IL-13Pred: A webserver to predict and design interleukin-13 inducing peptides

Algorithm of IL-13Pred

Interlukin-13(IL-13) plays a vital role in the IgE synthesis, goblet cell hyperplasia, mucus hypersecretion, airway hyperresponsivenes, aasthma and various cancer. Best of our knowledge no method has been developed for predicting epitope or antigenic peptides that can induce IL-13. First time an attempt have been made to develop method for predicting IL-13 inducing/non-inducing epitopes.

The prediction server for IL-13 inducing epitopes has been designed in a very user-friendly manner. Here, on this page, user can get the details of all the algorithms and procedures exploited in the different modules.

Dataset Used

Positive Dataset:

It comprises of 313 experimentally validated IL-13 inducing peptides/epitopes.

Negative dataset:

It comprises of 2908 experimentally validated non-IL-13 inducing peptides/eptitopes.

This algorithm of the server is relies on the following three models:

Prediction model

The "Predict" module provides the facility to the user to classify IL-13 inducing peptides from non-inducing peptides. User can provide multiple sequences as input to the server to predict the given peptide is IL-13 inducing/non-inducing. In this study we used various machine learning techniques to develop prediction modules.

Design model

In this study, "Design" module is used to create all possible analogs/mutants of the input sequence and identify the best analog which initiate cytokine i.e. IL-13 release. Usign various machine learning techniques it can predict wheather mutants can induce IL-13 secretion.

Scan model

In this study, we incorporated two scan modules:
I) Protein Scan: Aim of this approach is to identify IL-13 inducing regions in the protein sequence, which can futher removed or altered in the potential subunit vaccine candidates.
II) BLAST Scan: “Blast Search” module is based on a similarity search method, i.e., Basic Local Alignment Search Tool (BLAST). The input query sequence is searched against the database of known IL-13 inducing peptides. A query sequence is predicted as IL-13 inducer if found match or hit in the database; otherwise, it is predicted as non-IL-13 inducer peptide.