Skip to main content

Table 1 Performance comparison. “\(\uparrow\)” means the larger the value, the better; “\(\downarrow\)” means the smaller the value, the better. The standard deviation of the cross-validation results is calculated by the STDEVP function

From: NeRD: a multichannel neural network to predict cellular response of drugs by integrating multidimensional data

Method

\(CC_{p}\uparrow\)

\(R^{2}\uparrow\)

\(RMSE\downarrow\)

\(CC_{s}\uparrow\)

LR

0.234±0.0010

0.055±0.0004

0.171±0.0002

0.237±0.0011

SVR-L

0.232±0.0013

0.047±0.0012

0.172±0.0007

0.237±0.0008

SVR

0.469±0.0034

0.213±0.0065

0.153±0.0007

0.494±0.0051

RF

0.653±0.0355

0.419±0.0405

0.130±0.0056

0.606±0.0147

MLP

0.828±0.0029

0.698±0.0048

0.104±0.0007

0.800±0.0014

CNN

0.836±0.0026

0.700±0.0044

0.097±0.0008

0.807±0.0029

SRMF

0.837±0.0022

0.701±0.0037

0.097±0.0006

0.809±0.0018

VAE+MLP

0.830±0.0036

0.688±0.0060

0.098±0.0011

0.795±0.0031

DeepCDR

0.764±0.0147

0.572±0.0223

0.115±0.0032

0.676±0.0471

CDRScan

0.834±0.0039

0.696±0.0066

0.097±0.0008

0.810±0.0038

tCNNS

0.849±0.0039

0.721±0.0067

0.093±0.0010

0.822±0.0015

GraphDRP

0.848±0.0033

0.719±0.0057

0.093±0.0010

0.821±0.0020

NeRD

0.866\(\pm\)0.0027

0.750\(\pm\)0.0048

0.088\(\pm\)0.0007

0.839\(\pm\)0.0014