Using the Chou’s Pseudo Component to Predict the ncRNA Locations Based on the Improved K-Nearest Neighbor (iKNN) Classifier

Background: The non-coding RNA identification at the organelle genome level is a challenging task. In our previous work, an ncRNA dataset with less than 80% sequence identity was built, and a method incorporating an increment of diversity combining with support vector machine method was proposed. Objective: Based on the ncRNA_361 dataset, a novel decision-making method-an improved KNN (iKNN) classifier was proposed. Methods: In this paper, based on the iKNN algorithm, the physicochemical features of nucleotides, the degeneracy of genetic codons, and topological secondary structure were selected to represent the effective ncRNA characters. Then, the incremental feature selection method was utilized to optimize the feature set. Results: The results of iKNN indicated that the decision-making method of mean value is distinctly superior to the traditional decision-making method of majority vote the Increment of Diversity Combining Support Vector Machine (ID-SVM). The iKNN algorithm achieved an overall accuracy of 97.368% in the jackknife test, when k=3. Conclusion: It should be noted that the triplets of the structure-sequence mode under reading frames not only contains the entire sequence information but also reflects whether the base was paired or not, and the secondary structural topological parameters further describe the ncRNA secondary structure on the spatial level. The ncRNA dataset and the iKNN classifier are freely available at http://202.207.14.87:8032/fuwu/iKNN/index.asp.

Predicting Protein Subcellular Localization Using the Algorithm of Increment of Diversity Combined with Weighted K-Nearest Neighbor

Protein subcellular localization is an important research field of bioinformatics. In this paper, we use the algorithm of the increment of diversity combined with weighted K nearest neighbor to predict protein in SNL6 which has six subcelluar localizations and SNL9 which has nine subcelluar localizations. We use the increment of diversity to extract diversity finite coefficient as new features of proteins. And the basic classifier is weighted K-nearest neighbor. The prediction ability was evaluated by 5-jackknife cross-validation. Its predicted result is 83.3% for SNL6 and 87.6 % for SNL9. By comparing its results with other methods, it indicates the new approach is feasible and effective.

Predicting Protein Subcellular Localization Using the Algorithm of Diversity Finite Coefficient Combined with Artificial Neural Network

Protein subcellular localization is an important research field of bioinformatics. The subcellular localization of proteins classification problem is transformed into several two classification problems with error-correcting output codes. In this paper, we use the algorithm of the increment of diversity combined with artificial neural network to predict protein in SNL6 which has six subcelluar localizations. The prediction ability was evaluated by 5-jackknife cross-validation. Its predicted result is 81.3%. By com-paring its results with other methods, it indicates the new approach is feasible and effective.