International Conference on Biocomputation, Bioinformatics, and Biomedical Technologies (2008)
June 29, 2008 to July 5, 2008
The discriminative framework for protein remote homology detection based on support vector machines (SVMs) is reconstructed by the fusion of sequence based features. In this respect, n-peptide compositions are partitioned and fed into separate SVMs. The SVM outputs are evaluated with different techniques and tested to discern their ability for SCOP protein super family classification on a common benchmarking set. It reveals that the fusion approach leads to an improvement in prediction accuracy with a remarkable gain on computer memory usage.
protein homology detection, n-peptite compositions, support vector machines, data fusion
Hayri Sever, Aydin Can Polatkan, Hasan Ogul, "A Data Fusion Approach in Protein Homology Detection", International Conference on Biocomputation, Bioinformatics, and Biomedical Technologies, vol. 00, no. , pp. 7-12, 2008, doi:10.1109/BIOTECHNO.2008.23