Abstract
Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM) algorithm combined with a standard recursive feature elimination (RFE) approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60). The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be “drivers” of cancer onset/progression. Application of our models to publically available ovarian cancer (OC) patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm “open source”, we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.
Highlights
The sequencing of the human genome, genome-wide association studies (GWAS), quantitative trait loci (QTL) mapping, and similar research initiatives over the past few decades have greatly increased our understanding of the molecular pathways associated with human diseases
We present here an open source software platform using a highly versatile support vector machine (SVM) algorithm that utilizes standard recursive feature elimination (RFE) methods to predict cancer drug response
We utilize an SVM approach paired with recursive feature elimination (RFE)
Summary
The sequencing of the human genome, genome-wide association studies (GWAS), quantitative trait loci (QTL) mapping, and similar research initiatives over the past few decades have greatly increased our understanding of the molecular pathways associated with human diseases These efforts have significantly benefited from the liberal sharing of data and open-source. While a number of ML applications for precision medicine have benefited from community assessments of predicted drug response [e.g., [1,2]), such efforts have not always shared code, and for the majority of efforts only the organizers of the community assessment exercise were able to see the source code to evaluate each independent solution This is unfortunate because the open sharing of code has been demonstrated to be a significant catalyst in the optimization of ML applications as in the Large Scale Visual Recognition Challenge (ILSVRC) where computational solutions are openly available [6,7]
Sign-in/Register to view highlights & summary 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.
