Machine Learning-Based Differential Network Analysis: A Study of Stress-Responsive Transcriptomes in Arabidopsis

Machine learning (ML) Is an intelligent data mining technique that builds a prediction model based on the learning of prior knowledge to recognize patterns in large-scale data sets. We present an ML-based methodology for transcriptome analysis via comparison of gene coexpression networks, implemente...

Full description

Saved in:
Bibliographic Details
Published in:The Plant cell 2014-02, Vol.26 (2), p.520-537
Main Authors: Ma, Chuang, Xin, Mingming, Feldmann, Kenneth A., Wang, Xiangfeng
Format: Article
Language:English
Subjects:
Arabidopsis - genetics
Arabidopsis - physiology
Artificial Intelligence
Bioinformatics
Correlations
Databases, Genetic
Datasets
DNA damage
Drought
Gene expression
Gene Expression Profiling
Gene Expression Regulation, Plant
Gene Regulatory Networks
Genes
Genes, Plant
Genetic Association Studies
Large-Scale Biology
LARGE-SCALE BIOLOGY ARTICLE
Modeling
Phenotype
Plant cells
Plants
Signal Transduction - drug effects
Signal Transduction - genetics
Sodium Chloride - pharmacology
Software
Stress, Physiological - genetics
Transcriptome - genetics
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning (ML) Is an intelligent data mining technique that builds a prediction model based on the learning of prior knowledge to recognize patterns in large-scale data sets. We present an ML-based methodology for transcriptome analysis via comparison of gene coexpression networks, implemented as an R package called machine learning-based differential network analysis (mIDNA) and apply this method to reanalyze a set of abiotic stress expression data in Arabidopsis thaliana. The mIDNA first used a ML-based filtering process to remove nonexpressed, constitutively expressed, or non-stressresponsive "noninformative" genes prior to network construction, through learning the patterns of 32 expression characteristics of known stress-related genes. The retained "informative" genes were subsequently analyzed by ML-based network comparison to predict candidate stress-related genes showing expression and network differences between control and stress networks, based on 33 network topological characteristics. Comparative evaluation of the network-centric and gene-centric analytic methods showed that mIDNA substantially outperformed traditional statistical testing-based differential expression analysis at identifying stress-related genes, with markedly improved prediction accuracy. To experimentally valldate the mIDNA predictions, we selected 89 candidates out of the 1784 predicted salt stress-related genes with available SALK T-DNA mutagenesis lines for phenotypic screening and identified two previously unreported genes, mutants of which showed salt-sensitive phenotypes.
ISSN:1040-4651
1532-298X
DOI:10.1105/tpc.113.121913