Prediction of sub cellular localization of proteins is an important step in genome annotation and in search for achieving novel drug targets. Conducting experiments for extracting information about protein sub cellular localization is both time consuming and costly effort. Machine learning approaches, especially, ensemble of classifiers, providing efficient and reliable mechanism of computational prediction are thus highly desired. In this context, we propose a modification to the approach proposed in [K. C. Chou, J. Cell. Biol. 99(2006)517]. We have used a weighted polling method to fuse the output of individual Covariant Discriminant Classifiers. The individual classifiers are trained on features based on pseudo-amino acid composition of proteins. Three methods of verifications; re-substitution, jackknife, and independent data set tests have been employed and give over all accuracies of 87.13%, 71.15% and 74.90% respectively. The predicted accuracies are higher than that of the existing schemes.
展开▼
