Discovery of moiety preference by Shapley value in protein kinase family using random forest models

BMC Bioinformatics

Table 1 Summary of the performance tables and collected data sets for 10 kinase families

Group	Family	Accuracy	Sensitivity	Specificity	MCC	No. of inhibitors	No. of non-inhibitor
TK	VEGFR	0.86 ± 0.06	0.73 ± 0.12	0.93 ± 0.06	0.68 ± 0.16	387	744
	PDGFR	0.92 ± 0.06	0.75 ± 0.22	0.94 ± 0.02	0.78 ± 0.17	150	499
	JAK	0.94 ± 0.02	0.95 ± 0.05	0.91 ± 0.03	0.86 ± 0.07	1551	874
	FGFR	0.9 ± 0.06	0.76 ± 0.13	0.93 ± 0.04	0.75 ± 0.13	263	584
AGC	AKT	0.94 ± 0.03	0.94 ± 0.06	0.95 ± 0.04	0.87 ± 0.08	391	768
	PKG	0.92 ± 0.07	0.62 ± 0.08	0.96 ± 0.02	0.6 ± 0.25	61	390
CAMK	PIM	0.92 ± 0.03	0.92 ± 0.06	0.91 ± 0.06	0.84 ± 0.07	766	617
	PKD	0.86 ± 0.09	0.56 ± 0.07	0.92 ± 0.04	0.63 ± 0.11	79	442
CMGC	CLK	0.8 ± 0.08	0.63 ± 0.08	0.89 ± 0.1	0.57 ± 0.06	201	392
	GSK	0.81 ± 0.07	0.57 ± 0.04	0.91 ± 0.05	0.59 ± 0.07	260	639

ISSN: 1471-2105