Indian Journal of Science and Technology

Abstract

Objective: The measure of biomedical literature has been expanding quickly in the most recent decade. Text mining systems can analysis this vast scale information, shed light onto complex medication instruments and concentrate connection data that can bolster computational polypharmacology. The key idea of the paper is to find the drug candidate for the disease cholera, which is caused due to the organism Vibrio cholerae. Method: The technique estimates the Pointwise Mutual Information (PMI) among protein name obtained from the UniprotKB and the Medical Subject Headings that contain drug terms. Based on the PMI scores, gene/protein profiles and drug are produced and candidate drug-gene/protein associations are constructed when evaluating the relevancy of their profiles. Findings: The association between protein and drug is found and the drug candidates are proposed. Applications: The similar technique can be applied to find the drug candidate for various diseases which reduces the drug release cost in the market
Keywords: Association, Corpus, MEDLINEDatabase, MESH, Ontology, Text Mining