PROtein reSidue Annotation Toolkit. ProSAT toolkit is a set of programs that allow building SVM based models for annotating amino acid residues in protein sequences using user supplied features (like PSI-BLAST profiles, or PSIPred profiles). In particular, the toolkit builds features using a window around the residue, and is equipped with a specialized kernel function (normalized second order exponential kernel function nsoe ) along with the standard svm kernel function.

ProSAT_Learn is the program to learn "n" one-versus-rest classification models, where n are the possible number of annotations. It can also learn a support vector regression model to predict a floating point value.

ProSAT_Predict is the program to predict the annotation for each residue from the built models, and output a L x n dimension profile, outputting the score from each of the n one-versus-rest SVM models for each amino acid residue and L is the length of the protein sequence. In case of a regression model, n =1

ProSAT_Eval is the program to evaluate the various parameters like kernel, window lengths, and regularization parameters. ProSAT_Eval automatically performs cross validation and reports the standard classification and regression performance. Please use the perl script cv_script.pl to automatically perform model selection and training the best classification or regression model for the problem.

The license of this software is Freeware, you can free download and free use this calculator software.