期刊名称：International Journal of Computer Science and Security (IJCSS)
电子版ISSN：1985-1553
出版年度：2011
卷号：5
期号：1
页码：14-27
出版社：Computer Science Journals
摘要：Drug Discovery process include target identification i.e. to identify a target protein whose inhibition can destroy the pathogen. In testing phase, clinical and pre-clinical trials are done on the animals and then on humans. After the discovery process, the drug or medicine is made available for public use. But if the testing of the drug is ineffective or unable to yield the appropriate results, then the whole process need to be repeated. This makes the first stage of drug discovery the most important than the other stages. The present work will assist in the process of drug discovery. The present work involves the development of a model that extracts the sequence derived features from the given amino acid sequence using associative rule mining. Associative rule mining is a data mining technique useful to identify related items and to develop rules. In the present work, various parameters of the amino acid sequence are studied that affect the sequence-derived features and some of the equations and algorithms are implemented. Input is given through text file and collective results are obtained. MATLAB environment is used for the implementation. The results are compared with the previous bioinformatics tools. The model developed assists in protein class prediction process which assists drug discoverers in the drug discovery process.
