Identification of Candidate Genes Related to Inflammatory Bowel Disease Using Minimum Redundancy Maximum Relevance, Incremental Feature Selection, and the Shortest-Path Approach

Abstract

Identification of disease genes is a hot topic in biomedicine and genomics. However, it is a challenging problem because of the complexity of diseases. Inflammatory bowel disease (IBD) is an idiopathic disease caused by a dysregulated immune response to host intestinal microflora. It has been proven to be associated with the development of intestinal malignancies. Although the specific pathological characteristics and genetic background of IBD have been partially revealed, it is still an overdetermined disease and the blueprint of all genetic variants still needs to be improved. In this study, a novel computational method was built to identify genes related to IBD. Samples from two subtypes of IBD (ulcerative colitis and Crohn's disease) and normal samples were employed. By analyzing the gene expression profiles of these samples using minimum redundancy maximum relevance and incremental feature selection, 21 genes were obtained that could effectively distinguish samples from the two subtypes of IBD and the normal samples. Then, the shortest-path approach was used to search for an additional 20 genes in a large network constructed using protein-protein interactions based on the above-mentioned 21 genes. Analyses of the 41 genes obtained indicate that they are closely associated with this disease.

Detecting ulcerative colitis from colon samples using efficient feature selection and machine learning

“…Supervised machine learning has already proved to be useful in disease diagnosis and prognosis as well as personalized medicine 13,14 . In IBD, machine learning has been used to classify IBD paediatric patients using endoscopic and histological data 15 , to distinguish UC colonic samples from control and Crohn's disease colonic samples 16 , and to discriminate between healthy subjects, UC patients, and Crohn's disease patients using transcriptional profiles of peripheral blood 17 .…”

Investigation of inflammatory bowel disease risk factors in 4 families in central China

“…Accumulating evidence suggests that genetic factors are involved in the development of IBD ( 30 ). A total of 7 mutations within 4 genes were investigated in the present study.…”

Big data in IBD: big progress for clinical practice

“…Then, using an SVM as a machine learning classifier, they identified a feature set containing 21 genes, which yield the highest prediction accuracy. Additionally, based on the concept of functional similarity among closely related proteins, the authors used the protein–protein interaction network of the proteins encoded by those 21 genes and applied the shortest path approach (typically defined as the path with the least number of links between two proteins in a network) to find an additional 20 candidate genes 41. In another interesting study by Isakov et al , novel candidate genes were identified by developing a machine learning model trained on expression values of known IBD susceptibility genes and their functional annotations.…”