PSSMHCpan: a novel PSSM-based software for predicting class I peptide-HLA binding affinity

Abstract Predicting peptide binding affinity with human leukocyte antigen (HLA) is a crucial step in developing powerful antitumor vaccine for cancer immunotherapy. Currently available methods work quite well in predicting peptide binding affinity with HLA alleles such as HLA-A*0201, HLA-A*0101, and HLA-B*0702 in terms of sensitivity and specificity. However, quite a few types of HLA alleles that are present in the majority of human populations including HLA-A*0202, HLA-A*0203, HLA-A*6802, HLA-B*5101, HLA-B*5301, HLA-B*5401, and HLA-B*5701 still cannot be predicted with satisfactory accuracy using currently available methods. Furthermore, currently the most popularly used methods for predicting peptide binding affinity are inefficient in identifying neoantigens from a large quantity of whole genome and transcriptome sequencing data. Here we present a Position Specific Scoring Matrix (PSSM)-based software called PSSMHCpan to accurately and efficiently predict peptide binding affinity with a broad coverage of HLA class I alleles. We evaluated the performance of PSSMHCpan by analyzing 10-fold cross-validation on a training database containing 87 HLA alleles and obtained an average area under receiver operating characteristic curve (AUC) of 0.94 and accuracy (ACC) of 0.85. In an independent dataset (Peptide Database of Cancer Immunity) evaluation, PSSMHCpan is substantially better than the popularly used NetMHC-4.0, NetMHCpan-3.0, PickPocket, Nebula, and SMM with a sensitivity of 0.90, as compared to 0.74, 0.81, 0.77, 0.24, and 0.79. In addition, PSSMHCpan is more than 197 times faster than NetMHC-4.0, NetMHCpan-3.0, PickPocket, sNebula, and SMM when predicting neoantigens from 661 263 peptides from a breast tumor sample. Finally, we built a neoantigen prediction pipeline and identified 117 017 neoantigens from 467 cancer samples of various cancers from TCGA. PSSMHCpan is superior to the currently available methods in predicting peptide binding affinity with a broad coverage of HLA class I alleles.

[1]  Mark P. Styczynski,et al.  BLOSUM62 miscalculations improve search performance , 2008, Nature Biotechnology.

[2]  Morten Nielsen,et al.  Automated benchmarking of peptide-MHC class I binding predictions , 2015, Bioinform..

[3]  Hiroaki Tanaka,et al.  Multipeptide immune response to cancer vaccine IMA901 after single-dose cyclophosphamide associates with longer patient survival , 2012, Nature Medicine.

[4]  Alessandro Sette,et al.  Generating quantitative models describing the sequence specificity of biological processes with the stabilized matrix method , 2005, BMC Bioinformatics.

[5]  S. Muta,et al.  Changes at the floor of the peptide-binding groove induce a strong preference for proline at position 3 of the bound peptide: molecular dynamics simulations of HLA-A*0217. , 2000, Biopolymers.

[6]  Temple F. Smith,et al.  Prediction of gene structure. , 1992, Journal of molecular biology.

[7]  Sneh Lata,et al.  Application of machine learning techniques in predicting MHC binders. , 2007, Methods in molecular biology.

[8]  Weida Tong,et al.  Understanding and predicting binding between human leukocyte antigens (HLAs) and peptides by network analysis , 2015, BMC Bioinformatics.

[9]  Qing Zhang,et al.  Immune epitope database analysis resource (IEDB-AR) , 2008, Nucleic Acids Res..

[10]  Oliver Kohlbacher,et al.  SVMHC: a server for prediction of MHC-binding peptides , 2006, Nucleic Acids Res..

[11]  Morten Nielsen,et al.  The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding , 2009, Bioinform..

[12]  O. Lund,et al.  NetMHCpan, a method for MHC class I binding prediction beyond humans , 2008, Immunogenetics.

[13]  E. Mardis,et al.  pVAC-Seq: A genome-guided in silico approach to identifying tumor neoantigens , 2016, Genome Medicine.

[14]  Nagasuma R. Chandra,et al.  HLaffy: estimating peptide affinities for Class-1 HLA molecules by learning position-specific pair potentials , 2016, Bioinform..

[15]  Morten Nielsen,et al.  Gapped sequence alignment using artificial neural networks: application to the MHC class I system , 2016, Bioinform..

