Table 4

Performance of BVLSTM-MHC along with ten existent MHC class I predictors on independent MHCBN dataset

MethodsACCAUCF1MCCSpecificitySensitivityPrecisionAUPR# Postive examples# Negative examples
ANN [44]0.88270.91660.68660.62050.95070.62160.76670.772637142
comblibsidney 2008 [71]0.74190.11410.00001.00000.00000.00000.15911646
NetMHCcons [42]0.88830.91690.72220.65280.93660.70270.74290.845737142
NetMHCpan [63]0.85470.90240.59380.51730.94370.51350.70370.747137142
NetMHCpan EL [43]0.81560.82580.50750.39890.90850.45950.56670.597737142
PickPocket [27]0.87150.84290.68490.60430.92250.67570.69440.637837142
SMM [72]0.92680.95080.76920.72660.96350.74070.80000.854827137
SMMPMBEC [25]0.91460.95860.73080.68080.95620.70370.76000.858127137
BVLSTM-MHC0.95480.95120.87500.84900.98320.83330.92110.911242179
CNN-NF [46]0.86060.85130.62340.54490.89080.70590.55810.638334174
MHCflurry [45]0.78340.75260.49460.36330.83520.56100.44230.456941176
MethodsACCAUCF1MCCSpecificitySensitivityPrecisionAUPR# Postive examples# Negative examples
ANN [44]0.88270.91660.68660.62050.95070.62160.76670.772637142
comblibsidney 2008 [71]0.74190.11410.00001.00000.00000.00000.15911646
NetMHCcons [42]0.88830.91690.72220.65280.93660.70270.74290.845737142
NetMHCpan [63]0.85470.90240.59380.51730.94370.51350.70370.747137142
NetMHCpan EL [43]0.81560.82580.50750.39890.90850.45950.56670.597737142
PickPocket [27]0.87150.84290.68490.60430.92250.67570.69440.637837142
SMM [72]0.92680.95080.76920.72660.96350.74070.80000.854827137
SMMPMBEC [25]0.91460.95860.73080.68080.95620.70370.76000.858127137
BVLSTM-MHC0.95480.95120.87500.84900.98320.83330.92110.911242179
CNN-NF [46]0.86060.85130.62340.54490.89080.70590.55810.638334174
MHCflurry [45]0.78340.75260.49460.36330.83520.56100.44230.456941176
Table 4

Performance of BVLSTM-MHC along with ten existent MHC class I predictors on independent MHCBN dataset

MethodsACCAUCF1MCCSpecificitySensitivityPrecisionAUPR# Postive examples# Negative examples
ANN [44]0.88270.91660.68660.62050.95070.62160.76670.772637142
comblibsidney 2008 [71]0.74190.11410.00001.00000.00000.00000.15911646
NetMHCcons [42]0.88830.91690.72220.65280.93660.70270.74290.845737142
NetMHCpan [63]0.85470.90240.59380.51730.94370.51350.70370.747137142
NetMHCpan EL [43]0.81560.82580.50750.39890.90850.45950.56670.597737142
PickPocket [27]0.87150.84290.68490.60430.92250.67570.69440.637837142
SMM [72]0.92680.95080.76920.72660.96350.74070.80000.854827137
SMMPMBEC [25]0.91460.95860.73080.68080.95620.70370.76000.858127137
BVLSTM-MHC0.95480.95120.87500.84900.98320.83330.92110.911242179
CNN-NF [46]0.86060.85130.62340.54490.89080.70590.55810.638334174
MHCflurry [45]0.78340.75260.49460.36330.83520.56100.44230.456941176
MethodsACCAUCF1MCCSpecificitySensitivityPrecisionAUPR# Postive examples# Negative examples
ANN [44]0.88270.91660.68660.62050.95070.62160.76670.772637142
comblibsidney 2008 [71]0.74190.11410.00001.00000.00000.00000.15911646
NetMHCcons [42]0.88830.91690.72220.65280.93660.70270.74290.845737142
NetMHCpan [63]0.85470.90240.59380.51730.94370.51350.70370.747137142
NetMHCpan EL [43]0.81560.82580.50750.39890.90850.45950.56670.597737142
PickPocket [27]0.87150.84290.68490.60430.92250.67570.69440.637837142
SMM [72]0.92680.95080.76920.72660.96350.74070.80000.854827137
SMMPMBEC [25]0.91460.95860.73080.68080.95620.70370.76000.858127137
BVLSTM-MHC0.95480.95120.87500.84900.98320.83330.92110.911242179
CNN-NF [46]0.86060.85130.62340.54490.89080.70590.55810.638334174
MHCflurry [45]0.78340.75260.49460.36330.83520.56100.44230.456941176
Close
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close

This PDF is available to Subscribers Only

View Article Abstract & Purchase Options

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Close