Thecis-regulatory codes of response to combined heat and drought stress inArabidopsis thaliana

Abstract

Plants respond to their environment by dynamically modulating gene expression. A powerful approach for understanding how these responses are regulated is to integrate information about cis-regulatory elements (CREs) into models called cis-regulatory codes. Transcriptional response to combined stress is typically not the sum of the responses to the individual stresses. However, cis-regulatory codes underlying combined stress response have not been established. Here we modeled transcriptional response to single and combined heat and drought stress in Arabidopsis thaliana. We grouped genes by their pattern of response (independent, antagonistic, synergistic) and trained machine learning models to predict their response using putative CREs (pCREs) as features (median F-measure = 0.64). We then developed a deep learning approach to integrate additional omics information (sequence conservation, chromatin accessibility, histone modification) into our models, improving performance by 6.2%. While pCREs important for predicting independent and antagonistic responses tended to resemble binding motifs of transcription factors associated with heat and/or drought stress, important synergistic pCREs resembled binding motifs of transcription factors not known to be associated with stress. These findings demonstrate how in silico approaches can improve our understanding of the complex codes regulating response to combined stress and help us identify prime targets for future characterization.in nature and elicit both overlapping and conflicting physiological responses in plants (36). Moreover, TFs and TF binding motifs are known for these stresses individually (37,38). To better understand the regulatory logic underlying single and combined stress, first, we grouped genes likely to be co-regulated based on their shared pattern of transcriptional response under single and combined heat and drought stress (14) (Step 1, Fig. 1). Then, we used known TFBMs and enrichment based pCREs (Step 2, Fig. 1) to generate models of the cis-regulatory codes controlling these different patterns of responses to single and combined heat and drought stress using machine learning. To improve our models of the cisregulatory codes and therefore our understanding of how response to single and combined stress is regulated in A. thaliana, we modeled regulatory interactions (Step 3A, Fig. 1), used a deep learning approach to integrate additional omics information (i.e. chromatin accessibility, sequence conservation, and histone marks) into our models (Step 3B, Fig. 1), and expanded the scope of our models by including pCREs identified outside of the promoter region ( Step 3C, Fig. 1). In addition to providing a comprehensive overview of the cis-regulatory codes of response to single and combined heat and drought stress in A. thaliana, this study also exemplifies how a data-driven approach can be used to make novel discoveries in a complex system like gene regulation (Step 4, Fig.1). MATERIALS AND METHODS Expression data processing, response group classificat...

Predicting transcriptional responses to cold stress across plant species

“…3 B ). The importance of exonic features relative to upstream and downstream regions observed across grasses for cold in this study is the opposite of the pattern reported in a recent study of heat- and drought-responsive genes in Arabidopsis using k-mer features ( 36 ). The involvement of UTRs in transcriptional regulation was also observed in a study predicting mRNA expression levels from DNA sequence features in maize and sorghum ( 24 ).…”

Applying cis-regulatory codes to predict conserved and variable heat and cold stress response in maize

“…The full set (all motifs associated with the sets of all up- or down- regulated genes or specific co-expression clusters) of motifs identified for cold or heat responsive expression (above) were used and we determined the presence/absence for each motif within different sets of search spaces (Figure 3A) to assess how the use of different potential ‘promoter’ regions would affect model performance. The approach previously described by Zou et al (Zou et al, 2011; Uygun et al, 2017, 2019; Azodi et al, 2020a) was implemented to utilize the motif features to predict whether genes will exhibit cold- or heat-responsive expression. For each co-expression cluster, we compared the genes in the cluster to an equivalent number of genes that are expressed, but not classified as DE; and ran the model 100 times using all motifs, or only retaining the most highly enriched motifs (top 30, 50, 100 or 200) followed by calculation of the AUROC (see Methods for details; Figure 4; Figure S10).…”

“…Machine learning approaches have provided new and powerful ways for understanding and predicting gene expression in plants (Azodi et al, 2020b; Wang et al, 2020b; Washburn et al, 2019). These approaches have been used to predict expression levels (Washburn et al, 2019; Sartor et al, 2019), regulatory architecture (Mejía-Guerra and Buckler, 2019), as well as gene expression responses to abiotic stress (Zou et al, 2011; Uygun et al, 2017, 2019; Azodi et al, 2020a; Schwarz et al, 2020). These studies highlight the potential to develop predictive models that use putative cis-regulatory motifs to predict gene expression responses to stress.…”

Machine learning approaches to identify core and dispensable genes in pangenomes

“…Machine learning has increasingly more often been applied to genomics research (Golicz et al 2020). For example,machine learning has been used to predict gene expression levels from genomic sequence data (Azodi, Lloyd, and Shiu, n.d.). Machine learning has also been used in the biomedical field to diagnose disease (Kourou et al 2015).…”