LAUSR

AIMS We propose a unified computational framework, PheGe-Net, to bridge phenotypes and genotypes. BACKGROUND Genotype is the genetic makeup of a cell, an organism, or an individual, usually regarding a specific characteristic under consideration. Phenotype can be regarded as the macroscopic description of an organism, while genotype is its microscopic expression. OBJECTIVE Identifying phenotype-genotype associations is the primary step in explaining the pathogenesis of complex human diseases. It is also of key importance for the development of genomic medicine, sometimes known as personalized medicine, which is a way to customize medical care to an individual's unique genetic makeup. METHODS PheGe-Net utilizes a phenotype similarity network, a genotype similarity network, and known phenotype-genotype associations to explore the potential associations among other unlinked phenotypes and genotypes. As by-products, PheGe-Net can also discover the phenotype and genotype groups, such that the phenotypes or genotypes within the same group are highly correlated with each other. RESULTS We validate the effectiveness of PheGe-Net on a real-world data set; our method outperformed the second-best one by around 3% on Accuracy and NMI when clustering the phenotype/genotype; it also successfully detected phenotype-genotype associations, for example, the association for obesity (OMIM id: 601665) was analyzed, and among the top ten scored genes, two known ones were assigned with scores more than 0.75, and other eight predicted ones are also explainable. CONCLUSION Our method can reveal potential phenotype clusters and genotype clusters and their unknown associations through a variety of phenotype similarities, genotype similarities, and known phenotype-genotype associations.