| Abstract: | Predicting protein functional classes such as localization sites and modifications plays a crucial role in function annotation. Given a tremendous amount of sequence data yielded from high-throughput sequencing experiments, the need of efficient and interpretable prediction strategies has been rapidly amplified. Our previous approach for subcellular localization prediction, PSLDoc, archives high overall accuracy for Gram-negative bacteria. However, PSLDoc is computational intensive due to incorporation of homology extension in feature extraction and probabilistic latent semantic analysis in feature reduction. Besides, prediction results generated by support vector machines are accurate but generally difficult to interpret. In this work, we incorporate three new techniques to improve efficiency and interpretability. First, homology extension is performed against a compact non-redundant database using a fast search model to reduce running time. Second, correspondence analysis (CA) is incorporated as an efficient feature reduction to generate a clear visual separation of different protein classes. Finally, functional classes are predicted by a combination of accurate compact set (CS) relation and interpretable one-nearest neighbor (1-NN) algorithm. Besides localization data sets, we also apply a human protein kinase set to validate generality of our proposed method. Experiment results demonstrate that our method make accurate prediction in a more efficient and interpretable manner. First, homology extension using a fast search on a compact database can greatly accelerate traditional running time up to twenty-five times faster without sacrificing prediction performance. This suggests that computational costs of many other predictors that also incorporate homology information can be largely reduced. In addition, CA can not only efficiently identify discriminative features but also provide a clear visualization of different functional classes. Moreover, predictions based on CS achieve 100% precision. When combined with 1-NN on unpredicted targets by CS, our method attains slightly better or comparable performance compared with the state-of-the-art systems. |
