期刊名称:International Journal of Computer Trends and Technology
电子版ISSN:2231-2803
出版年度:2016
卷号:40
期号:2
页码:78-83
DOI:10.14445/22312803/IJCTT-V40P114
出版社:Seventh Sense Research Group
摘要:In this paper, a method is presented for classifying snake toxins into neurotoxins, cytotoxins or cardiotoxins, using a fourstage neural network. A training phase was used to teach the network to recognize the type of toxin based on the number of amino acid residues between the disulphide bridges, on a sample set of 139 snake toxins. When the trained network was used to classify a set of 239 toxins, the system achieved an accuracy of 74%.