A Survey on Chemical Text Mining Techniques for Identifying Relationship Network between Drug Disease Genes and Molecules

Abstract

The Text mining plays essential roles in the field of Chemoinformatics to reveal unknown information. The enormous amount of biomedical information is available on internet and resides in the form of published articles, files, patents etc. As the rich source of data is growing massively, it is widely contributing to the scientific researchers. Text mining is the most widely used in field of Natural Language Processing. The Text Pre-processing and data analysis techniques applied on biomedical literature allows us to identify ad investigate new theories. Finding the association between the chemical entities like drug, disease, genes and molecules is the new area of focus for researchers. This paper presents the study on several approaches and techniques proposed for chemical text-mining to identify relationship network for drug-disease, disease-gene associations.In this paper, we focus on comparative analysis of various Text mining techniques used for chemical literature with their results evaluations as well as observations.