Abstract
Cancer chemotherapy responses have been related to multiple pharmacogenetic biomarkers, often for the same drug. This study utilizes machine learning to derive multi‐gene expression signatures that predict individual patient responses to specific tyrosine kinase inhibitors, including erlotinib, gefitinib, sorafenib, sunitinib, lapatinib and imatinib. Support vector machine (SVM) learning was used to train mathematical models that distinguished sensitivity from resistance to these drugs using a novel systems biology‐based approach. This began with expression of genes previously implicated in specific drug responses, then expanded to evaluate genes whose products were related through biochemical pathways and interactions. Optimal pathway‐extended SVMs predicted responses in patients at accuracies of 70% (imatinib), 71% (lapatinib), 83% (sunitinib), 83% (erlotinib), 88% (sorafenib) and 91% (gefitinib). These best performing pathway‐extended models demonstrated improved balance predicting both sensitive and resistant patient categories, with many of these genes having a known role in cancer aetiology. Ensemble machine learning‐based averaging of multiple pathway‐extended models derived for an individual drug increased accuracy to >70% for erlotinib, gefitinib, lapatinib and sorafenib. Through incorporation of novel cancer biomarkers, machine learning‐based pathway‐extended signatures display strong efficacy predicting both sensitive and resistant patient responses to chemotherapy.
Highlights
We developed gene signatures that predict patient responses to specific chemotherapies from gene expression (GE) and copy number (CN) levels in a set of distinct breast and/or bladder cancer cell lines,[5] with each line characterized by the drug concentration that inhibited growth by half (GI50).[6,7]
Genes associated with drug response or function were curated for gefitinib (N = 113), sunitinib (N = 90), erlotinib (N = 71), imatinib (N = 157), sorafenib (N = 73) and lapatinib (N = 91)
Multiple factor analysis (MFA) analysis was performed on genes encoding proteins related to these curated genes to identify those that correlated, either directly or inversely, with GI50
Summary
We developed gene signatures that predict patient responses to specific chemotherapies from gene expression (GE) and copy number (CN) levels in a set of distinct breast and/or bladder cancer cell lines,[5] with each line characterized by the drug concentration that inhibited growth by half (GI50).[6,7] Support vector machine (SVM) and random forest machine learning (ML) models were built for each drug using expression and/or CN values from ‘curated genes’ with evidence from published cancer literature of a contribution to the function or response to said drug in cell lines or patients. This paper develops signatures for tyrosine kinase inhibitors (TKIs),[8] for which literature on genes associated with response is somewhat more limited
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
