Data Mining for Building Neural Protein Sequence Classification Systems with Improved Performance

• Main Authors: Wang, Dianhui, Lee, Nung Kion, Dillon, Tharam S.
• Format: Conference or Workshop Item
• Language: English
• Published: IEEE 2003
• Subjects: QA75 Electronic computers. Computer science; T Technology (General)
• Online Access: http://ir.unimas.my/id/eprint/11927/1/Data%20Mining_abstract.pdf; http://ir.unimas.my/id/eprint/11927/; http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1223671

Traditionally, two protein sequences are classified into the same class if their feature patterns have high homology. These feature patterns were originally extracted by sequence alignment algorithms, which measure similarity between an unseen protein sequence and identified protein sequences. Neural network approaches, while reasonably accurate at classification, give no information ahout the relationship between the unseen case and the classified items that is useful to biologist. In contrast, in this paper we use a generalized radial basis function (GRBF) neural network architecture 'that generates fuzzy classification rules that could he used for further knowledge discovery. Our proposed techniques were evaluated using protein sequences with ten classes of super-families downloaded from a public domain database, and the results compared favorably with other standard machine learning techniques.