Download the SVM STANDALONE (wxPython) for MAC


Methods Used in VaxinPAD

Datasets-

The datasets were derived from patent and publication literature. We have developed two following datasets:

Main dataset-

This comprises of 305 experimentally validated immunomodulatory peptide sequences from patents as positive dataset and 385 peptides found endogenously occuring in human plasma as negative dataset. The algorithm of VaxinPAD is based on the following models:

Dipeptide Composition (DPC) based model

The dipeptide composition of the positive and negative dataset sequences was calculated and given as input to the SVMlight software to generate prediction models.

Dipeptide Composition + Motif based model

To increase the robustness of prediction, we used the hybrid model by integrating motif based and SVM based methods. If the user's query peptide has the any one of the motifs as those from our datasets, we assign peptide type to it based on motif that it contains. SVM model of prediction is used in case no motif is found.

References for the Physicochemical properties calculated for the peptides

HydrophobicityEISD840101
HydrophilicityHOPT810101
Steric HinderanceCHAM810101
Net HydrogenFAUJ880109
SolvationEISD860101
ChargeKLEP840101
HydropathyKYTJ820101
pIpI
AmphiphilicityMITS020101
WeightFASG760101