Text mining for interpreting gene

Abstract

Text mining provides methods to retrieve and extract information contained in free-text automatically. The advances in molecular biology techniques have given rise to high throughput biology that produces tremendous data and related publications in the past decades. Here the efficient constituents of Co-reference resolution incorporating Natural Language Processing (NLP) to interpret Gene expression are focused. It may overcome the challenges and limitations of text mining in biological data for resolving unsolved problems and this paper describes a new phase of text mining process to uncover interesting term correlations, genomic term identification in curation process , identification of biological relations and help the biologists in their analysis of complex problems. The new phase of text mining process is organized in four tasks of namely use NLP, find correlated terms, Co-reference resolution and built a structured database. © 2011 Springer-Verlag Berlin Heidelberg.