Machine-Learning Analysis of mRNA: An Application to Inflammatory Bowel Disease

Abstract

Inflammatory Bowel Disease (IBD), that includes Crohn's disease (CD) and Ulcerative Colitis (UC), is a global health concern due to the increasing number of cases. Diagnosing IBD is a challenging task due to a considerable number of clinical factors. Delayed or inaccurate IBD diagnosis can worsen the disease and complicate achieving remission, therefore, early diagnosis and prompt treatment are crucial. In this study, we adapted a methodology to analyze 16s rRNA (18,758 features) to analyze mRNA (54,675 features) that consists of three phases: 1) preprocessing, 2) feature selection, and 3) testing. We applied this methodology for analyzing mRNA datasets from the Gene Expression Omnibus (GEO) repository, aiming to discover possible biomarkers for IBD diagnosis. We experimented with three datasets, using one dataset for feature (gene) selection and we tested the results in the other two. We compared results with those obtained from other feature selection methods, such as the F-score-based K-Best and random selection. The Area Under the Curve (AUC) was used to measure the diagnostic accuracy and as a metric to compare results between the methodology and other feature selection methods. The Matthews Correlation Coefficient (MCC) was used as an additional metric to evaluate the performance of the methodology and for comparison with other feature selection methods.