Your browser doesn't support javascript.
loading
Pathway-Based Genomics Prediction using Generalized Elastic Net.
Sokolov, Artem; Carlin, Daniel E; Paull, Evan O; Baertsch, Robert; Stuart, Joshua M.
Afiliação
  • Sokolov A; Department of Biomolecular Engineering and Center for Biomolecular Science and Engineering, University of California Santa Cruz, Santa Cruz, California, United States of America.
  • Carlin DE; Department of Biomolecular Engineering and Center for Biomolecular Science and Engineering, University of California Santa Cruz, Santa Cruz, California, United States of America.
  • Paull EO; Department of Biomolecular Engineering and Center for Biomolecular Science and Engineering, University of California Santa Cruz, Santa Cruz, California, United States of America.
  • Baertsch R; Department of Biomolecular Engineering and Center for Biomolecular Science and Engineering, University of California Santa Cruz, Santa Cruz, California, United States of America.
  • Stuart JM; Department of Biomolecular Engineering and Center for Biomolecular Science and Engineering, University of California Santa Cruz, Santa Cruz, California, United States of America.
PLoS Comput Biol ; 12(3): e1004790, 2016 Mar.
Article em En | MEDLINE | ID: mdl-26960204
We present a novel regularization scheme called The Generalized Elastic Net (GELnet) that incorporates gene pathway information into feature selection. The proposed formulation is applicable to a wide variety of problems in which the interpretation of predictive features using known molecular interactions is desired. The method naturally steers solutions toward sets of mechanistically interlinked genes. Using experiments on synthetic data, we demonstrate that pathway-guided results maintain, and often improve, the accuracy of predictors even in cases where the full gene network is unknown. We apply the method to predict the drug response of breast cancer cell lines. GELnet is able to reveal genetic determinants of sensitivity and resistance for several compounds. In particular, for an EGFR/HER2 inhibitor, it finds a possible trans-differentiation resistance mechanism missed by the corresponding pathway agnostic approach.
Assuntos

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Animals / Humans Idioma: En Ano de publicação: 2016 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Animals / Humans Idioma: En Ano de publicação: 2016 Tipo de documento: Article