Skip to main content

Table 2 RF and SOHN trained with ChEMBL data against the Merck test data

From: Avoiding hERG-liability in drug design via synergetic combinations of different (Q)SAR methodologies and data sources: a case study in an industrial setting

Statistical models (public)

ACC

BA

SENS

SPEC

PPV

NPV

MCC

KAPPA

RFChEMBL

0.74

0.57

0.26

0.88

0.37

0.81

0.16

0.15

SOHNChEMBL

0.73

0.66

0.54

0.78

0.42

0.86

0.30

0.29