Speos: an ensemble graph representation learning framework to predict core gene candidates for complex diseases

Abstract

Understanding phenotype-to-genotype relationships is a grand challenge of 21st century biology with translational implications. The recently proposed “omnigenic” model postulates that effects of genetic variation on traits are mediated by core-genes and -proteins whose activities mechanistically influence the phenotype, whereas peripheral genes encode a regulatory network that indirectly affects phenotypes via core gene products. Here, we develop a positive-unlabeled graph representation-learning ensemble-approach based on a nested cross-validation to predict core-like genes for diverse diseases using Mendelian disorder genes for training. Employing mouse knockout phenotypes for external validations, we demonstrate that core-like genes display several key properties of core genes: Mouse knockouts of genes corresponding to our most confident predictions give rise to relevant mouse phenotypes at rates on par with the Mendelian disorder genes, and all candidates exhibit core gene properties like transcriptional deregulation in disease and loss-of-function intolerance. Moreover, as predicted for core genes, our candidates are enriched for drug targets and druggable proteins. In contrast to Mendelian disorder genes the new core-like genes are enriched for druggable yet untargeted gene products, which are therefore attractive targets for drug development. Interpretation of the underlying deep learning model suggests plausible explanations for our core gene predictions in form of molecular mechanisms and physical interactions. Our results demonstrate the potential of graph representation learning for the interpretation of biological complexity and pave the way for studying core gene properties and future drug development.

PheSeq, a Bayesian deep learning model to enhance and interpret the gene-disease association studies

“…When processing network that contains a specific gene, we locate the gene within the STRING network and then apply a graph embedding method. The proposed pipeline provides a diverse range of options for embedding computation, including node2vec [ 48 ], Mashup [ 49 ], BioPlex 3.0 [ 50 , 51 ], HuRI, and drug-target network [ 50 , 52 ], and struct2vec [ 53 ]. In the case studies, we primarily adhere to Yue’s guideline [ 54 ] and employ struct2vec to compute the graph embedding.…”

Co-expression in tissue-specific gene networks links genes in cancer-susceptibility loci to known somatic driver genes

“…Another possibility is that the genes affected by common variants are ‘peripheral’ genes which regulate a set of ‘core’ genes that mediate the cancer risk as suggested by the omnigenic model [ 17 ]. In previous work, Ratajczak et al observed the omnigenic model to hold for the effect of common germline variants associated with a trait in ‘peripheral’ genes converging on ‘core’ genes that influence the given trait [ 18 ]. In line with this model, we hypothesised that some somatic cancer drivers may be regulated by the peripheral genes derived from cancer risk loci identified through GWAS.…”