Skip to main content

Table 8 The accuracy and Matthew’s correlation coefficient of DistDom, FUPred, and DeepDom of classifying single-domain and multi-domain proteins in the CASP14 dataset with the confidence interval reported with 95% confidence

From: Multi-head attention-based U-Nets for predicting protein domain boundaries using 1D sequence features and 2D distance maps

Model

Accuracy

MCC

DistDom

0.759 (0.729, 0.788)

0.499 (0.434, 0.565)

FUPred

0.670 (0.654, 0.686)

0.328 (0.295, 0.363)

DeepDom

0.393 (0.376, 0.410)

0.052 (− 0.001, 0.106)

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us