Statistics

TCRex currently provides prediction models for 49 different epitopes including 44 viral and 5 cancer epitopes. Performance metrics of these prediction models are shown in the tables below. Additionally, the validation graphs show the receiver operating characteristic (ROC) curve, the precision-recall (PR) curve, and the main feature importances of each classifier model.

Viral Epitope Nr. of sequences Balanced accuracy AUROC Average precision
CMV IPSINVHHY 85 0.7 ± 0.02 0.84 ± 0.04 0.66 ± 0.06
CMV NLVPMVATV 4812 0.56 ± 0.0 0.72 ± 0.01 0.39 ± 0.01
CMV QIKVRVKMV 36 0.5 ± 0.0 0.79 ± 0.05 0.4 ± 0.09
CMV QYDPVAALF 41 0.7 ± 0.06 0.82 ± 0.06 0.6 ± 0.06
CMV TPRVTGGGAM 258 0.7 ± 0.02 0.88 ± 0.03 0.75 ± 0.04
CMV VTEHDTLLY 277 0.54 ± 0.0 0.78 ± 0.02 0.39 ± 0.04
CMV YSEHPTFTSQY 74 0.59 ± 0.06 0.93 ± 0.04 0.71 ± 0.06
DENV1 GTSGSPIVNR 165 0.75 ± 0.05 0.88 ± 0.04 0.76 ± 0.06
DENV2 GTSGSPIIDK 60 0.61 ± 0.06 0.74 ± 0.08 0.49 ± 0.04
DENV3/4 GTSGSPIINR 158 0.73 ± 0.02 0.86 ± 0.03 0.75 ± 0.03
EBV EPLPQGQLTAY 36 0.64 ± 0.08 0.91 ± 0.06 0.68 ± 0.18
EBV GLCTLVAML 1208 0.66 ± 0.01 0.82 ± 0.02 0.59 ± 0.0
EBV HPVGEADYFEY 32 0.72 ± 0.08 0.86 ± 0.08 0.68 ± 0.13
EBV IVTDFSVIK 46 0.6 ± 0.05 0.83 ± 0.04 0.53 ± 0.05
EBV RAKFKQLL 262 0.65 ± 0.02 0.89 ± 0.01 0.69 ± 0.04
EBV YVLDHLIVV 103 0.52 ± 0.02 0.76 ± 0.07 0.44 ± 0.09
HCV ARMILMTHF 66 0.74 ± 0.07 0.86 ± 0.08 0.69 ± 0.12
HCV ATDALMTGY 177 0.75 ± 0.03 0.91 ± 0.04 0.77 ± 0.06
HCV CINGVCWTV 131 0.53 ± 0.03 0.75 ± 0.06 0.37 ± 0.11
HCV HSKKKCDEL 45 0.77 ± 0.09 0.99 ± 0.01 0.93 ± 0.03
HCV KLVALGINAV 65 0.62 ± 0.05 0.73 ± 0.08 0.51 ± 0.14
HIV EIYKRWII 185 0.65 ± 0.02 0.75 ± 0.06 0.52 ± 0.04
HIV FLKEKGGL 156 0.6 ± 0.03 0.76 ± 0.06 0.48 ± 0.1
HIV FPRPWLHGL 120 0.81 ± 0.02 0.93 ± 0.02 0.83 ± 0.03
HIV FRDYVDRFYKTLRAEQASQE 367 0.87 ± 0.02 1.0 ± 0.0 0.96 ± 0.01
HIV HPKVSSEVHI 75 0.69 ± 0.07 0.87 ± 0.08 0.7 ± 0.16
HIV IIKDYGKQM 54 0.81 ± 0.07 0.95 ± 0.04 0.84 ± 0.07
HIV ISPRTLNAW 58 0.61 ± 0.06 0.84 ± 0.03 0.6 ± 0.12
HIV KAFSPEVIPMF 210 0.73 ± 0.02 0.9 ± 0.01 0.71 ± 0.03
HIV KRWIILGLNK 396 0.65 ± 0.02 0.85 ± 0.04 0.64 ± 0.08
HIV KRWIIMGLNK 75 0.69 ± 0.05 0.85 ± 0.09 0.73 ± 0.12
HIV LPPIVAKEI 62 0.79 ± 0.04 0.9 ± 0.05 0.78 ± 0.06
HIV QVPLRPMTYK 48 0.64 ± 0.04 0.77 ± 0.11 0.51 ± 0.16
HIV RFYKTLRAEQASQ 210 0.9 ± 0.03 0.99 ± 0.0 0.96 ± 0.01
HIV RLRPGGKKK 31 0.73 ± 0.06 0.89 ± 0.09 0.73 ± 0.2
HIV RYPLTFGWCF 30 0.52 ± 0.03 0.72 ± 0.13 0.42 ± 0.12
HIV TPGPGVRYPL 86 0.68 ± 0.04 0.88 ± 0.03 0.74 ± 0.07
HIV TPQDLNTML 159 0.81 ± 0.02 0.94 ± 0.04 0.87 ± 0.06
HSV2 RPRGEVRFL 63 0.77 ± 0.04 0.92 ± 0.05 0.84 ± 0.08
HTLV1 SFHSLHLLF 131 0.68 ± 0.03 0.81 ± 0.08 0.63 ± 0.08
Influenza GILGFVFTL 3107 0.68 ± 0.01 0.81 ± 0.01 0.59 ± 0.03
Influenza LPRRSGAAGA 2137 0.54 ± 0.01 0.84 ± 0.01 0.4 ± 0.02
Influenza PKYVKQNTLKLAT 292 0.52 ± 0.01 0.72 ± 0.02 0.36 ± 0.05
YellowFeverVirus LLWNGPMAV 474 0.66 ± 0.01 0.79 ± 0.01 0.53 ± 0.03
Cancer Epitope Nr. of sequences Balanced accuracy AUROC Average precision
Melanoma AMFWSVPTV 82 0.59 ± 0.04 0.78 ± 0.04 0.48 ± 0.12
Melanoma EAAGIGILTV 266 0.69 ± 0.03 0.9 ± 0.01 0.74 ± 0.01
Melanoma ELAGIGILTV 1035 0.54 ± 0.0 0.72 ± 0.01 0.37 ± 0.03
Melanoma FLYNLLTRV 61 0.63 ± 0.08 0.87 ± 0.03 0.59 ± 0.1
Multiple Myeloma LLLGIGILV 233 0.58 ± 0.01 0.77 ± 0.04 0.44 ± 0.06