Generalising sequence models for epigenome predictions with tissue and assay embeddings

TL;DR

This paper introduces a novel method that incorporates tissue and assay embeddings into sequence models for epigenome prediction, significantly improving inference across diverse experimental conditions and providing new insights into genetic variant effects.

Contribution

It presents a new approach that integrates contextual tissue and assay information into sequence models, surpassing previous methods in accuracy and robustness.

Findings

Achieves strong correlation across various tissue and assay pairs.

Outperforms previous models in multiple epigenetic prediction tasks.

Provides first insights into genetic variants' impact on epigenetic models.

Abstract

Sequence modelling approaches for epigenetic profile prediction have recently expanded in terms of sequence length, model size, and profile diversity. However, current models cannot infer on many experimentally feasible tissue and assay pairs due to poor usage of contextual information, limiting $\textit{in silico}$ understanding of regulatory genomics. We demonstrate that strong correlation can be achieved across a large range of experimental conditions by integrating tissue and assay embeddings into a Contextualised Genomic Network (CGN). In contrast to previous approaches, we enhance long-range sequence embeddings with contextual information in the input space, rather than expanding the output space. We exhibit the efficacy of our approach across a broad set of epigenetic profiles and provide the first insights into the effect of genetic variants on epigenetic sequence model training. Our general approach to context integration exceeds state of the art in multiple settings while employing a more rigorous validation procedure.