Research Article

BERT-PPII: The Polyproline Type II Helix Structure Prediction Model Based on BERT and Multichannel CNN

Table 2

The dataset under less strict definition (NonStrict_data).

DatasetNumber of sequenceNumber of PPIINumber of non-PPIITotal

Training set71216449015541421618432
Test set178115880379276395156
Independent test set10018639208785217424