A FRAME WORK FOR IDENTIFICATION OF RELATIONSHIP BETWEEN GENE AND DISEASE CAUSING MUTATION USING BIOLOGICAL TEXT MINING

• Main Authors: Krishna, A.Murali, Jyothi, Dr. S.
• Format: Article in Journal/Newspaper
• Language: English
• Published: International Journal of Innovative Technology and Research 2017
• Subjects: CSE; Mutation;Extraction;NLP;Text Mining;Pubmed;Gene; DML
• Online Access: http://www.ijitr.com/index.php/ojs/article/view/1547

We have gone through various papers describing the mutations in between them and associated disease in a rapid pace. The articles of previous studies show that there is a need to acquire knowledge of gene mutation causing diseases and its association. The need cannot be solved manually, but it has to be automated, so our study is based to develop a framework which gathers information of disease association mutation for knowledge sharing to doctors and researchers. Our work is done using texting mining for extraction of disease causing mutation and its associated NLP from previous abstracts. Our proposed system extracts mutation causing gene using NLP.DMLtool consists of modules of NLP that process text input using semantic and synaptic patterns to gain disease mutation. DML developed gives recall and precision high with F-score 0.87 , 0.89 and 0.91, which were evaluated on 3 various datasets related to associated disease mutations. In DML we used a special module which extracts mentioned mutation and its gene text associated with it. Various types of datasets have been evaluated on our framework and its performance has been check with performance metric.The obtained results shows better performance compared to the existing on association of disease-mutation and also solves problems of low precision and their approaches.LMA is applied to large data sets of different type of abstracts in Pubmed, it extracts associated disease-mutations and its related information of patients, population of data and its type size. The gained result from our work is stored in a database, which can be acquired by query processing. In our work we conclude that using text mining method, we can increase high throughput, this gives potential to the research and also assist the research in identifying mutation causing disease and it’s associated with.