DeepGEP: Deep learning for gene expression prediction from multi-omics in mammals

Jiali Cai; Ruiqing Wang; Yipeng Li; Wentao Gong; Xiangchun Pan; Bin Ma; Penghao Wang; Xiaolong Yuan

doi:10.1016/j.ygeno.2026.111285

Back

DeepGEP: Deep learning for gene expression prediction from multi-omics in mammals

Journal article

Open access

Peer reviewed

DeepGEP: Deep learning for gene expression prediction from multi-omics in mammals

Jiali Cai, Ruiqing Wang, Yipeng Li, Wentao Gong, Xiangchun Pan, Bin Ma, Penghao Wang and Xiaolong Yuan

Genomics (San Diego, Calif.), Vol.118, 111285

2026

DOI: https://doi.org/10.1016/j.ygeno.2026.111285

PMID: 42331263

Files and links (1)

pdf

Published4.23 MBDownload View

Open Access CC BY-NC-ND V4.0

Abstract

Deep learning

Gene expression prediction

Multi-omics integration

Mammals

Deep neural networks offer great potential for integrating multi-omics data to predict gene expression and uncover regulatory mechanisms. Here, we developed DeepGEP, an attention-based Long Short-Term Memory model trained on 228 datasets, including RNA-seq, ATAC-seq, and ChIP-seq of four histone modifications (H3K4me3, H3K4me1, H3K27ac, H3K27me3) from humans, pigs, and cattle. DeepGEP outperformed several other machine learning methods, achieving Pearson correlation coefficients (PCC) of 0.70-0.82, with accuracy improving up to 0.93 after K-means clustering. Attention weight analysis highlighted regulatory regions within ±1000 bp of transcription start sites and revealed that H3K4me3 and chromatin accessibility contributed most strongly to gene expression prediction, while H3K4me1, H3K27ac, and H3K27me3 played less prominent roles. Our study demonstrates the value of integrating chromatin accessibility and histone modifications for accurate cross-species gene expression prediction, providing a versatile framework for multi-omics modeling and advancing understanding of mammalian gene regulation.

Details

Title: DeepGEP: Deep learning for gene expression prediction from multi-omics in mammals
Authors/Creators: Jiali Cai - South China Agricultural University
Ruiqing Wang - South China Agricultural University
Yipeng Li - South China Agricultural University
Wentao Gong - South China Agricultural University
Xiangchun Pan - South China Agricultural University
Bin Ma - Murdoch University
Penghao Wang - Murdoch University
Xiaolong Yuan - South China Agricultural University
Publication Details: Genomics (San Diego, Calif.), Vol.118, 111285
Publisher: Elsevier Inc.
Identifiers: 991005896084107891
Murdoch Affiliation: School of Medical, Molecular and Forensic Sciences
Language: English
Resource Type: Journal article

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: SDGs in the Output

Metrics

1 Record Views