HOPPred

Welcome to HOPPred
A webserver to predict peptide hormones

Peptide hormones are genome-encoded signalling molecules that play vital roles in regulating almost all essential biological processes. Their therapeutic consequences have been proven in “replacement therapies” and insulin was the first among the successful peptide drugs. It utilizes a wide range of information and techniques for the prediction that includes machine learning techniques, BLAST, MERCI and peptide hormone mapping.

Predict

This tool allow the user to predict whether the peptide is a peptide hormone 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.

Design

This module facilitates the user to scan the sequence(s) in order to find the peptide hormones 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.

BLAST

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

Motif-Search

This module facilitates the user to scan for the peptide hormones motifs in the submitted sequences. MERCI tool is used to locate the motifs in the sequences. If the motif is found in the sequence, it will be assigned as peptide hormone.

Reference: Kaur D, Arora A, Vigneshwar P, Raghava GPS (2024) Prediction of peptide hormones using an ensemble of machine learning and similarity-based methods. Proteomics, e2400004..

Raghava's group      

Scroll to Top