Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zhao, Duan, Yi, Zhu, Jiwei, Ba, Ying, Cao, Chuan, Su, Bing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917334443098112
author Yang, Zhao
Duan, Yi
Zhu, Jiwei
Ba, Ying
Cao, Chuan
Su, Bing
author_facet Yang, Zhao
Duan, Yi
Zhu, Jiwei
Ba, Ying
Cao, Chuan
Su, Bing
contents Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of kilobases away. Our work first reveals that for current models, long sequence modeling can decrease performance. Even carefully designed algorithms only mitigate the performance degradation caused by long sequences. Instead, we find that proximal multimodal epigenomic signals near target genes prove more essential. Hence we focus on how to better integrate these signals, which has been overlooked. We find that different signal types serve distinct biological roles, with some directly marking active regulatory elements while others reflect background chromatin patterns that may introduce confounding effects. Simple concatenation may lead models to develop spurious associations with these background patterns. To address this challenge, we propose Prism, a framework that learns multiple combinations of high-dimensional epigenomic features to represent distinct background chromatin states and uses backdoor adjustment to mitigate confounding effects. Our experimental results demonstrate that proper modeling of multimodal epigenomic signals achieves state-of-the-art performance using only short sequences for gene expression prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21550
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction
Yang, Zhao
Duan, Yi
Zhu, Jiwei
Ba, Ying
Cao, Chuan
Su, Bing
Machine Learning
Genomics
Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of kilobases away. Our work first reveals that for current models, long sequence modeling can decrease performance. Even carefully designed algorithms only mitigate the performance degradation caused by long sequences. Instead, we find that proximal multimodal epigenomic signals near target genes prove more essential. Hence we focus on how to better integrate these signals, which has been overlooked. We find that different signal types serve distinct biological roles, with some directly marking active regulatory elements while others reflect background chromatin patterns that may introduce confounding effects. Simple concatenation may lead models to develop spurious associations with these background patterns. To address this challenge, we propose Prism, a framework that learns multiple combinations of high-dimensional epigenomic features to represent distinct background chromatin states and uses backdoor adjustment to mitigate confounding effects. Our experimental results demonstrate that proper modeling of multimodal epigenomic signals achieves state-of-the-art performance using only short sequences for gene expression prediction.
title Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction
topic Machine Learning
Genomics
url https://arxiv.org/abs/2602.21550