Skip to main content

Table 5 Results of the ablation study for model architecture w/o pretraining

From: AptaTrans: a deep neural network for predicting aptamer-protein interaction using pretrained encoders

Model setup

ROC-AUC

ACC

MCC

F1

AptaTrans

0.899

0.857

0.639

0.733

w/o FCS mining

0.893

0.851

0.627

0.708

w/ simple Encoders

0.879

0.850

0.583

0.677

w/ shallow CNN

0.832

0.819

0.537

0.658

  1. Bold indicates the highest scores
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us