Identifying Predictive Features in Drug Response Using Machine Learning: Opportunities and Challenges.
This article reviews several techniques from machine learning that can be used to study the problem of identifying a small number of features, from among tens of thousands of measured features, that can accurately predict a drug response. Prediction problems are divided into two categories: sparse c...
| Publicado en: | Annual Review of Pharmacology & Toxicology Vol. 55; pp. 15 - 31 |
|---|---|
| Autor principal: | |
| Formato: | equations & formulas review tables/charts Journal Article |
| Publicado: |
Annual Reviews Inc.
2015
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=100273998&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 100273998 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 03621642 26P jtl: Annual Review of Pharmacology & Toxicology issn: 03621642 maglogo: N pubinfo: dt: 2015 vid: 55 pid: 59 pub: Annual Reviews Inc. place: Palo Alto, California artinfo: ui: 100273998 100273998 100273998 10.1146/annurev-pharmtox-010814-124502 100273998 ppf: 15 ppct: 16 formats: tig: atl: Identifying Predictive Features in Drug Response Using Machine Learning: Opportunities and Challenges. aug: au: Vidyasagar, Mathukumalli affil: Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, Texas 75080; email: sug: subj: Chemistry, Pharmaceutical Methods Chemotherapy, Cancer Drug Therapy Evaluation Microarray Analysis Neural Networks (Computer) Genes Pharmacy and Pharmacology ab: This article reviews several techniques from machine learning that can be used to study the problem of identifying a small number of features, from among tens of thousands of measured features, that can accurately predict a drug response. Prediction problems are divided into two categories: sparse classification and sparse regression. In classification, the clinical parameter to be predicted is binary, whereas in regression, the parameter is a real number. Well-known methods for both classes of problems are briefly discussed. These include the SVM (support vector machine) for classification and various algorithms such as ridge regression, LASSO (least absolute shrinkage and selection operator), and EN (elastic net) for regression. In addition, several well-established methods that do not directly fall into machine learning theory are also reviewed, including neural networks, PAM (pattern analysis for microarrays), SAM (significance analysis for microarrays), GSEA (gene set enrichment analysis), and k-means clustering. Several references indicative of the application of these methods to cancer biology are discussed. pubtype: Academic Journal doctype: equations & formulas review tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|