Biocomb: Feature Selection and Classification with the Embedded Validation Procedures for Biomedical Data Analysis
Contains functions for the data analysis with the emphasis on biological data, including several algorithms for feature ranking, feature selection, classification algorithms with the embedded validation procedures. The functions can deal with numerical as well as with nominal features. Includes also the functions for calculation of feature AUC (Area Under the ROC Curve) and HUM (hypervolume under manifold) values and construction 2D- and 3D- ROC curves. Biocomb provides the calculation of Area Above the RCC (AAC) values and construction of Relative Cost Curves (RCC) to estimate the classifier performance under unequal misclassification costs problem. Biocomb has the special function to deal with missing values, including different imputing schemes.