Skip to main content

Table 4 Model accuracies for the halogenases dataset. The highest-performing result for each level is indicated in bold

From: Comparative Assessment of Protein Large Language Models for Enzyme Commission Number Prediction

Method

Accuracy

 

level 1

level 2

level 3

level 4

CLEAN

1.000

0.972

0.944

0.944

ProteInfer

0.611

0.388

0.083

0.694

DNN ESM2 3B

0.917

0.917

0.500

0.805

DNN ESM1b

0.917

0.917

0.500

0.833

DNN ProtBERT

0.805

0.917

0.528

0.750

Models Ensemble

0.917

0.917

0.500

0.833

BLASTp

0.750

0.639

0.194

0.583

Models + BLASTp

0.917

0.917

0.555

0.833

  1. \(^a\) This assessment was performed based on the ground truth derived only from the manual curation in [16]
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us