Current methods for the prediction of T‐cell epitopes

Kar, Prattusha; Ruiz‐Perez, Lanie; Arooj, Mahreen; Mancera, Ricardo L.

doi:10.1002/pep2.24046

Cited by 14 publications

(11 citation statements)

References 203 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on experimentally assessed binding affinity data of 743 peptides for the seven major HLA class-I types, we calculated the sensitivity, specificity, and accuracy of the predictors depending on HLA type and peptide length (29). MHC-binding predictors have been benchmarked and reviewed previously (30)(31)(32)(33)(34). Weekly automated benchmarking is performed for new entries to the immune epitope database (IEDB) but often covers only a small sample of peptides and HLA types (35).…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of MHC Class-I Binding Prediction Tools Based on an Experimentally Validated MHC–Peptide Binding Data Set

Bonsack

Hoppe

Winter

et al. 2019

Cancer Immunology Research

View full text Add to dashboard Cite

Knowing whether a protein can be processed and the resulting peptides presented by major histocompatibility complex (MHC) is highly important for immunotherapy design. MHC ligands can be predicted by in silico peptide-MHC class-I binding prediction algorithms. However, prediction performance differs considerably, depending on the selected algorithm, MHC class-I type, and peptide length. We evaluated the prediction performance of 13 algorithms based on binding affinity data of 8-to 11-mer peptides derived from the HPV16 E6 and E7 proteins to the most prevalent human leukocyte antigen (HLA) types. Peptides from high to low predicted binding likelihood were synthesized, and their HLA binding was experimentally verified by in vitro competitive binding assays. Based on the actual binding capacity of the peptides, the performance of prediction algorithms was analyzed by calculating receiver operating characteristics (ROC) and the area under the curve (A ROC). No algorithm outperformed others, but different algorithms predicted best for particular HLA types and peptide lengths. The sensitivity, specificity, and accuracy of decision thresholds were calculated. Commonly used decision thresholds yielded only 40% sensitivity. To increase sensitivity, optimal thresholds were calculated, validated, and compared. In order to make maximal use of prediction algorithms available online, we developed MHCcombine, a web application that allows simultaneous querying and output combination of up to 13 prediction algorithms. Taken together, we provide here an evaluation of peptide-MHC class-I binding prediction tools and recommendations to increase prediction sensitivity to extend the number of potential epitopes applicable as targets for immunotherapy.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of MHC Class-I Binding Prediction Tools Based on an Experimentally Validated MHC–Peptide Binding Data Set

Bonsack

Hoppe

Winter

et al. 2019

Cancer Immunology Research

View full text Add to dashboard Cite

show abstract

“…Current technologies (e.g., (Nielsen et al, 2007)) predict if a given peptide will bind to a given HLA allele using properties of the amino acids but without using 3D details of the chemical structure of the peptide or information on the structural binding of the peptide and HLA molecule. Computational predictions of binding are considered too difficult at the present time due to the sensitivity of the structural conformations to the detailed chemistry of peptides and the non-covalent interactions (Kar et al, 2018). Nevertheless, simulations could be used to generate similarity scores between peptides, and then the supervised binding data can be used to train a kernelized classification algorithm.…”

Section: Discussionmentioning

confidence: 99%

Simulation-assisted machine learning

et al. 2019

View full text Add to dashboard Cite

Motivation In a predictive modeling setting, if sufficient details of the system behavior are known, one can build and use a simulation for making predictions. When sufficient system details are not known, one typically turns to machine learning, which builds a black-box model of the system using a large dataset of input sample features and outputs. We consider a setting which is between these two extremes: some details of the system mechanics are known but not enough for creating simulations that can be used to make high quality predictions. In this context we propose using approximate simulations to build a kernel for use in kernelized machine learning methods, such as support vector machines. The results of multiple simulations (under various uncertainty scenarios) are used to compute similarity measures between every pair of samples: sample pairs are given a high similarity score if they behave similarly under a wide range of simulation parameters. These similarity values, rather than the original high dimensional feature data, are used to build the kernel. Results We demonstrate and explore the simulation-based kernel (SimKern) concept using four synthetic complex systems—three biologically inspired models and one network flow optimization model. We show that, when the number of training samples is small compared to the number of features, the SimKern approach dominates over no-prior-knowledge methods. This approach should be applicable in all disciplines where predictive models are sought and informative yet approximate simulations are available. Availability and implementation The Python SimKern software, the demonstration models (in MATLAB, R), and the datasets are available at https://github.com/davidcraft/SimKern. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

“…Epitope prediction is the first crucial stage in vaccine development since the epitope serves to stimulate immune responses from B-cells and T-cells, and prediction algorithms can be used to design a successful vaccine. For analyzing peptide reactions in epitope prediction, computational approaches such as SVMs, motif-based systems, QSAR (Quantitative Structure-Activity Relationship Analysis), structure-based, neural networks, and Hidden Markov Models (HMMs) can be used [ 27 ]. Based on statistical theory, SVMs are used to categorize data into two groups: binders and non-binders [ 28 ].…”

Section: Computational Tools In Modern Vaccine Developmentmentioning

confidence: 99%