1.The detailed example
csv file: test.csv
Annotation,HLA,peptide NCI-3784,HLA-A01:01,MKRFVQWL NCI-3784,HLA-A03:01,MKRFVQWL NCI-3784,HLA-B07:02,MKRFVQWL NCI-3784,HLA-B07:02,MKRFVQWL NCI-3784,HLA-C07:02,MKRFVQWL NCI-3784,HLA-C07:02,MKRFVQWL NCI-3784,HLA-A01:01,KRFVQWLK NCI-3784,HLA-A03:01,KRFVQWLK NCI-3784,HLA-B07:02,KRFVQWLK NCI-3784,HLA-B07:02,KRFVQWLK
To note , deephlapan only predicts the potential neoantigens within HLA-A,B,C alleles. The blank in the file name is not allowed (e.g. ‘A B C.csv’ should be ‘A_B_C.csv’).
2. The meaning of each parameter
Binding score: the score predicted by the binding model of DeepHLApan, which ranges from 0 to 1 and indicates the probability that peptide binds with HLA allele. It would be more likely to be binders if the binding score closer to 1.
Immunogenicity score : the score predicted by the immunogenicity model of DeepHLApan, which ranges from 0 to 1 and 0.5 is the threshold to select the predicted immunogenic pHLA.
Address: College of Pharmaceutical Sciences, Zhejiang University, Hangzhou
Citation: Wu, J., Wang, W., Zhang, J., Zhou, B., Zhao, W., Su, Z., Gu, X., Wu J., Zhou Z.*, Chen, S.* (2019). DeepHLApan: A deep learning approach for neoantigen prediction considering both HLA-peptide binding and immunogenicity. Frontiers in Immunology, 10, 2559. https://doi.org/10.3389/fimmu.2019.02559