Predicting transcriptional responses to cold stress across plant species

Authors

• Xiaoxi Meng, University of Nebraska-Lincoln
• Zhikai Liang, University of Nebraska - LincolnFollow
• Xiuru Dai, Shandong Agricultural University & University of Nebraska-Lincoln
• Yang Zhang, University of Nebraska-Lincoln
• Samira Mahboub, University of Nebraska-LincolnFollow
• Daniel W. Ngu, University of Nebraska-Lincoln
• Rebecca Roston, University of Nebraska- LincolnFollow
• James Schnable, University of Nebraska-LincolnFollow

ORCID IDs

Xiaoxi Meng http://orcid.org/0000-0001-7217-2037

Zhikai Liang http://orcid.org/0000-0002-9963-8631

Yang Zhang http://orcid.org/0000-0003-1712-7211

Rebecca L. Roston http://orcid.org/0000-0002-3063-5002

James C. Schnable http://orcid.org/0000-0001-6739-5527

Document Type

Article

Date of this Version

3-3-2021

Citation

PNAS 2021 Vol. 118 No. 10 e2026330118

https://doi.org/10.1073/pnas.2026330118

Abstract

Although genome-sequence assemblies are available for a growing number of plant species, gene-expression responses to stimuli have been cataloged for only a subset of these species. Many genes show altered transcription patterns in response to abiotic stresses. However, orthologous genes in related species often exhibit different responses to a given stress. Accordingly, data on the regulation of gene expression in one species are not reliable predictors of orthologous gene responses in a related species. Here, we trained a supervised classification model to identify genes that transcriptionally respond to cold stress. A model trained with only features calculated directly from genome assemblies exhibited only modest decreases in performance relative to models trained by using genomic, chromatin, and evolution/ diversity features. Models trained with data from one species successfully predicted which genes would respond to cold stress in other related species. Cross-species predictions remained accurate when training was performed in cold-sensitive species and predictions were performed in cold-tolerant species and vice versa. Models trained with data on gene expression in multiple species provided at least equivalent performance to models trained and tested in a single species and outperformed single-species models in cross-species prediction. These results suggest that classifiers trained on stress data from well-studied species may suffice for predicting gene-expression patterns in related, less-studied species with sequenced genomes.