From: Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning
Feature extractor
Dataset
MCC
AUROC
AUPRC
ProtBert
SJC
0.352
0.856
0.354
ESM-2
0.535
0.917
0.564
UniProtSMB
0.488
0.922
0.498
0.704
0.961
0.750