PSSMHCpan: a novel PSSM-based software for predicting class I peptide-HLA binding affinity
Tóm tắt
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.
Từ khóa
Tài liệu tham khảo
Altschul, 2009, PSI-BLAST pseudocounts and the minimum description length principle, Nucleic Acids Res, 37, 815, 10.1093/nar/gkn981
Andreatta, 2016, Gapped sequence alignment using artificial neural networks: application to the MHC class I system, Bioinformatics, 32, 511, 10.1093/bioinformatics/btv639
Apweiler, 2004, UniProt: the Universal Protein knowledgebase, Nucleic Acids Res, 32, D115, 10.1093/nar/gkh131
Backert, 2015, Immunoinformatics and epitope prediction in the age of genomic medicine, Genome Med, 7, 119, 10.1186/s13073-015-0245-0
Bhasin, 2007, A hybrid approach for predicting promiscuous MHC class I restricted T cell epitopes, J Biosci, 32, 31, 10.1007/s12038-007-0004-5
Bhasin, 2003, MHCBN: a comprehensive database of MHC binding and non-binding peptides, Bioinformatics, 19, 665, 10.1093/bioinformatics/btg055
Carreno, 2015, Cancer immunotherapy. A dendritic cell vaccine increases the breadth and diversity of melanoma neoantigen-specific T cells, Science, 348, 803, 10.1126/science.aaa3828
Donnes, 2006, SVMHC: a server for prediction of MHC-binding peptides, Nucleic Acids Res, 34, W194, 10.1093/nar/gkl284
Hoof, 2009, NetMHCpan, a method for MHC class I binding prediction beyond humans, Immunogenetics, 61, 1, 10.1007/s00251-008-0341-z
Hundal, 2016, pVAC-Seq: a genome-guided in silico approach to identifying tumor neoantigens, Genome Med, 8, 11, 10.1186/s13073-016-0264-5
Karosiene, 2012, NetMHCcons: a consensus method for the major histocompatibility complex class I predictions, Immunogenetics, 64, 177, 10.1007/s00251-011-0579-8
Kim, 2014, Dataset size and composition impact the reliability of performance benchmarks for peptide-MHC binding predictions, BMC Bioinformatics, 15, 241, 10.1186/1471-2105-15-241
Lata, 2007, Application of machine learning techniques in predicting MHC binders, Meth Mol Biol, 409, 201, 10.1007/978-1-60327-118-9_14
Liao, 2011, Predicting peptide binding to Major Histocompatibility Complex molecules, Autoimmunity Rev, 10, 469, 10.1016/j.autrev.2011.02.003
Lundegaard, 2011, Prediction of epitopes using neural network based methods, J Immunol Meth, 374, 26, 10.1016/j.jim.2010.10.011
Luo, 2015, Understanding and predicting binding between human leukocyte antigens (HLAs) and peptides by network analysis, BMC Bioinformatics, 16, S9, 10.1186/1471-2105-16-S13-S9
Luo, 2016, sNebula, a network-based algorithm to predict binding between human leukocyte antigens and peptides, Sci Rep, 6, 32115, 10.1038/srep32115
Luo, 2015, Machine learning methods for predicting HLA-peptide binding activity, Bioinform Biol Insights, 9, 21
Meydan, 2013, Prediction of peptides binding to MHC class I and II alleles by temporal motif mining, BMC Bioinformatics, 14, S13, 10.1186/1471-2105-14-S2-S13
Mukherjee, 2016, HLaffy: estimating peptide affinities for Class-1 HLA molecules by learning position-specific pair potentials, Bioinformatics, 10.1093/bioinformatics/btw156
Nielsen, 2016, NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets, Genome Med, 8, 33, 10.1186/s13073-016-0288-x
Nielsen, 2007, NetMHCpan, a method for quantitative predictions of peptide binding to any HLA-A and -B locus protein of known sequence, PloS One, 2, e796, 10.1371/journal.pone.0000796
Nielsen, 2003, Reliable prediction of T-cell epitopes using neural networks with novel sequence representations, Protein Sci, 12, 1007, 10.1110/ps.0239403
Noguchi, 2002, Hidden Markov model-based prediction of antigenic peptides that interact with MHC class II molecules, J Biosci Bioeng, 94, 264, 10.1016/S1389-1723(02)80160-8
Peters, 2006, A community resource benchmarking predictions of peptide binding to MHC-I molecules, PLoS Comput Biol, 2, e65, 10.1371/journal.pcbi.0020065
Peters, 2005, Generating quantitative models describing the sequence specificity of biological processes with the stabilized matrix method, BMC Bioinformatics, 6, 132, 10.1186/1471-2105-6-132
Robinson, 2016, The IPD-IMGT/HLA Database - new developments in reporting HLA variation, Human Immunol, 10.1016/j.humimm.2016.01.020
Schueler-Furman, 2000, Structure-based prediction of binding peptides to MHC class I molecules: application to a broad range of MHC alleles, Protein Sci, 9, 1838, 10.1110/ps.9.9.1838
Schuler, 2007, SYFPEITHI: database for searching and T-cell epitope prediction, Meth Mol Biol, 409, 75, 10.1007/978-1-60327-118-9_5
Styczynski, 2008, BLOSUM62 miscalculations improve search performance, Nat Biotechnol, 26, 274, 10.1038/nbt0308-274
Toh, 2000, 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, Biopolymers, 54, 318, 10.1002/1097-0282(20001015)54:5<318::AID-BIP30>3.0.CO;2-T
Trolle, 2015, Automated benchmarking of peptide-MHC class I binding predictions, Bioinformatics, 31, 2174, 10.1093/bioinformatics/btv123
Vigneron, 2013, Database of T cell-defined human tumor antigens: the 2013 update, Cancer Immunity, 13, 15
Walter, 2012, Multipeptide immune response to cancer vaccine IMA901 after single-dose cyclophosphamide associates with longer patient survival, Nat Med, 18, 1254, 10.1038/nm.2883
Wang, 2010, ANNOVAR: functional annotation of genetic variants from high-throughput sequencing data, Nucleic Acids Res, 38, e164, 10.1093/nar/gkq603
Xia, 2012, Position weight matrix, gibbs sampler, and the associated significance tests in motif characterization and prediction, Scientifica, 2012, 917540, 10.6064/2012/917540
Yadav, 2014, Predicting immunogenic tumour mutations by combining mass spectrometry and exome sequencing, Nature, 515, 572, 10.1038/nature14001
Zhang, 2011, Machine learning competition in immunology - prediction of HLA class I binding peptides, J Immunol Meth, 374, 1, 10.1016/j.jim.2011.09.010
Zhang, 2009, The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding, Bioinformatics, 25, 1293, 10.1093/bioinformatics/btp137
Zhang, 2008, Immune epitope database analysis resource (IEDB-AR), Nucleic Acids Res, 36, W513, 10.1093/nar/gkn254
PSSMHCpan Project Page