TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic data

Abstract It is challenging to identify regulatory transcriptional regulators (TRs), which control gene expression via regulatory elements and epigenomic signals, in context-specific studies on the onset and progression of diseases. The use of large-scale multi-omics epigenomic data enables the repre...

Full description

Saved in:
Bibliographic Details
Main Authors: Guorui Zhang, Chao Song, Mingxue Yin, Liyuan Liu, Yuexin Zhang, Ye Li, Jianing Zhang, Maozu Guo, Chunquan Li
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-58921-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850145097877815296
author Guorui Zhang
Chao Song
Mingxue Yin
Liyuan Liu
Yuexin Zhang
Ye Li
Jianing Zhang
Maozu Guo
Chunquan Li
author_facet Guorui Zhang
Chao Song
Mingxue Yin
Liyuan Liu
Yuexin Zhang
Ye Li
Jianing Zhang
Maozu Guo
Chunquan Li
author_sort Guorui Zhang
collection DOAJ
description Abstract It is challenging to identify regulatory transcriptional regulators (TRs), which control gene expression via regulatory elements and epigenomic signals, in context-specific studies on the onset and progression of diseases. The use of large-scale multi-omics epigenomic data enables the representation of the complex epigenomic patterns of control of the regulatory elements and the regulators. Herein, we propose Transcription Regulator Activity Prediction Tool (TRAPT), a multi-modality deep learning framework, which infers regulator activity by learning and integrating the regulatory potentials of target gene cis-regulatory elements and genome-wide binding sites. The results of experiments on 570 TR-related datasets show that TRAPT outperformed state-of-the-art methods in predicting the TRs, especially in terms of forecasting transcription co-factors and chromatin regulators. Moreover, we successfully identify key TRs associated with diseases, genetic variations, cell-fate decisions, and tissues. Our method provides an innovative perspective on identifying TRs by using epigenomic data.
format Article
id doaj-art-329c6483725d4d868b44049deee435b2
institution OA Journals
issn 2041-1723
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-329c6483725d4d868b44049deee435b22025-08-20T02:28:10ZengNature PortfolioNature Communications2041-17232025-04-0116112010.1038/s41467-025-58921-0TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic dataGuorui Zhang0Chao Song1Mingxue Yin2Liyuan Liu3Yuexin Zhang4Ye Li5Jianing Zhang6Maozu Guo7Chunquan Li8The First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaThe First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaThe First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaThe First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaThe First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaThe First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaThe First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaSchool of Intelligence Science and Technology, Beijing University of Civil Engineering and ArchitectureThe First Affiliated Hospital & National Health Commission Key Laboratory of Birth Defect Research and Prevention, Hengyang Medical School, University of South ChinaAbstract It is challenging to identify regulatory transcriptional regulators (TRs), which control gene expression via regulatory elements and epigenomic signals, in context-specific studies on the onset and progression of diseases. The use of large-scale multi-omics epigenomic data enables the representation of the complex epigenomic patterns of control of the regulatory elements and the regulators. Herein, we propose Transcription Regulator Activity Prediction Tool (TRAPT), a multi-modality deep learning framework, which infers regulator activity by learning and integrating the regulatory potentials of target gene cis-regulatory elements and genome-wide binding sites. The results of experiments on 570 TR-related datasets show that TRAPT outperformed state-of-the-art methods in predicting the TRs, especially in terms of forecasting transcription co-factors and chromatin regulators. Moreover, we successfully identify key TRs associated with diseases, genetic variations, cell-fate decisions, and tissues. Our method provides an innovative perspective on identifying TRs by using epigenomic data.https://doi.org/10.1038/s41467-025-58921-0
spellingShingle Guorui Zhang
Chao Song
Mingxue Yin
Liyuan Liu
Yuexin Zhang
Ye Li
Jianing Zhang
Maozu Guo
Chunquan Li
TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic data
Nature Communications
title TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic data
title_full TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic data
title_fullStr TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic data
title_full_unstemmed TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic data
title_short TRAPT: a multi-stage fused deep learning framework for predicting transcriptional regulators based on large-scale epigenomic data
title_sort trapt a multi stage fused deep learning framework for predicting transcriptional regulators based on large scale epigenomic data
url https://doi.org/10.1038/s41467-025-58921-0
work_keys_str_mv AT guoruizhang traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT chaosong traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT mingxueyin traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT liyuanliu traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT yuexinzhang traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT yeli traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT jianingzhang traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT maozuguo traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata
AT chunquanli traptamultistagefuseddeeplearningframeworkforpredictingtranscriptionalregulatorsbasedonlargescaleepigenomicdata