Leveraging TCGA gene expression data to build predictive models for cancer drug response

• Type of Material: Article
• Authors: Evan A. Clayton, Georgia Institute of Technology; Toyya A. Pujol, Georgia Institute of Technology; John F. McDonald, Georgia Institute of Technology; Peng Qiu, Emory University
• Language: English
• Date: 2020-09-30
• Publisher: BMC
• Publication Version: Final Published Version
• Copyright Statement: © The Author(s) 2020
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1186/s12859-020-03690-4
• Title of Journal or Parent Work: BMC Bioinformatics
• Volume: 21
• Issue: Suppl 14
• Start Page: 364
• End Page: 364
• Grant/Funding Information: This work was supported by the National Institute of Health (T32, GM105490, CRP:10–2012-03), the National Science Foundation (CCF1552784), and the Giglio Family Breast Cancer Fund. PQ is an ISAC Marylou Ingram Scholar and a Carol Ann and David D. Flanagan Faculty Fellow. Publication costs are funded by PQ’s Faculty Fellowship. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
• Keywords: Fluorouracil; Neoplasms; Gene Expression Regulation, Neoplastic; Cluster Analysis; Personalized oncology; ROC Curve; Antineoplastic Agents; Predictive models; Drug response; Machine learning; Area Under Curve; Databases, Genetic; Humans; Machine Learning; Deoxycytidine
• Research Categories: Health Sciences, Oncology; Biology, Genetics

Abstract

Background: Machine learning has been utilized to predict cancer drug response from multi-omics data generated from sensitivities of cancer cell lines to different therapeutic compounds. Here, we build machine learning models using gene expression data from patients' primary tumor tissues to predict whether a patient will respond positively or negatively to two chemotherapeutics: 5-Fluorouracil and Gemcitabine. Results: We focused on 5-Fluorouracil and Gemcitabine because based on our exclusion criteria, they provide the largest numbers of patients within TCGA. Normalized gene expression data were clustered and used as the input features for the study. We used matching clinical trial data to ascertain the response of these patients via multiple classification methods. Multiple clustering and classification methods were compared for prediction accuracy of drug response. Clara and random forest were found to be the best clustering and classification methods, respectively. The results show our models predict with up to 86% accuracy; despite the study's limitation of sample size. We also found the genes most informative for predicting drug response were enriched in well-known cancer signaling pathways and highlighted their potential significance in chemotherapy prognosis. Conclusions: Primary tumor gene expression is a good predictor of cancer drug response. Investment in larger datasets containing both patient gene expression and drug response is needed to support future work of machine learning models. Ultimately, such predictive models may aid oncologists with making critical treatment decisions.