[16]  Morten Nielsen,et al.  Prediction of epitopes using neural network based methods. , 2011, Journal of immunological methods.

[17]  Alejandro A. Schäffer,et al.  PSI-BLAST pseudocounts and the minimum description length principle , 2008, Nucleic acids research.

[18]  Jennifer L. Johnson,et al.  Transcriptome Analysis in Domesticated Species: Challenges and Strategies , 2015, Bioinformatics and biology insights.

[19]  Xuhua Xia,et al.  Position Weight Matrix, Gibbs Sampler, and the Associated Significance Tests in Motif Characterization and Prediction , 2012, Scientifica.

[20]  Weida Tong,et al.  Machine Learning Methods for Predicting HLA–Peptide Binding Activity , 2015, Bioinformatics and biology insights.

[21]  Cathy H. Wu,et al.  UniProt: the Universal Protein knowledgebase , 2004, Nucleic Acids Res..

[22]  Morten Nielsen,et al.  NetMHCcons: a consensus method for the major histocompatibility complex class I predictions , 2011, Immunogenetics.

[23]  Gajendra P.S. Raghava,et al.  A hybrid approach for predicting promiscuous MHC class I restricted T cell epitopes , 2007, Journal of Biosciences.

[24]  M. Nielsen,et al.  NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets , 2016, Genome Medicine.

[25]  J. Castle,et al.  HLA typing from RNA-Seq sequence reads , 2012, Genome Medicine.

[26]  Hao Ye,et al.  sNebula, a network-based algorithm to predict binding between human leukocyte antigens and peptides , 2016, Scientific Reports.

[27]  Morten Nielsen,et al.  Dataset size and composition impact the reliability of performance benchmarks for peptide-MHC binding predictions , 2014, BMC Bioinformatics.

[28]  Hasan H. Otu,et al.  Prediction of peptides binding to MHC class I and II alleles by temporal motif mining , 2013, BMC Bioinformatics.

[29]  Mathias M Schuler,et al.  SYFPEITHI: database for searching and T-cell epitope prediction. , 2007, Methods in molecular biology.

[30]  J. Arthur,et al.  Predicting peptide binding to Major Histocompatibility Complex molecules. , 2011, Autoimmunity reviews.

[31]  O. Lund,et al.  novel sequence representations Reliable prediction of T-cell epitopes using neural networks with , 2003 .

[32]  Morten Nielsen,et al.  A Community Resource Benchmarking Predictions of Peptide Binding to MHC-I Molecules , 2006, PLoS Comput. Biol..

[33]  Z. Modrušan,et al.  Predicting immunogenic tumour mutations by combining mass spectrometry and exome sequencing , 2014, Nature.

[34]  O. Lund,et al.  NetMHCpan, a Method for Quantitative Predictions of Peptide Binding to Any HLA-A and -B Locus Protein of Known Sequence , 2007, PloS one.

[35]  Gajendra P. S. Raghava,et al.  MHCBN: a comprehensive database of MHC binding and non-binding peptides , 2003, Bioinform..

[36]  Deborah Hix,et al.  The immune epitope database (IEDB) 3.0 , 2014, Nucleic Acids Res..

[37]  O. Schueler‐Furman,et al.  Structure‐based prediction of binding peptides to MHC class I molecules: Application to a broad range of MHC alleles , 2000, Protein science : a publication of the Protein Society.

[38]  Harris Papadopoulos,et al.  Machine learning competition in immunology - Prediction of HLA class I binding peptides. , 2011, Journal of immunological methods.

[39]  E. Mardis,et al.  A dendritic cell vaccine increases the breadth and diversity of melanoma neoantigen-specific T cells , 2015, Science.

[40]  Nathalie Vigneron,et al.  Database of T cell-defined human tumor antigens: the 2013 update. , 2013, Cancer immunity.

[41]  H. Hakonarson,et al.  ANNOVAR: functional annotation of genetic variants from high-throughput sequencing data , 2010, Nucleic acids research.

[42]  T. Hanai,et al.  Hidden Markov model-based prediction of antigenic peptides that interact with MHC class II molecules. , 2002, Journal of bioscience and bioengineering.

[43]  Steven G E Marsh,et al.  The IPD-IMGT/HLA Database - New developments in reporting HLA variation. , 2016, Human immunology.

[44]  Oliver Kohlbacher,et al.  Immunoinformatics and epitope prediction in the age of genomic medicine , 2015, Genome Medicine.