Toward more accurate pan-specific MHC-peptide binding prediction: a review of current methods and tools

Abstract

Binding of short antigenic peptides to major histocompatibility complex (MHC) molecules is a core step in adaptive immune response. Precise identification of MHC-restricted peptides is of great significance for understanding the mechanism of immune response and promoting the discovery of immunogenic epitopes. However, due to the extremely high MHC polymorphism and huge cost of biochemical experiments, there is no experimentally measured binding data for most MHC molecules. To address the problem of predicting peptides binding to these MHC molecules, recently computational approaches, called pan-specific methods, have received keen interest. Pan-specific methods make use of experimentally obtained binding data of multiple alleles, by which binding peptides (binders) of not only these alleles but also those alleles with no known binders can be predicted. To investigate the possibility of further improvement in performance and usability of pan-specific methods, this article extensively reviews existing pan-specific methods and their web servers. We first present a general framework of pan-specific methods. Then, the strategies and performance as well as utilities of web servers are compared. Finally, we discuss the future direction to improve pan-specific methods for MHC-peptide binding prediction.

Tumor neoantigens: building a framework for personalized cancer immunotherapy

“…Multiple tools exist to predict peptide binding to MHCI. A comprehensive list of prediction tools is available (http://cancerimmunity.org/resources/webtools/), and the bioinformatics and biochemical aspects of these programs have been extensively reviewed elsewhere (62)(63)(64). Whereas SYFPEITHI (65), Rankpep (66), and BIMAS (67) were the first such tools to be developed, more accurate prediction algorithms have now come on line, and some have been incorporated into the Immune Epitope Database and Analysis Resource (IEDB) (68).…”

Rapid, Precise, and Reproducible Prediction of Peptide–MHC Binding Affinities from Molecular Dynamics That Correlate Well with Experiment

“…This can be achieved by higher order machine learning techniques such as artificial neural networks, support vector machines, or hidden Markov models. These approaches have been extrapolated for pan allele predictions yielding coverage of many human MHCI and MHCII alleles 6 . Such sequencebased machine learning predictions of pMHC binding are highly dependent on the availability of pre-existing training data.…”

Learning Sequence Determinants of Protein:Protein Interaction Specificity with Sparse Graphical Models

“…Several large-scale studies have been conducted using such techniques for particular families of interacting proteins, including PDZ domains and their peptide ligands (Chen et al, 2008;Tonikian et al, 2008), and human basic-region leucine zippers (bZIPs) and their coiled-coil partners (Fong et al, 2004;Grigoryan et al, 2009). In lieu of large-scale studies, the aggregation of a large number of smaller-scale experiments can also yield extensive amounts of detailed binding data, for example, for major histocompability complex (MHC) and ligands (Peters et al, 2005;Nielsen et al, 2007;Wang et al, 2008;Bordner and Mittelmann, 2010;Zhang et al, 2012), and serine proteases and inhibitors (Lu et al, 2001;Li et al, 2005).…”