MNESEDA: A prior-guided subgraph representation learning framework for predicting disease-related enhancers

Abstract

Enhancers, as a class of functional genomic regulatory elements, activate transcription of their target genes and play significant roles in the pathogenesis of complex human diseases. Therefore, identifying associations between enhancers and diseases could help to illuminate the potential disease pathogenesis mechanism. However, current methods for identifying disease-related enhancers mainly focus on biological experiments, which are time-consuming and cost-intensive. It is crucial to develop an effective computational model for detecting novel enhancer-disease associations (EDAs). To this end, we propose a prior-guided maximum neighbor enclosing subgraph (MNES) representation learning framework named MNESEDA, for enhancer-disease association prediction, where maximum connected motif (MCM) discovery is a key ingredient that constrains the subsequent MNES extraction strategy. The proposed residual information fusion captures representation difference between motif subgraphs and alleviates the over-smoothing issue. Extensive experiments conducted on three datasets demonstrate the superior performance of MNESEDA over recent state-of-the-art methods and the satisfactory generalization and transfer ability. Further case studies exhibit the potential ability of MNESEDA to predict novel disease-related enhancers. Overall, MNESEDA could serve as an effective guide to elucidate pathogenesis and etiology of human diseases and decipher potential disease biomarkers.