Abbreviations: (R) = target variable e.g. 1 or 0 in training data randomly changed for each protein, HE = hold-out dataset error (%) i.e. error when predicting 30% of training data, OE = overall

NIAID Data Ecosystem60

The impact of genomic polymorphisms on the repertoire of human MHC class I-associated peptides

MHC-I类肽段呈递

免疫表位预测

epitope description:ATLPKNPPPK antigen name:Transcription factor 20 host organism:Homo sapiens mhc allele name:HLA-A*03:01

ImmuneData50

Additional file 3: of NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets

MHC-肽结合预测

Allele-specific length preference for 24 MHC molecules characterized by 20 or more ligand data points for the allmer and 9mer prediction methods compared to the length preference in the SYFPEITHI data

Figshare2016-12-15 更新80

Additional file 4: Table S3. of Deep convolutional neural networks for pan-specific peptide-MHC class I binding prediction

MHC-肽结合预测

计算免疫学

Detailed results for 5-fold cross-validation. (XLSX 11 kb)

Figshare2017-12-28 更新50