Table 4

Performance of different models trained using different encoding schemes on the fivefold cross-validation test. Values in bold indicate the best performance

RNA modification typeClassifiersSensitivity (%)Specificity (%)MCCAUROCAUROC01
m1ACNNENAC82.9790.000.5630.9280.0683
CNNOne-hot81.4590.000.5530.9300.0700
CNNRNA embedding75.8990.000.5170.9120.0636
DeepPromise84.1590.000.5710.9340.0710
RFENAC79.7690.000.5490.9230.0672
RFOne-hot77.2390.000.5310.9220.0650
RFRNA embedding74.5390.000.5860.9100.0628
SVMENAC74.8790.000.5100.8950.0582
SVMOne-hot64.5690.000.2400.8380.0438
SVMRNA embedding70.6690.000.4820.8890.0556
m6ACNNENAC53.3290.000.4660.8500.0338
CNNOne-hot53.9390.000.4710.8520.0342
CNNRNA embedding52.4590.000.4580.8450.0328
DeepPromise54.8790.000.4790.8570.0351
RFENAC30.4790.000.2600.7140.0207
RFOne-hot22.8890.000.1790.6500.0174
RFRNA embedding26.4190.000.2250.6960.0167
SVMENAC28.3990.000.2330.6970.0164
SVMOne-hot37.2590.000.3210.7540.0223
SVMRNA embedding36.6190.000.3150.7510.0218
RNA modification typeClassifiersSensitivity (%)Specificity (%)MCCAUROCAUROC01
m1ACNNENAC82.9790.000.5630.9280.0683
CNNOne-hot81.4590.000.5530.9300.0700
CNNRNA embedding75.8990.000.5170.9120.0636
DeepPromise84.1590.000.5710.9340.0710
RFENAC79.7690.000.5490.9230.0672
RFOne-hot77.2390.000.5310.9220.0650
RFRNA embedding74.5390.000.5860.9100.0628
SVMENAC74.8790.000.5100.8950.0582
SVMOne-hot64.5690.000.2400.8380.0438
SVMRNA embedding70.6690.000.4820.8890.0556
m6ACNNENAC53.3290.000.4660.8500.0338
CNNOne-hot53.9390.000.4710.8520.0342
CNNRNA embedding52.4590.000.4580.8450.0328
DeepPromise54.8790.000.4790.8570.0351
RFENAC30.4790.000.2600.7140.0207
RFOne-hot22.8890.000.1790.6500.0174
RFRNA embedding26.4190.000.2250.6960.0167
SVMENAC28.3990.000.2330.6970.0164
SVMOne-hot37.2590.000.3210.7540.0223
SVMRNA embedding36.6190.000.3150.7510.0218
Table 4

Performance of different models trained using different encoding schemes on the fivefold cross-validation test. Values in bold indicate the best performance

RNA modification typeClassifiersSensitivity (%)Specificity (%)MCCAUROCAUROC01
m1ACNNENAC82.9790.000.5630.9280.0683
CNNOne-hot81.4590.000.5530.9300.0700
CNNRNA embedding75.8990.000.5170.9120.0636
DeepPromise84.1590.000.5710.9340.0710
RFENAC79.7690.000.5490.9230.0672
RFOne-hot77.2390.000.5310.9220.0650
RFRNA embedding74.5390.000.5860.9100.0628
SVMENAC74.8790.000.5100.8950.0582
SVMOne-hot64.5690.000.2400.8380.0438
SVMRNA embedding70.6690.000.4820.8890.0556
m6ACNNENAC53.3290.000.4660.8500.0338
CNNOne-hot53.9390.000.4710.8520.0342
CNNRNA embedding52.4590.000.4580.8450.0328
DeepPromise54.8790.000.4790.8570.0351
RFENAC30.4790.000.2600.7140.0207
RFOne-hot22.8890.000.1790.6500.0174
RFRNA embedding26.4190.000.2250.6960.0167
SVMENAC28.3990.000.2330.6970.0164
SVMOne-hot37.2590.000.3210.7540.0223
SVMRNA embedding36.6190.000.3150.7510.0218
RNA modification typeClassifiersSensitivity (%)Specificity (%)MCCAUROCAUROC01
m1ACNNENAC82.9790.000.5630.9280.0683
CNNOne-hot81.4590.000.5530.9300.0700
CNNRNA embedding75.8990.000.5170.9120.0636
DeepPromise84.1590.000.5710.9340.0710
RFENAC79.7690.000.5490.9230.0672
RFOne-hot77.2390.000.5310.9220.0650
RFRNA embedding74.5390.000.5860.9100.0628
SVMENAC74.8790.000.5100.8950.0582
SVMOne-hot64.5690.000.2400.8380.0438
SVMRNA embedding70.6690.000.4820.8890.0556
m6ACNNENAC53.3290.000.4660.8500.0338
CNNOne-hot53.9390.000.4710.8520.0342
CNNRNA embedding52.4590.000.4580.8450.0328
DeepPromise54.8790.000.4790.8570.0351
RFENAC30.4790.000.2600.7140.0207
RFOne-hot22.8890.000.1790.6500.0174
RFRNA embedding26.4190.000.2250.6960.0167
SVMENAC28.3990.000.2330.6970.0164
SVMOne-hot37.2590.000.3210.7540.0223
SVMRNA embedding36.6190.000.3150.7510.0218
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