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 (mlDNA) and apply this method to reanalyze a set of abiotic stress expression data in Arabidopsis thaliana. The mlDNA first used a ML-based filtering process to remove nonexpressed, constitutively expressed, or non-stress-responsive “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 mlDNA substantially outperformed traditional statistical testing–based differential expression analysis at identifying stress-related genes, with markedly improved prediction accuracy. To experimentally validate the mlDNA 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.

Supplemental Dataset 1Known Stress-related Genes Collected from the TAIR and DRASTIC Databases, their Expression Changes in the Stress Microarray Datasets, and the Statistical Results of their Gene Ontology (GO) AnnotationsSupplemental Dataset 2“Informative” Genes Obtained from PSOL-based ML Analysis for Gene Co-expression Network Construction under Six Studied Stresses in Two TissuesSupplemental Dataset 3Candidate Stress-related Genes Predicted by mlDNASupplemental Dataset 4List of the Candidate Stress-related Genes Evidenced by a High-throughput Phenotypic Screening ExperimentSupplemental Dataset 5Detailed Information for Gene Ontology (GO) Modules Enriched with Salt Stress-related GenesSupplemental Dataset 6List of Stress Shared GenesSupplemental Dataset 7List of Stress-Specific Genes