Machine Learning Approaches Distinguish Multiple Stress Conditions using Stress-Responsive Genes and Identify Candidate Genes for Broad Resistance in Rice

Abstract

Abiotic and biotic stress responses are traditionally thought to be regulated by discrete signaling mechanisms. Recent experimental evidence revealed a more complex picture where these mechanisms are highly entangled and can have synergistic and antagonistic effects on each other. In this study, we identified shared stress-responsive genes between abiotic and biotic stresses in rice (Oryza sativa) by performing meta-analyses of microarray studies. About 70% of the 1,377 common differentially expressed genes showed conserved expression status, and the majority of the rest were down-regulated in abiotic stresses and up-regulated in biotic stresses. Using dimension reduction techniques, principal component analysis, and partial least squares discriminant analysis, we were able to segregate abiotic and biotic stresses into separate entities. The supervised machine learning model, recursive-support vector machine, could classify abiotic and biotic stresses with 100% accuracy using a subset of differentially expressed genes. Furthermore, using a random forests decision tree model, eight out of 10 stress conditions were classified with high accuracy. Comparison of genes contributing most to the accurate classification by partial least squares discriminant analysis, recursive-support vector machine, and random forests revealed 196 common genes with a dynamic range of expression levels in multiple stresses. Functional enrichment and coexpression network analysis revealed the different roles of transcription factors and genes responding to phytohormones or modulating hormone levels in the regulation of stress responses. We envisage the top-ranked genes identified in this study, which highly discriminate abiotic and biotic stresses, as key components to further our understanding of the inherently complex nature of multiple stress responses in plants.

expVIP: a Customizable RNA-seq Data Analysis and Visualization Platform

“…We found that slightly more genes were up-regulated than down-regulated in abiotic stresses, whereas in disease conditions, the opposite pattern was observed: this contrasts with a previous meta-analysis of rice abiotic and biotic stress microarray experiments, where 60% of differentially express genes were down-regulated under abiotic stress and 60% of differentially expressed genes were up-regulated under biotic stress (Shaik and Ramakrishna, 2014). These results may be different because the rice analysis included additional stress conditions that might have influenced overall trends, microarrays having an incomplete gene complement, or biological differences between species.…”

Revealing Shared and Distinct Gene Network Organization in Arabidopsis Immune Responses by Integrative Analysis

“…By converting the selection of immune-related genes into a task to classify the conditions of the expression profiles, NGF automatically identified immune-related genes, and it reveals advantages over some existing methods used in plant systems biology. Compared with other differential expression analyses based on machine-learning methods (Shaik and Ramakrishna, 2014), the major innovation of NGF is that it incorporates the gene network as a priori knowledge to effectively narrow the hypothesis space of candidate genes. In contrast to network-based methods that rely on known functional genes to discover new candidates (Lee et al, 2010;Ma et al, 2014), NGF can be regarded as a de novo gene discovery algorithm, which is particularly useful when only few genes involved in the biological process of interest are known.…”

“…Technically, machinelearning algorithms are very good at extracting information from a large amount of data in an automated way. State-of-the-art machine-learning methods have been used to successfully identify stress-responsive genes (Ma et al, 2014;Shaik and Ramakrishna, 2014) and development-related gene associations (Bassel et al, 2011a) from large-scale plant gene expression data. Recently, Dutkowski and Ideker (2011) proposed a new machine-learning ranking algorithm called the networkguided forest (NGF).…”

The phenotype alterations showed by the res tomato mutant disappear when the plants are grown under semi-arid conditions: Is the res mutant tolerant to multiple stresses?

“…The climate change is already causing the surge of major abiotic stresses and will also influence biotic stresses impact on plants and, therefore, it is necessary to develop a resilient agricultural system in order to uphold the increasing food demand worlwide. 1,2 Moreover, the problem is more complex due to the fact that plant response to multiple stresses is different from that for individual stresses, and the molecular signaling pathways controlling biotic and abiotic stress responses may interact and antagonize each other. 3,4 The responses to biotic and abiotic stresses are largely controlled by different hormone signaling pathways, being JA a clear example.…”