TheHLA-DR4Pred is an SVM and ANN based HLA-DRB1*0401(MHC class II alleles) binding peptides prediction method. The accuracy of the SVM and ANN based methods is ~86% and ~78% respectively.The performence of the methods was tested through 5 set cross-validation. The training of SVM and ANN was done by using the freely availaible SVM_LIGHT and SNNS packages respectively. The data for training of neural network and SVM model has been extracted from MHCBN database.This method will be useful in cellular immunology, Vaccine design, immunodiagnostics, immunotherapeuatics and molecular understanding of autoimmune susceptibility.
 
 
Home
Instructions Information References Developers  
 
 
 
 
 
 
 
 
 
 
 
SVM     Threshold     
 
 
ANN     Threshold     
 
Display Top      Peptides
 
 
 

    
 
 
   
 

Dr. G P S Raghava
Coordinator, Bioinformatics Centre
Institute of Microbial Technology
Sector 39A, Chandigarh, India
Phone: +91-172-690557 +91-172-690908
Fax: +91-172-690585 +91-172-690632
Email: raghava@iiitd.ac.in
 

If you use this webserver please cite: Bhasin M, Raghava GPS (2004).SVM based method for predicting HLA-DRB1 binding peptides in an antigen sequence. Bioinformatics 20(3): 421-3