BT203: MutD – A PubMed Scale Resource for Protein Mutation-Disease Relations through Bio-Medical Literature Mining

A large amount of information about the role of gene variants and mutations in diseases is available in curated databases such as OMIM, ClinVar, and UniprotKB. However, much of this information remains ‘locked’ in the unstructured form in the scientific publications. Since manual curation involves significant human effort and time there is always a lag in the information between the curated databases and the literature. The recent findings published in the literature takes significant time to find its way into the curated knowledgebase. Text mining approaches can accelerate the process of assembling this knowledge from the published literature. However, developing a text-mining system with semantic understanding capability in the biomedical domain is very challenging. In an earlier work, we described MutD, a literature mining system that extracts relationship between protein point mutation and diseases from bio-medical abstracts. In this abstract, we present access to a PubMed scale resource through a web interface that allows users to retrieve protein point mutation-disease relations extracted through biomedical literature mining.