POPI: predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties

Tung, Chun Wei; Ho, Shinn-Ying

doi:10.1093/bioinformatics/btm061

Cited by 92 publications

(87 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Frequently, peptides are represented in binary format, but recently Tung and Ho [52] used the physicochemical properties of peptides known to bind to MHCI molecules as input data for SVMs, developing the POPI method (Table I). Similarly, Salomon and Flower [53] predicted MHCII-peptide binding using a kernel-based SVM that was trained on the similarity scores of MHCII allelic-specific peptide ligands.…”

Section: Machine Learning-based Motifsmentioning

confidence: 99%

Prediction of MHC-Peptide Binding: A Systematic and Comprehensive Overview

Lafuente¹,

Reche

2009

CPD

136

View full text Add to dashboard Cite

T cell immune responses are driven by the recognition of peptide antigens (T cell epitopes) that are bound to major histocompatibility complex (MHC) molecules. T cell epitope immunogenicity is thus contingent on several events, including appropriate and effective processing of the peptide from its protein source, stable peptide binding to the MHC molecule, and recognition of the MHC-bound peptide by the T cell receptor. Of these three hallmarks, MHC-peptide binding is the most selective event that determines T cell epitopes. Therefore, prediction of MHC-peptide binding constitutes the principal basis for anticipating potential T cell epitopes. The tremendous relevance of epitope identification in vaccine design and in the monitoring of T cell responses has spurred the development of many computational methods for predicting MHC-peptide binding that improve the efficiency and economics of T cell epitope identification. In this report, we will systematically examine the available methods for predicting MHC-peptide binding and discuss their most relevant advantages and drawbacks.

show abstract

Section: Machine Learning-based Motifsmentioning

confidence: 99%

Prediction of MHC-Peptide Binding: A Systematic and Comprehensive Overview

Lafuente¹,

Reche

2009

CPD

136

View full text Add to dashboard Cite

show abstract

“…Since the metabolic activation of PAHs could induce higher genotoxicity [30], additional biological features such as Ames tests with the addition of microsomal S9 fraction for metabolic activations of PAHs might serve as useful features for improving the prediction performance. Advanced machine learning methods combined with feature selection algorithms such as support vector machine and genetic algorithm could be further applied to further improve the prediction performance [31,32]. This study demonstrated a potential application of such models for predicting bioactivity of mixtures by combining chemical and biological features and could be further developed for other bioactivities.…”

Section: Discussionmentioning

confidence: 90%

Prediction of Proinflammatory Potentials of Engine Exhausts by Integrating Chemical and Biological Features

Lin

Jhang

et al. 2016

Bioinformatics and Biomedical Engineering

View full text Add to dashboard Cite

Abstract. The increasing prevalence of immune-related diseases has raised concerns about immunotoxicity of engine exhausts. The evaluation of immunotoxicity associated with engine exhausts has relied on expensive and timeconsuming experiments. In this study, a computational method named CBM was developed for predicting proinflammatory potentials of engine exhausts using chemical and biological data which are routinely analyzed for toxicity evaluation. The CBM model, based on a principal component regression algorithm, performs well with high correlation coefficient values of 0.972 and 0.849 obtained from training and independent test sets, respectively. In contrast, chemical or biological features alone showed poor correlation with the toxicity. The model indicates the importance of the utilization of both chemical and biological features for developing an effective model. The proposed method could be further developed and applied to predict bioactivities of mixtures.

show abstract

“…Therefore, the idea of producing anti-peptide antibodies in rabbits and BALB/c mice using the validated protocol with the High III mice cannot be ruled out. Although the antibody response was obtained for both immunogens in the High III mice, the high anti-Let#1 antibody titer compared with the anti-Let#2 antibody titer and the higher affinity may be justified by testing the immunogenicity prediction (POPI 2.0) [65], which indicates this peptide is more efficient as an immunogen with potential epitopes that are recognized by CD4 + T cell receptors. Furthermore, these antibodies were quite specific and did not react in a cross-evaluation with other antigens, suggesting that the method is efficient for validating these antibodies as potential identifiers of the native NaPi-IIb protein.…”

Section: Discussionmentioning

confidence: 98%

Novel Immunogenic Epitopes in the NaPi-IIb Protein: Production of Monospecific Antibodies Using Synthetic Peptides Outlined on Isoform Specific Regions of the Type IIb Sodium-Dependent Phosphate Transporter (NaPi-IIb)

Megale¹,

Júnior²,

Rangel³

et al. 2016

JCT

View full text Add to dashboard Cite

NaPi-IIb is a multiple passage protein membrane which is primarily responsible for phosphate uptake in the kidney and in the small intestine. Beyond its physiological functions, their involvement with carcinogenesis was initially described in mid-2003, due to its distinct level of expression in normal and tumor cells of the ovary. Although less common than cervical cancer, epithelial ovarian cancer is considered the most lethal gynecologic malignancy, which is mainly due to diagnosis in the advanced stages as a result of the absence of symptoms during the onset of the disease and the lack of tools for early detection. Here, we produce antibodies that are anti-synthetic peptides that are derived from the regions of second extracellular loop of NaPi-IIb, which is a non-overlapping portion of MX35 epitope. These two 15 distinct amino acid residue peptides, designated as Let#1 and Let#2, are engineered in a very thorough way to detect specific sites only in this isoform, thus excluding cross-reactivity with other carriers of the same family. The lack of immunogenicity of small peptides is surpassed by the conjugation with carrier proteins. Using immunochemical methods, we demonstrate that polyclonal antibodies that are mono-specific for * Corresponding author. Â. A. A. Megale et al. 130the Let#1 and Let#2 peptides recognize proteins that express similar amino acid sequences during blood circulation. Additionally, using flow cytometry, we identify NaPi-IIb in NIH:OVCAR-3 cells. The clear identification of two shorter peptides on the extracellular loop of NaPi-IIb, which are far from the monoclonal antibody MX35-recognizing epitopes, adds new promising tools for ovarian cancer follow-up and staging.

show abstract

POPI: predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties

Abstract: A web server for prediction of peptide immunogenicity (POPI) and the used dataset of MHC class I binding peptides (PEPMHCI) are available at http://iclab.life.nctu.edu.tw/POPI

Cited by 92 publications

References 30 publications

Prediction of MHC-Peptide Binding: A Systematic and Comprehensive Overview

Prediction of MHC-Peptide Binding: A Systematic and Comprehensive Overview

Prediction of Proinflammatory Potentials of Engine Exhausts by Integrating Chemical and Biological Features

Novel Immunogenic Epitopes in the NaPi-IIb Protein: Production of Monospecific Antibodies Using Synthetic Peptides Outlined on Isoform Specific Regions of the Type IIb Sodium-Dependent Phosphate Transporter (NaPi-IIb)

Contact Info

Product

Resources

About