Send to

Choose Destination
Gigascience. 2017 May 1;6(5):1-11. doi: 10.1093/gigascience/gix017.

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

Liu G1,2,3, Li D2,3, Li Z1, Qiu S1,2, Li W2, Chao CC2,3,4, Yang N2,3,4, Li H2,4, Cheng Z5, Song X6, Cheng L2,3,7, Zhang X1,2, Wang J2,8, Yang H2,8, Ma K2, Hou Y2,3,9, Li B2,3,10.

Author information

BGI Education Center, University of Chinese Academy of Sciences, Main Building, Beishan Industrial Zone, Yantian District, Shenzhen 518083, China.
BGI-Shenzhen, Main Building, Beishan Industrial Zone, Yantian District, Shenzhen 518083, China.
BGI-GenoImmune, Gaoxing road, East Lake New Technology Development Zone, Wuhan 430079, China.
Complete Genomics, Inc., 2071 Stierlin Court, Mountain View, CA 94043, USA.
Molecular Imaging Program at Stanford, Department of Radiology and Bio-X Program, Stanford University, Montag Hall, 355 Galvez Street, Stanford, CA 94305, USA.
The Third Affiliated Hospital of Kunming Medical University (Tumor Hospital of Yunnan Province), Kunzhou Road, Xishan District, Kunming 650100, Yunnan Province, China.
BGI-Yunnan, Haiyuan North Road, Kunming Hi-tech Development Zone, Kunming 650000, Yunnan Province, China.
James D. Watson Institute of Genome Sciences, Yuhang Tong Road, Xihu District, Hangzhou 310058, Zhejiang Province, China.
Department of Biology, University of Copenhagen, Nørregade 10, PO Box 2177, 1017 Copenhagen K, Denmark.
BGI-Forensics, Main Building, Beishan Industrial, Zone Yantian District, Shenzhen 518083, China.


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.


Antitumor vaccine; PSSMHCpan; neoantigen; peptide-HLA binding affinity

[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Silverchair Information Systems Icon for PubMed Central
Loading ...
Support Center