The Community for Technology Leaders
Green Image
Issue No. 05 - Sept.-Oct. (2012 vol. 9)
ISSN: 1545-5963
pp: 1432-1441
Bilge Karacali , Dept. of Electr. & Electron. Eng., Izmir Inst. of Technol., Urla Izmir, Turkey
We propose hierarchical motif vectors to represent local amino acid sequence configurations for predicting the functional attributes of amino acid sites on a global scale in a quasi-supervised learning framework. The motif vectors are constructed via wavelet decomposition on the variations of physico-chemical amino acid properties along the sequences. We then formulate a prediction scheme for the functional attributes of amino acid sites in terms of the respective motif vectors using the quasi-supervised learning algorithm that carries out predictions for all sites in consideration using only the experimentally verified sites. We have carried out comparative performance evaluation of the proposed method on the prediction of N-glycosylation of 55,184 sites possessing the consensus N-glycosylation sequon identified over 15,104 human proteins, out of which only 1,939 were experimentally verified Nglycosylation sites. In the experiments, the proposed method achieved better predictive performance than the alternative strategies from the literature. In addition, the predicted N-glycosylation sites showed good agreement with existing potential annotations, while the novel predictions belonged to proteins known to be modified by glycosylation.
proteins, biochemistry, biological techniques, molecular biophysics, human protein sequence analysis, hierarchical motif vectors, amino acid sequence configuration, functional site prediction, quasisupervised learning framework, wavelet decomposition, physicochemical amino acid properties, consensus N-glycosylation sequon, Vectors, Amino acids, Proteins, Humans, Approximation methods, Prediction algorithms, Databases, quasi-supervised learning., Functional attribute prediction, hierarchical motif vectors, protein sequence analysis
Bilge Karacali, "Hierarchical Motif Vectors for Prediction of Functional Sites in Amino Acid Sequences Using Quasi-Supervised Learning", IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 9, no. , pp. 1432-1441, Sept.-Oct. 2012, doi:10.1109/TCBB.2012.68
102 ms
(Ver 3.1 (10032016))