Skip to main content

Table 1 Performance experiments of IC50 comparison of our method and existing methods

From: DeepAEG: a model for predicting cancer drug response based on data enhancement and edge-collaborative update strategies

Methods

PCC

SCC

RMSE

Ridge regression

0.780

0.731

2.386

MOLI

0.807 ± 0.007

0.797 ± 0.005

2.081 ± 0.005

CDRscan

0.872 ± 0.004

0.856 ± 0.002

1.941 ± 0.014

tCNNs

0.889 ± 0.015

0.879 ± 0.006

1.781 ± 0.004

DeepCDR

0.9190 ± 0.005

0.8949 ± 0.002

1.082 ± 0.004

DeepTTA

0.9217 ± 0.004

0.8949 ± 0.005

1.0569 ± 0.002

DeepAEG

0.9333 ± 0.006

0.9776 ± 0.005

0.9067 ± 0.002

  1. The best performance values obtained by the model are shown in bold. Three evaluation indexes, including PCC, SCC and RMSE, are selected to evaluate the robustness of the model. DeepAEG consistently achieves optimal performance compared to other past methods
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us