GTPBinder: is a support Vectors Machine (SVM) based prediction method of GTP-interacting resiudes in a protein.The PSSM profile for each sequence was generated by PSI-BLAST search against non-redundant database of SWISS-PROT with three iterations, at cut-off 0.001.

To submit a protein sequence for prediction, following steps have to be followed:
Input sequence:

There are two ways of sequence submission. Either directly paste into the text-box or upload the text file using 'BROWSE' option. Before uploading please ensure that the sequence must be in FASTA format and single-letter code of amino acid representation.

There are two approaches of prediction on the basis of input vector used to train SVM: Binary pattern and PSSM profile.

The probability of correct prediction directly depends on the threshold. For prediction with high confidence (less probability of false positive prediction) high threshold should be choosen. At low threshold, the probability of false negative prediction is very low. On default theshold (0.0) the rate of false negative and false positive prediction was nearly equal during training of SVM model.

Output of GTPBinder is given in tabular format. This table contain three columns
(i) Amino acid residues,
(ii) SVM score
(iii) Prediction class.

© Raghava's group, 2009.Department of Computational Biology .