Metrics based performance control over text mining tools in bioinformatics

• Authors: Jayanthi Manicassamy;P. Dhavachelvan
• Venue: Proceedings of the International Conference on Advances in Computing, Communication and Control
• Year: 2009

Bioinformatics is a field of biology merging with few other sciences like information technology and statistics which involves in the discovery of new tools for data analysis and interpretation of accurate result. Some of the areas in which bioinformatics is applicable are in disease identification, drug discovery, DNA sequence analysis and structural analysis. There are various tools that have been developed in text mining, in the area of bioinformatics in various analysis processes like sequence analysis, functional analysis, structural analysis and similarity analysis. Performance is a key factor in utilization of existing tools or in the development of new tools which could be evaluated by means of comparison of feature or by means of evaluating metrics. Metrics based assessment is made on developed products because it qualifies the characteristics of a product like precision, recall, information retrieval. The merit that we are discovering by evaluating the existing products, leads us in the development of new products by avoiding the pitfalls of the existing products. This work describes the standard procedure for evaluating text mining tools in bioinformatics based on (1) features, functionalities and (2) performance metrics. The metrics set that have been used here are involved in the performance evaluation of text mining tools like error rate, ontological improvement are specified with detailed result analysis. The results observed during this evaluation made on the specified tools have made an indication for having a standard development cum evaluation of text mining based bioinformatics tools.