DISIS: prediction of drug response through an iterative sure independence screening

PloS One
Yun FangXiaoqi Zheng

Abstract

Prediction of drug response based on genomic alterations is an important task in the research of personalized medicine. Current elastic net model utilized a sure independence screening to select relevant genomic features with drug response, but it may neglect the combination effect of some marginally weak features. In this work, we applied an iterative sure independence screening scheme to select drug response relevant features from the Cancer Cell Line Encyclopedia (CCLE) dataset. For each drug in CCLE, we selected up to 40 features including gene expressions, mutation and copy number alterations of cancer-related genes, and some of them are significantly strong features but showing weak marginal correlation with drug response vector. Lasso regression based on the selected features showed that our prediction accuracies are higher than those by elastic net regression for most drugs.

References

Mar 23, 2001·The Journal of Biological Chemistry·T KataokaJ Tschopp
Sep 13, 2001·Proceedings of the National Academy of Sciences of the United States of America·J E StauntonT R Golub
May 7, 2003·The Journal of Biological Chemistry·Michele D VosGeoffrey J Clark
Aug 6, 2004·The New England Journal of Medicine·Amy HollemanWilliam E Evans
Apr 27, 2005·Journal of Bioinformatics and Computational Biology·Chris Ding, Hanchuan Peng
Aug 27, 2005·IEEE Transactions on Pattern Analysis and Machine Intelligence·Hanchuan PengChris Ding
Dec 22, 2005·Cancer Science·Naoyuki HommaTeiichi Motoyama
Aug 2, 2007·Proceedings of the National Academy of Sciences of the United States of America·Jae K LeeDan Theodorescu
Apr 11, 2009·Nature·Michael R StrattonP Andrew Futreal
Jan 1, 2008·Journal of the Royal Statistical Society. Series B, Statistical Methodology·Hao Helen Zhang
Dec 8, 2010·Bioinformatics·Gregory RiddickHoward A Fine
Mar 1, 2012·BMC Proceedings·Yue S NiuLingling An
Sep 4, 2012·International Journal of Molecular Sciences·Abida AbudukadeerHeidi Fiegl

❮ Previous
Next ❯

Citations

Dec 8, 2016·Artificial Intelligence in Medicine·Mehmet Tan
Sep 24, 2020·BMC Medical Informatics and Decision Making·Biao AnYufang Qin
Jan 18, 2017·Computational and Mathematical Methods in Medicine·Selen Yılmaz IsıkhanCelal Reha Alpar
Aug 6, 2019·Frontiers in Chemistry·Pavel SidorovPedro J Ballester

❮ Previous
Next ❯

Methods Mentioned

BETA
chemical therapy

Software Mentioned

ENR
ActiveArea
Elastic
Random Forest
STF
ISIS

Related Concepts

Related Feeds

Cancer Genomics (Keystone)

Cancer genomics approaches employ high-throughput technologies to identify the complete catalog of somatic alterations that characterize the genome, transcriptome and epigenome of cohorts of tumor samples. Discover the latest research using such technologies in this feed.