Indexing important drugs from medical literature

Riad Alharbey, Jong In Kim, Ali Daud, Min Song, Abdulrahman A. Alshdadi, Malik Khizar Hayat

Abstract: Health maintenance is one of the foremost pillars of human society which needs up-to-date solutions to medical problems. The advancement in the biomedical field has intensified the—information load that exists in the form of clinic reports, research papers, or lab tests, etc. Extracting meaningful insights from this corpus is equally important as its progress—to make it valuable for recent medicine. In terms of biomedical text mining, the areas explored include protein–protein interactions, entity-relationship detection, and so on. The biomedical effects of drugs have significance when administered to a living organism. Biomedical literature is not widely explored in terms of gene-drug relations, hence needs investigation. Indexing methods can be used for ranking gene-drug relations. In scientific literature, Hirsch’s the h-index is usually used to quantify the impact of an individual author. Likewise, in this research, we propose the Drug-Index, a quantifiable measure that can be used to detect gene-drug relations. It is useful in drug discovery, diagnosing, personalized treatment using suitable drugs for relevant genes. For a strong and reliable gene-drug relationship discovery, drugs are extracted from a subset of MEDLINE—a bibliographic medical database. The detected drugs are verified from the PharmacoGenomics KnowledgeBase (PharmGKB)—a publicly available medical knowledgebase by Stanford University.