PAAQD: Predicting immunogenicity of MHC class I binding peptides using amino acid pairwise contact potentials and quantum topological molecular similarity descriptors

Saethang, Thammakorn; Hirose, Osamu; Kimkong, Ingorn; Vu, Tran Anh; Dang, Xuan Tho; Nguyen, Lan Anh; Le, Tu Kien T.; Kubo, Mamoru; Yamada, Yoichi; Satou, Kenji

doi:10.1016/j.jim.2012.09.016

Cited by 26 publications

(20 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Correlations between the immunogenicity of a peptide, its MHC-binding affinity and pMHC complex stability tend to be poor. [82][83][84][85] Each method has its advantages and shortcomings and depending on needs and means, different strategies for TA T cell epitope discovery are indicated. Bioinformatics sequencing data analysis, identification of mutated and overexpressed genes, and prediction of MHC ligands constitute a crucial initial part.…”

Section: Discussionmentioning

confidence: 99%

Current tools for predicting cancer-specific T cell immunity

Gfeller¹,

Bassani-Sternberg²,

Schmidt³

et al. 2016

OncoImmunology

View full text Add to dashboard Cite

Tumor exome and RNA sequencing data provide a systematic and unbiased view on cancer-specific expression, over-expression, and mutations of genes, which can be mined for personalized cancer vaccines and other immunotherapies. Of key interest are tumor-specific mutations, because T cells recognizing neoepitopes have the potential to be highly tumoricidal. Here, we review recent developments and technical advances in identifying MHC class I and class II-restricted tumor antigens, especially neoantigen derived MHC ligands, including in silico predictions, immune-peptidome analysis by mass spectrometry, and MHC ligand validation by biochemical methods on T cells.

show abstract

Section: Discussionmentioning

confidence: 99%

Current tools for predicting cancer-specific T cell immunity

Gfeller¹,

Bassani-Sternberg²,

Schmidt³

et al. 2016

OncoImmunology

View full text Add to dashboard Cite

show abstract

“…However, it should be noted that the in silico prediction methods used predict only the theoretical affinity of the peptide for the MHC molecule and do not reveal if this peptide is actually being processed in vivo and/or recognized by a CD8 T-cell receptor, a necessary step in the initiation of an immune response. While there are models that predict the immunogenicity of a presented peptide, they are still plagued by poor accuracy, and most remain limited to very common HLA alleles (40).…”

Section: Discussionmentioning

confidence: 99%

Varicella-Zoster Virus-Derived Major Histocompatibility Complex Class I-Restricted Peptide Affinity Is a Determining Factor in the HLA Risk Profile for the Development of Postherpetic Neuralgia

Meysman

Ogunjimi

Naulaerts

et al. 2015

J Virol

View full text Add to dashboard Cite

Postherpetic neuralgia (PHN) is the most common complication of herpes zoster and is typified by a lingering pain that can last months or years after the characteristic herpes zoster rash disappears. It is well known that there are risk factors for the development of PHN, such as its association with certain HLA alleles. In this study, previous HLA genotyping results were collected and subjected to a meta-analysis with increased statistical power. This work shows that the alleles HLA-A*33 and HLA-B*44 are significantly enriched in PHN patients, while HLA-A*02 and HLA-B*40 are significantly depleted. Prediction of the varicella-zoster virus (VZV) peptide affinity for these four HLA variants by using one in-house-developed and two existing state-of-the-art major histocompatibility complex (MHC) class I ligand prediction methods reveals that there is a great difference in their absolute and relative peptide binding repertoires. It was observed that HLA-A*02 displays a high affinity for an ϳ7-fold-higher number of VZV peptides than HLA-B*44. Furthermore, after correction for HLA allele-specific limitations, the relative affinity of HLA-A*33 and HLA-B*44 for VZV peptides was found to be significantly lower than those of HLA-A*02 and HLA-B*40. In addition, HLA peptide affinity calculations indicate strong trends for VZV to avoid high-affinity peptides in some of its proteins, independent of the studied HLA allele. IMPORTANCE Varicella-zoster virus can cause two distinct diseases: chickenpox (varicella) and shingles (herpes zoster).Varicella is a common disease in young children, while herpes zoster is more frequent in older individuals. A common complication of herpes zoster is postherpetic neuralgia, a persistent and debilitating pain that can remain months up to years after the resolution of the rash. In this study, we show that the relative affinity of HLA variants associated with higher postherpetic neuralgia risk for varicella-zoster virus peptides is lower than that of variants with a lower risk. These results provide new insight into the development of postherpetic neuralgia and strongly support the hypothesis that one of its possible underlying causes is a suboptimal anti-VZV immune response due to weak HLA binding peptide affinity. P rimary infection by varicella-zoster virus (VZV) results in the common childhood disease varicella (chickenpox). VZV persists as a latent infection in dorsal root ganglion cells with minimal gene transcription (1). Clinical reactivation of VZV typically results in a characteristic painful dermatomal rash and is termed shingles or herpes zoster (HZ). Furthermore, HZ patients transmit VZV and thus could cause chickenpox in susceptible individuals, thereby reigniting the epidemiological VZV cycle (2, 3). It is estimated that ϳ10% to 30% of individuals will develop HZ in their lifetimes, with the frequency increasing to 50% for those Ͼ85 years of age (4). For many of these patients, the affected region remains painful for months or, exceptionally, years after the HZ rash reso...

