This repository stores the code for the final project of CSCI 5523 Fall 2020 from the team Drug Sensor.
Predicting drug response to assist creating the best treatment strategy from genomic information is an essential goal of precision medicine. We have noticed the collaborative effort between the National Cancer Institute (NCI) and the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project which provides a platform for us to develop drug sensitivity prediction algorithms on a genomic profiling data set measured in human breast cancer cell lines. We mainly focused on selecting interesting drug targets and applying various supervised learning approaches to predict drug sensitivity for a panel of cell lines based on gene expression profiles, during which we also explored feature engineering and dimension reduction techniques.
Each member contributed equally to this project. More specifically, Yixuan Wang was responsible for data analysis. Yu Fang, Yu Han, Xianjian Xie, and Xiang Zhang investigated the different machine learning models respectively.
Reference:
Costello, J. C. et al. A community effort to assess and improve drug sensitivity prediction algorithms. Nat. Biotechnol. 32, 1202–1212 (2014).