Exploiting Genomic Features to Improve the Prediction of Transcription Factor-Binding Sites in Plants

Abstract

The identification of transcription factor (TF) target genes is central in biology. A popular approach is based on the location by pattern-matching of potential cis-regulatory elements (CREs). During the last few years, tools integrating next-generation sequencing data have been developed to improve the performances of pattern-matching. However, such tools have not yet been comprehensively evaluated in plants. Hence, we developed a new streamlined method aiming at predicting CREs and target genes of plant TFs in specific organs or conditions. Our approach implements a supervised machine learning strategy, which allows to learn decision rule models using TF ChIP-chip/seq experimental data. Different layers of genomic features were integrated in predictive models: the position on the gene, the DNA-sequence conservation, the chromatin state, and various cis-regulatory element footprints. Among the tested features, the chromatin features were crucial for improving the accuracy of the method. Furthermore, we evaluated the transferability of predictive models across TFs, organs and species. Finally, we validated our method by correctly inferring the target genes of key TF controlling metabolite biosynthesis at the organ-level in Arabidopsis. We developed a tool -Wimtrap- to reproduce our approach in plant species and conditions/organs for which ChIP-chip/seq data are available. Wimtrap is a user-friendly R package that supports a R-shiny web interface and is provided with pre-built models that can be used to quickly get predictions of CREs and TF gene targets in different organs or conditions in Arabidopsis thaliana, Solanum lycopersicum, Oryza sativa, and Zea mays.

Differential gene expression during floral transition in pineapple

“…Various experimental approaches have been used to detect and validate cis‐regulatory transcription factor binding sites (TFBS) in vivo (Christ et al, 2013; Ishimori, 2022; Koschmann et al, 2012; Rivière et al, 2022; Yu, Lin, Li, et al, 2016). However, it is worth mentioning that the precision of identifying a TFBS using cross‐species modeling depends on the degree of divergence between the species with results suggesting that the approach has predictive value (Rivière et al, 2022). We evaluated the cis regulation motifs of the DNA gene to selected DE transcription factor (TF) binding motifs potentially involved in the transition of the shoot apical meristem to floral state.…”

“…In our investigation, Arabidopsis thaliana and Oryza sativa were used as model species, as cis‐DNA elements within noncoding regions are poorly annotated in most plant species (Galli et al, 2020). Various experimental approaches have been used to detect and validate cis‐regulatory transcription factor binding sites (TFBS) in vivo (Christ et al, 2013; Ishimori, 2022; Koschmann et al, 2012; Rivière et al, 2022; Yu, Lin, Li, et al, 2016). However, it is worth mentioning that the precision of identifying a TFBS using cross‐species modeling depends on the degree of divergence between the species with results suggesting that the approach has predictive value (Rivière et al, 2022).…”

An Evidence Theory and Fuzzy Logic Combined Approach for the Prediction of Potential ARF-Regulated Genes in Quinoa

“…Merge several types of information specific to ARF-binding sites to reduce false positives significantly. However, it still needs to be improved by introducing other parameters like digital genomic footprinting or DNase-I hypersensitivity score [ 73 ]. Further directions will be the development of algorithms by fusion more specific and recently investigated to predict ARF-binding sites.…”

Machine learning for major food crops breeding: Applications, challenges, and ways forward

“…Integrating one type of omics data from multiple public databases requires rigorous efforts. Hence, most ML studies on MFCs (Awad, 2019b; Gupta et al., 2021; Lin et al., 2019; Maldonado et al., 2020; Rivière et al., 2022; Sirsat et al., 2022; Wang et al., 2021) utilize only one type of omics data.…”