ACNNT3: Attention-CNN Framework for Prediction of Sequence-Based Bacterial Type III Secreted Effectors

Table 1

Comparison with mainstream deep-learning methods.

Method
ACNNT3	0.919	0.944	0.967	0.922	0.968
DenseNet	0.850	0.907	0.942	0.870	0.951
VGG16	0.846	0.892	0.934	0.847	0.937
ResNet	0.609	0.691	0.838	0.552	0.795
CNN	0.780	0.842	0.901	0.776	0.904
LSTM	0.875	0.933	0.959	0.909	0.961

The bold values indicate the best prediction results.