Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction
This work addresses gene expression prediction for genomics researchers, offering a novel approach to improve accuracy by focusing on multimodal signal integration rather than sequence length extension.
The paper tackles gene expression prediction by showing that long DNA sequences can degrade model performance, and instead identifies proximal multimodal epigenomic signals as more essential, proposing the Prism framework to integrate these signals effectively and achieve state-of-the-art results using only short sequences.
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.