Network Embedding for Peripheral Weak Genetic Effects of Complex Diseases

Complex diseases are determined by many genetic and environmental factors. The Omnigenic model provides a new conceptual model for exploring the pathogenic mechanism of complex diseases. The model points out that the weak genetic effects of a large number of peripheral genes are superimposed on the core genes, thus contributing most of the heritability to complex diseases. At present, many studies have explored and verified the important role of peripheral genes. However, few studies have focused on the impact of peripheral genes on the regulation of core genes in complex diseases. Therefore, we proposed an embedding tool called PToC to characterize the impact of the weak genetic effects of peripheral genes on the core genes of the disease, and represent the impact into weak effect vectors from the two aspects of network topological structure and biological functional. In the case study on schizophrenia, we curated core and peripheral genes. First, we extracted weak effect vectors using PToC, and applied them to identify peripheral genes, achieved an average AUC 17.90% higher than other network embedding methods. Additionally, we constructed a sample classifier based on weak effect vectors. Experimental results show that the average AUC value of this method in distinguishing different sample types is 0.91, which is better than existing methods. Thus, PToC offers a novel perspective and tool for analyzing the weak effects of peripheral genes, enhancing disease diagnosis and treatment.