Genome-wide cis-decoding for expression designing in tomato using cistrome data and explainable deep learning
In the evolutionary paths of plants, variations of the cis-regulatory elements (CREs) resulting in expression diversification have played a central role in driving the establishment of lineage-specific traits. However, it is difficult to predict expression behaviors from the CRE patterns to properly harness them, mainly because the biological processes are complex. In this study, we used cistrome datasets and explainable convolutional neural network (CNN) frameworks to predict genome-wide expression patterns in tomato fruits from the DNA sequences in gene regulatory regions. By fixing the effects of trans-elements using single cell-type spatiotemporal transcriptome data for the response variables, we developed a prediction model of a key expression pattern for the initiation of tomato fruit ripening. Feature visualization of the CNNs identified nucleotide residues critical to the objective expression pattern in each gene and their effects, were validated experimentally in ripening tomato fruits. This cis-decoding framework will not only contribute to understanding the regulatory networks derived from CREs and transcription factor interactions, but also provide a flexible way of designing alleles with optimized expression.