{"title":"通过因果关系感知Graph-Transformer深度学习解码压力特定转录调节","authors":"Umesh Bhati , Akanksha Sharma , Sagar Gupta , Anchit Kumar , Upendra Kumar Pradhan , Ravi Shankar","doi":"10.1016/j.cpb.2025.100521","DOIUrl":null,"url":null,"abstract":"<div><div>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 <em>Arabidopsis</em>. 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 <span><span>https://hichicob.ihbt.res.in/ctfbind/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":38090,"journal":{"name":"Current Plant Biology","volume":"43 ","pages":"Article 100521"},"PeriodicalIF":4.5000,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Decoding stress specific transcriptional regulation by causality aware Graph-Transformer deep learning\",\"authors\":\"Umesh Bhati , Akanksha Sharma , Sagar Gupta , Anchit Kumar , Upendra Kumar Pradhan , Ravi Shankar\",\"doi\":\"10.1016/j.cpb.2025.100521\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>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 <em>Arabidopsis</em>. 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 <span><span>https://hichicob.ihbt.res.in/ctfbind/</span><svg><path></path></svg></span>.</div></div>\",\"PeriodicalId\":38090,\"journal\":{\"name\":\"Current Plant Biology\",\"volume\":\"43 \",\"pages\":\"Article 100521\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2025-08-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Current Plant Biology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2214662825000891\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PLANT SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current Plant Biology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214662825000891","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PLANT SCIENCES","Score":null,"Total":0}
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 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/.
期刊介绍:
Current Plant Biology aims to acknowledge and encourage interdisciplinary research in fundamental plant sciences with scope to address crop improvement, biodiversity, nutrition and human health. It publishes review articles, original research papers, method papers and short articles in plant research fields, such as systems biology, cell biology, genetics, epigenetics, mathematical modeling, signal transduction, plant-microbe interactions, synthetic biology, developmental biology, biochemistry, molecular biology, physiology, biotechnologies, bioinformatics and plant genomic resources.