show abstract

“…This dataset named as 'IMMA2 dataset' is available at http://iclab.life.nctu.edu.tw/POPISK/download.php . The other dataset has been applied to PAAQD [ 27 ], and we name it 'PAAQD dataset'. This dataset contains 278 HLA-A2 restricted immunogenic epitopes and 101 non-immunogenic epitopes, available at http://pirun.ku.ac.th/~fsciiok/PAAQD.rar .…”

Section: Methodsmentioning

confidence: 99%

“…POPISK [ 26 ] is a SVM-based method using the weighted degree string kernel. PAAQD [ 27 ] adopted two novel sequence-derived features (the amino acid pairwise contact potentials and the quantum topological molecular similarity), and the SVM-based predictor was constructed. In the previous work [ 28 ], we proposed the average scoring ensemble method by combining seven sequence-derived features.…”

Section: Introductionmentioning

confidence: 99%

Accurate Prediction of Immunogenic T-Cell Epitopes from Epitope Sequences Using the Genetic Algorithm-Based Ensemble Learning

et al. 2015

View full text Add to dashboard Cite

BackgroundT-cell epitopes play the important role in T-cell immune response, and they are critical components in the epitope-based vaccine design. Immunogenicity is the ability to trigger an immune response. The accurate prediction of immunogenic T-cell epitopes is significant for designing useful vaccines and understanding the immune system.MethodsIn this paper, we attempt to differentiate immunogenic epitopes from non-immunogenic epitopes based on their primary structures. First of all, we explore a variety of sequence-derived features, and analyze their relationship with epitope immunogenicity. To effectively utilize various features, a genetic algorithm (GA)-based ensemble method is proposed to determine the optimal feature subset and develop the high-accuracy ensemble model. In the GA optimization, a chromosome is to represent a feature subset in the search space. For each feature subset, the selected features are utilized to construct the base predictors, and an ensemble model is developed by taking the average of outputs from base predictors. The objective of GA is to search for the optimal feature subset, which leads to the ensemble model with the best cross validation AUC (area under ROC curve) on the training set.ResultsTwo datasets named ‘IMMA2’ and ‘PAAQD’ are adopted as the benchmark datasets. Compared with the state-of-the-art methods POPI, POPISK, PAAQD and our previous method, the GA-based ensemble method produces much better performances, achieving the AUC score of 0.846 on IMMA2 dataset and the AUC score of 0.829 on PAAQD dataset. The statistical analysis demonstrates the performance improvements of GA-based ensemble method are statistically significant.ConclusionsThe proposed method is a promising tool for predicting the immunogenic epitopes. The source codes and datasets are available in S1 File.

show abstract

PAAQD: Predicting immunogenicity of MHC class I binding peptides using amino acid pairwise contact potentials and quantum topological molecular similarity descriptors

Cited by 26 publications

References 43 publications

Current tools for predicting cancer-specific T cell immunity

Current tools for predicting cancer-specific T cell immunity

Varicella-Zoster Virus-Derived Major Histocompatibility Complex Class I-Restricted Peptide Affinity Is a Determining Factor in the HLA Risk Profile for the Development of Postherpetic Neuralgia

Accurate Prediction of Immunogenic T-Cell Epitopes from Epitope Sequences Using the Genetic Algorithm-Based Ensemble Learning

Contact Info

Product

Resources

About