Decoding stress specific transcriptional regulation by causality aware Graph-Transformer deep learning

Cells respond to environmental stimuli through transcriptional reprogramming orchestrated by transcription factors (TFs) which interpret cis-regulatory DNA sequences to determine the timing and locations of gene expression. The diversification of TFs and their interactions with cis-regulatory elemen...

Full description

Saved in:
Bibliographic Details
Main Authors: Umesh Bhati, Akanksha Sharma, Sagar Gupta, Anchit Kumar, Upendra Kumar Pradhan, Ravi Shankar
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Current Plant Biology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214662825000891
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cells respond to environmental stimuli through transcriptional reprogramming orchestrated by transcription factors (TFs) which interpret cis-regulatory DNA sequences to determine the timing and locations of gene expression. The diversification of TFs and their interactions with cis-regulatory elements (CREs) underpins plant adaptation to stress through the formation of gene regulatory networks (GRNs). However, deciphering condition-specific GRNs through selective TF bindings for spatio-temporal gene expression remains major challenge in plant biology. To decipher that the present study brings forward a novel computational framework designed to reason about the spatio-temporal dynamics of TF interaction. Leveraging over ∼23TB of multi-omics data (ChIP-seq, RNA-seq, and protein-protein interaction), a system of Bayesian causal networks was raised. It is capable of explaining TF’s conditional bindings across diverse conditions for Arabidopsis. These networks, validated against extensive experimental data, became input to a Graph Transformer deep learning system. Models were developed for 110 abiotic stress-related TFs, enabling accurate condition-specific detection of TF binding directly from RNA-seq data, bypassing the need for separate ChIP-seq experiments. The approach, CTF-BIND achieved a high average accuracy of ∼93 % when tested against a large volume of experimentally established data from various conditions. It is implemented as an interactive, open-access web server and database which captures dynamic shifts in regulatory pathways. CTF-BIND revolutionizes TF condition-specific binding identification with deep-learning, offering a cost-effective alternative to ChIP-seq. It is expected to accelerate the research towards crop improvement strategies. CTF-BIND is freely available as a web server at https://hichicob.ihbt.res.in/ctfbind/.
ISSN:2214-6628