A webserver to predict HLA-DRB1*0401 binders

HLA-DR4Pred 2.0 is the update of the older version HLA-DR4Pred, which was a SVM and ANN based method to predict the HLA-DRB1*04:01 bindind peptides. In the updated version, the models were trained on a dataset comprising of 12676 HLA-DRB1*04:01 binders and 86300 non-binders. The performance of the models were evaluated using 5-fold cross-validation. The models were trained on dipeptide composition as well as on hybrid features(dipeptide composition + BLAST-search) by implementing extra-tree classifiers from the scikit library of python. The datasets were extracted from Immune Epitope Database (IEDB). This method will be highly useful in the fields of cellular immunology, immunodiagnostics, immunotherapeutics, and will aid in molecular understanding of autoimmune susceptibility.


This tool allow the user to predict whether the peptide is a binder of HLA-DRB1*04:01 or not from their amino acid sequence. The module allow users to make the prediction based on either Dipeptide composition (DPC) or hybrid of DPC and BLAST.


This module facilitates the user to scan the larger sequence(s) in order to find the HLA-DRB1*04:01 binders by generating the patterns of the desired length (9-22) from the submitted sequence(s). The prediction for each sub-sequence will be made on chosen model.


This tool generates all the possible mutant of the submitted sequence and predict whether the mutated peptide is a binder of HLA-DRB1*04:01 or not. The prediction for each mutated peptide will be made on chosen model.


This module hit the submitted sequences against the custom database generated using HLADR4Pred 2.0 datasets. The sequence will be assigned as binder if the hit will be foud against positive else non-binder. Users can set e-value.


This module facilitates the user to scan for the HLA-DRB1*04:01 motifs in the submitted sequences. MERCI tool is used to locate the motifs in the sequences. If the motif is found in the sequence, the sequence will be assigned as HLA-DRB1*04:01 binder.


This module provides the standalone version of this method which user can use in the absence of internet or can run larger number of sequences at a time. The perl-based, python-based standalone, and GitHub will be available on this page.

Scroll to Top