Anti-cancer drug sensitivity predictive modeling for improvement of precision medicine using machine learning algorithms



Journal Title

Journal ISSN

Volume Title



Precision medicine entails the design of therapies that are matched for each individual patient. Thus, predictive modeling of anti-cancer drug responses for specific patients constitutes a significant challenge for personalized therapy, which has been done by primarily focusing on generating functions that map gene expressions and genetic mutation profiles to drug sensitivity. Numerous algorithms have been proposed from time-to-time for mapping these genomic characterizations to drug sensitivity, such as ensemble based learning techniques, linear regression with regularization, kernel based methods, deep learning based approaches. The typical practice is to consider a training set of cell lines with experimentally-measured genomic characterizations (such as RNA-Seq, microarray gene expression, Reverse Phase Protein Array, methylation, SNPs, etc.) and responses to different drugs, to design supervised predictive models for each individual drug based on one or more genomic characterizations. In this dissertation, I have explored diverse approaches for drug sensitivity prediction and combination therapy design based on different genomic characterizations considering inner data properties. The ultimate objective of my research is to select most effective and optimal therapy for a new patient.



Anti-cancer drug sensitivity prediction, Machine learning, Precision medicine