Skip to main content

01.12.2016 | Research | Ausgabe 1/2016 Open Access

Journal of Translational Medicine 1/2016

ProInflam: a webserver for the prediction of proinflammatory antigenicity of peptides and proteins

Journal of Translational Medicine > Ausgabe 1/2016
Sudheer Gupta, Midhun K. Madhu, Ashok K. Sharma, Vineet K. Sharma
Wichtige Hinweise

Electronic supplementary material

The online version of this article (doi:10.​1186/​s12967-016-0928-3) contains supplementary material, which is available to authorized users.



Proinflammatory immune response involves a complex series of molecular events leading to inflammatory reaction at a site, which enables host to combat plurality of infectious agents. It can be initiated by specific stimuli such as viral, bacterial, parasitic or allergenic antigens, or by non-specific stimuli such as LPS. On counter with such antigens, the complex interaction of antigen presenting cells, T cells and inflammatory mediators like IL1α, IL1β, TNFα, IL12, IL18 and IL23 lead to proinflammatory immune response and further clearance of infection. In this study, we have tried to establish a relation between amino acid sequence of antigen and induction of proinflammatory response.


A total of 729 experimentally-validated proinflammatory and 171 non-proinflammatory epitopes were obtained from IEDB database. The A, F, I, L and V amino acids and AF, FA, FF, PF, IV, IN dipeptides were observed as preferred residues in proinflammatory epitopes. Using the compositional and motif-based features of proinflammatory and non-proinflammatory epitopes, we have developed machine learning-based models for prediction of proinflammatory response of peptides. The hybrid of motifs and dipeptide-based features displayed best performance with MCC = 0.58 and an accuracy of 87.6 %.


The amino acid sequence-based features of peptides were used to develop a machine learning-based prediction tool for the prediction of proinflammatory epitopes. This is a unique tool for the computational identification of proinflammatory peptide antigen/candidates and provides leads for experimental validations. The prediction model and tools for epitope mapping and similarity search are provided as a comprehensive web server which is freely available at http://​metagenomics.​iiserb.​ac.​in/​proinflam/​ and http://​metabiosys.​iiserb.​ac.​in/​proinflam/​.
Additional file 1: Table S1. Amino acid composition distribution between proinflammatory and non-proinflammatory data.
Additional file 2: Table S2. Dipeptide composition distribution between proinflammatory and non proinflammatory data.
Additional file 3: Table S3. MERCI motifs extracted form proinflammatory and non-proinflammatory data.
Additional file 4: Table S4. Performance of models developed on main dataset, with RandomForest, BayesNet, NaiveBayes, IBk and J48.
Additional file 5: Table S5. . Performance of different machine learning models developed on alternate dataset.
Über diesen Artikel

Weitere Artikel der Ausgabe 1/2016

Journal of Translational Medicine 1/2016 Zur Ausgabe