A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Support vector machine classification on the web
Bioinformatics
Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification
Information Sciences: an International Journal
Reducing the storage requirements of 1-v-1 support vector machine multi-classifiers
RSFDGrC'05 Proceedings of the 10th international conference on Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing - Volume Part II
| Hi-index | 0.00 |
Cytokines are crucial intercellular regulators that have important physiological roles in a wide range of disease processes. The identification of new cytokines by computational methods can provide valuable clues in functional studies of uncharacterized proteins without performing extensive experiments. In this study, we developed a new prediction method for the cytokine family based on dipeptide composition and length distribution by using support vector machine (SVM). The cross-validation results demonstrated that cytokines could be correctly identified with an accuracy of 97% at family classification and 90% at subfamily recognition correctly, respectively. In comparison with existing methods in the literature, the present method displayed great competitiveness on identifying cytokines correctly.