Multi-SConES

Main content

Mahito Sugiyama, Chloe-Agathe Azencott, Dominik Grimm, Yoshinobu Kawahara and Karsten Borgwardt

Multi-Task Feature Selection on Multiple Networks via Maximum Flows

Summary

This is a multi-task version of SConES, that allows for network GWAS with more than one network and more than one phenotype. This method achieves multi-task feature selection coupled with multiple network regularizers using a maximum-flow algorithm.

Code

An R implementation of the method can be found in our GitHub repository here.

Reference

Please see the following paper for detailed information and refer it in your published research.

Keyboard navigation between tabs via Alt arrow keys as well as Home and End.

Mahito Sugiyama, Chloé-Agathe Azencott, Dominik Grimm, Yoshinobu Kawahara, Karsten Borgwardt.
Multi-Task Feature Selection on Multiple Networks via Maximum Flows.
Proceedings of the 2014 SIAM International Conference on Data Mining. 2014, 199-207. (Online)

The article and supplementary information can be downloaded here: (Article, Supplement (PDF, 67 KB))

@inbook{Sugiyama_multi_2014,
author = {Mahito Sugiyama and Chlo\'{e}-Agathe Azencott and Dominik Grimm and Yoshinobu Kawahara and Karsten M. Borgwardt},
title = {Multi-{T}ask {F}eature {S}election on {M}ultiple {N}etworks via {M}aximum {F}lows},
booktitle = {Proceedings of the 2014 SIAM International Conference on Data Mining},
chapter = {23},
pages = {199-207},
doi = "10.1137/1.9781611973440.23",
URL = {http://epubs.siam.org/doi/abs/10.1137/1.9781611973440.23},
eprint = {http://epubs.siam.org/doi/pdf/10.1137/1.9781611973440.23}
}

 
 
Page URL: https://www.bsse.ethz.ch/mlcb/research/bioinformatics-and-computational-biology/multi-scones.html
27.04.2017
© 2017 Eidgenössische Technische Hochschule Zürich