AlgPred 2.0: An improved method for predicting allergenic proteins and mapping of IgE epitopes

Title:
AlgPred 2.0 Dataset – Experimentally validated allergenic and non‑allergenic proteins with IgE epitopes

Description:

Project: AlgPred 2.0 – An improved method for predicting allergenic proteins and mapping of IgE epitopes

Publication: Sharma, N., Patiyal, S., Dhall, A., Pande, A., Arora, C., & Raghava, G.P.S. (2021). AlgPred 2.0: an improved method for predicting allergenic proteins and mapping of IgE epitopes. Briefings in Bioinformatics, 22(5), bbaa294. https://doi.org/10.1093/bib/bbaa294

Overview: This dataset accompanies AlgPred 2.0, an updated version of AlgPred (2006) for predicting allergenic proteins and mapping IgE epitopes. The dataset is the largest compiled for allergen prediction, with stringent redundancy reduction (no two proteins >40% similar across train/validation sets). IgE epitopes (10,451) are provided for epitope mapping.

Content:

Key Findings – Compositional Analysis:

• Allergens enriched in: C, G, R, S

• Non‑allergens enriched in: A, E, K, L, Q

• MEME motifs and MERCI motifs identified exclusively in allergens (provided in supplementary data)

Best Model Performance (Hybrid – RF + BLAST + MERCI, validation set):

Alternative model (RF + AAC alone): AUC = 0.92, MCC = 0.68

Comparison with existing methods (as reported in literature):

Independent dataset validation (297 newly added allergens, non‑redundant 56 set): Accuracy = 94.3% (280/297) and 91.1% (51/56)

Usage: Predicting allergenic proteins, mapping IgE epitopes in protein sequences, scanning protein for allergen‑specific motifs, similarity search against allergen/IgE databases.

Related Resources: Web server: https://webs.iiitd.edu.in/raghava/algpred2/ | GitHub: https://github.com/raghavagps/algpred2

Contact: raghava@iiitd.ac.in (Gajendra P. S. Raghava)