English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Predicting related traits from SNP markers by multi-task learning

Lippert, C., Stegle, O., Jegelka, S., Altun, Y., & Borgwardt, K. (2009). Predicting related traits from SNP markers by multi-task learning. Poster presented at German Conference on Bioinformatics (GCB 2009), Halle, Germany.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0003-0FF2-C Version Permalink: http://hdl.handle.net/21.11116/0000-0003-0FF3-B
Genre: Poster

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Lippert, C1, 2, Author              
Stegle, O1, 2, Author              
Jegelka, S2, 3, Author              
Altun, Y2, 3, Author              
Borgwardt, KM1, 2, Author              
Affiliations:
1Former Research Group Machine Learning and Computational Biology, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_2528696              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              
3Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              

Content

show
hide
Free keywords: -
 Abstract: The availability of the genetic background of large sample groups motivates genome-wide association studies which map the phenome of the sample to various genetic loci. A multitude of complex, high-dimensional phenotypes, like physiological measurements, cannot be treated as independent entities. Instead, pleiotropy, i.e. single genetic loci influencing large sets of phenotypes, calls for methods that account for interdependencies of the phenotypic traits. We address this important challenge using multi-task learning, providing a systematic framework to exploit the correlation structure of the phenome. Our method is scalable, allows large numbers of putative regulators and phenotypes to be modeled in a joint fashion. Here, Y is a phenotype matrix of N individuals \(\times\) K phenotypes, X is a genotype matrix of N individuals \(\times\) M SNPs, \& is a M\(\times\)K matrix that assigns phenotype-specific weights to SNPs and \% is a K \(\times\) K matrix combining the predictions of correlated phenotypes. To ensure interpretability of the solutions, we employ a transparent sparsity prior, regularizing the weights \& on a per SNP level. This choice of regularization encourages sparse relations to SNPs while sharing information across correlated phenotypes. Methodologically, our approach advances the state-of-the-art [Kim+09] by jointly modeling of the correlation structure of the phenome and the relationships between SNPs and phenotypes. This leads to an optimization problem that is not jointly convex; however, can be efficiently tackled using an alternating procedure.},

Details

show
hide
Language(s):
 Dates: 2009-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: German Conference on Bioinformatics (GCB 2009)
Place of Event: Halle, Germany
Start-/End Date: 2009-09-28 - 2009-09-30

Legal Case

show

Project information

show

Source 1

show
hide
Title: German Conference on Bioinformatics (GCB 2009)
Source Genre: Proceedings
 Creator(s):
Grosse, I, Editor
Neumann, S, Editor
Posch, S, Editor
Schreiber, F, Editor
Stadler, P, Editor
Affiliations:
-
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: 110 Start / End Page: 190 - 191 Identifier: -