Teamwork: improved eQTL mapping using combinations of machine learning methods

Expression quantitative trait loci (eQTL) mapping is a widely used technique to uncover regulatory relationships between genes. A range of methodologies have been developed to map links between expression traits and genotypes. The DREAM (Dialogue on Reverse Engineering Assessments and Methods) initi...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2012-07, Vol.7 (7), p.e40916-e40916
Main Authors: Ackermann, Marit, Clément-Ziza, Mathieu, Michaelson, Jacob J, Beyer, Andreas
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Biology
Biotechnology
Chromosome Mapping
Committees
Computational Biology - methods
Computer applications
Computer simulation
Data mining
Forest management
Gene expression
Gene Expression Profiling - methods
Gene mapping
Gene Regulatory Networks
Genes
Genetic diversity
Genetics
Genomics
Genotype
Genotypes
International conferences
Learning algorithms
Machine learning
Mapping
Methods
Quantitative genetics
Quantitative Trait Loci
Reverse engineering
ROC Curve
Self evaluation
Statistical methods
Teaching methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Expression quantitative trait loci (eQTL) mapping is a widely used technique to uncover regulatory relationships between genes. A range of methodologies have been developed to map links between expression traits and genotypes. The DREAM (Dialogue on Reverse Engineering Assessments and Methods) initiative is a community project to objectively assess the relative performance of different computational approaches for solving specific systems biology problems. The goal of one of the DREAM5 challenges was to reverse-engineer genetic interaction networks from synthetic genetic variation and gene expression data, which simulates the problem of eQTL mapping. In this framework, we proposed an approach whose originality resides in the use of a combination of existing machine learning algorithms (committee). Although it was not the best performer, this method was by far the most precise on average. After the competition, we continued in this direction by evaluating other committees using the DREAM5 data and developed a method that relies on Random Forests and LASSO. It achieved a much higher average precision than the DREAM best performer at the cost of slightly lower average sensitivity.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0040916