Open AccessImproved Disease Gene Predication Method
Author(s) -
Gerui He,
Zhiming Liu,
Lingyun Luo,
Yaping Wan
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/719/1/012024
Subject(s) - disease , gene , gene ontology , gene annotation , computational biology , function (biology) , aggregate (composite) , biological data , computer science , biology , bioinformatics , genetics , gene expression , genome , medicine , materials science , pathology , composite material
The prediction of disease genes has always been a hot topic in the field of bioinformatics. Machine learning methods can effectively dig out the hidden relationship between disease-causing genes and predict disease genes. At present, the prediction algorithm of Gene Ontology (GO) combined with GO annotation has limitations. It is believed that disease genes will only accumulate on the biological process branches of GO, ignoring the cellular components and molecular function branches. Disease gene prediction is performed by considering data from three branches of biological processes, cell components, and molecular functions. Multiple sets of experiments were performed. The data showed that the use of three branches to predict disease genes increased the accuracy from 78% to 91%, indicating that the disease genes not only aggregate on the branches of biological processes but also aggregate on molecular functions and cellular components.