution genomic enrichment for flexible and cost-effective targeted next-generation sequencingNature Protocols, 2011
- Changes in breast cancer biomarkers in the IGF1R/PI3K pathway in recurrent breast cancer after tamoxifen treatmentEndocrine-Related Cancer, 2011
- Pathway Commons, a web resource for biological pathway dataNucleic Acids Research, 2010
- The chromatin-remodeling factor CHD4 coordinates signaling and repair after DNA damageThe Journal of cell biology, 2010
- Combined Vascular Endothelial Growth Factor Receptor and Epidermal Growth Factor Receptor (EGFR) Blockade Inhibits Tumor Growth in Xenograft Models of EGFR Inhibitor ResistanceClinical Cancer Research, 2009
- Translational research: Crossing the valley of deathNature, 2008
- Regularization and Variable Selection Via the Elastic NetJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- Inhibition of Smad Antiproliferative Function by CDK PhosphorylationCell Cycle, 2004