NClassG+
Several feature-based classifiers were trained using different sequence transformation vectors (frequencies, dipeptides, physicochemical factors and PSSM) and Support Vector Machines (SVMs) with Linear, Polynomial and Gaussian kernel functions. Nested k-fold cross-validation (CV) was applied to select the best models, using the inner CV loop to tune the parameters of the model and the outer CV group to compute the error. The parameters and Kernel functions and the combinations between all possible feature vectors were optimized using grid search. The final model was tested against an independent set not previously seen by the model, obtaining better predictive performance compared to the other two methods available for the identification of non-classically secreted proteins.
Classifiers
Publication
User Recommendations
A. Please be patient because our resources are limited.
B. As general data adjustment criteria, proteins had to be at least 50 amino acids long and no more than 10 000 amino acids long.
C. An interesting detail is that NClassG+ automatically recognizes proteins that were used for its training, so if one of your proteins was part of the training sets, it will be labeled as: POS SET, or NEG SET .
D. When you send a query, please be patient for the process to be completed because the webservice automatically updates the process status. Please allow for the system to display the results.
E. The training datasets are available upon request. drestrepom.at.unal.edu.co
Bogotá D.C. - Colombia
