Skip to main content

Table 3 Fivefold cross-validation results (mean ± one standard deviation) of embedding layer module on the training set

From: pLMSNOSite: an ensemble-based approach for predicting protein S-nitrosylation sites by integrating supervised word embedding and embedding from pre-trained protein language model

Model

ACC

SN

SP

MCC

2D-CNN

0.688 ± 0.018

0.760 ± 0.063

0.615 ± 0.069

0.382 ± 0.034

ANN

0.658 ± 0.018

0.697 ± 0.0351

0.619 ± 0.010

0.318 ± 0.036

LSTM

0.674 ± 0.011

0.816 ± 0.067

0.533 ± 0.074

0.368 ± 0.024

ConvLSTM

0.667 ± 0.006

0.836 ± 0.023

0.498 ± 0.017

0.355 ± 0.017

BiLSTM

0.686 ± 0.009

0.747 ± 0.093

0.626 ± 0.083

0.380 ± 0.022

  1. The highest values in each category are bolded
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us