Journal of Cheminformatics

Table 6 Performance of the models built on ChEMBL_22 and ChEMBL_23 data

From: Large scale comparison of QSAR and conformal prediction methods and their applications in drug discovery

Method	Model data	Prediction set	Model targets	Sensitivity	Specificity	CCR
QSAR	ChEMBL_23	ChEMBL_24	282	0.63	0.80	0.71
MCP_incl		ChEMBL_24	282	0.63	0.67	0.65
MCP_excl		ChEMBL_24	282	0.56	0.61	0.58
QSAR	ChEMBL_22	ChEMBL_23	282	0.64	0.84	0.74
QSAR		ChEMBL_24	282	0.60	0.81	0.71
MCP_incl		ChEMBL_23	282	0.61	0.72	0.66
MCP_incl		ChEMBL_24	282	0.61	0.67	0.64
MCP_excl		ChEMBL_23	282	0.56	0.68	0.62
MCP_excl		ChEMBL_24	282	0.54	0.61	0.57

MCP model results are given at 80% confidence level. MCP_incl and MCP_excl indicate the ‘both’ prediction class was included in the result calculation or was ignored, respectively

Back to article page

ISSN: 1758-2946

Contact us

Submission enquiries: journalsubmissions@springernature.com