Quantitative structure–activity relationships of chemical bioactivity toward proteins associated with molecular initiating events of organ-specific toxicity

Gadaleta, Domenico; Garcia de Lomana, Marina; Serrano-Candelas, Eva; Ortega-Vallbona, Rita; Gozalbes, Rafael; Roncaglioni, Alessandra; Benfenati, Emilio

doi:10.1186/s13321-024-00917-x

Table 2 Validation performance of the best models for each target associated with MIEs

From: Quantitative structure–activity relationships of chemical bioactivity toward proteins associated with molecular initiating events of organ-specific toxicity

AOP	Target	SEN ± st.dev	SPE ± st.dev	BA ± st.dev	MCC ± st.dev	AUC ± st.dev	#test	Method	Features
STE	AHR	0.93 ± 0.04	0.67 ± 0.08	0.80 ± 0.05	0.64 ± 0.09	0.86 ± 0.05	67	GB	Fingerprints
	PPARa	0.88 ± 0.02	0.84 ± 0.03	0.86 ± 0.01	0.70 ± 0.03	0.93 ± 0.01	588	BRF	DRAGON
	PPARg	0.88 ± 0.01	0.82 ± 0.04	0.85 ± 0.02	0.64 ± 0.03	0.93 ± 0.01	818	BRF	Fingerprints
	PXR	0.84 ± 0.04	0.83 ± 0.04	0.83 ± 0.03	0.67 ± 0.06	0.91 ± 0.02	124	XGB-SMOTE	CDDD-VSURF
CHO	BSEP	0.8 ± 0.12	0.75 ± 0.06	0.77 ± 0.06	0.42 ± 0.10	0.86 ± 0.06	59	BRF	DRAGON
CHO	MRP4	0.94 ± 0.06	0.19 ± 0.16	0.57 ± 0.08	0.23 ± 0.22	0.64 ± 0.10	25	BRF-SMOTE	DRAGON
CFD	ACHE	0.86 ± 0.01	0.83 ± 0.02	0.85 ± 0.01	0.67 ± 0.02	0.92 ± 0.01	1089	BRF	Fingerprints
	NMDA	0.88 ± 0.04	0.74 ± 0.07	0.81 ± 0.04	0.63 ± 0.07	0.89 ± 0.03	87	SVM-SMOTE	CDDD
	THRa	0.92 ± 0.03	0.90 ± 0.06	0.91 ± 0.03	0.81 ± 0.06	0.97 ± 0.02	91	BRF	CDDD
	THRb	0.75 ± 0.03	0.87 ± 0.03	0.81 ± 0.02	0.62 ± 0.04	0.89 ± 0.02	316	GB-SMOTE	DRAGON
	TTR	0.8 ± 0.08	0.76 ± 0.09	0.78 ± 0.05	0.57 ± 0.11	0.85 ± 0.05	46	XGB-SMOTE	CDDD-VSURF
	VGSC	0.89 ± 0.04	0.81 ± 0.07	0.85 ± 0.04	0.71 ± 0.08	0.92 ± 0.03	71	XGB	Fingerprints
NTC	BMP	0.89 ± 0.02	0.96 ± 0.07	0.92 ± 0.04	0.52 ± 0.06	0.97 ± 0.02	158	BRF	Fingerprints
	CYP26	0.85 ± 0.06	0.93 ± 0.14	0.89 ± 0.07	0.59 ± 0.11	0.94 ± 0.04	36	BRF	Fingerprints
	FGF	0.98 ± 0.04	0.66 ± 0.23	0.82 ± 0.12	0.72 ± 0.19	0.90 ± 0.10	21	SVM-RBF	DRAGON
	FGFR1	0.87 ± 0.02	0.82 ± 0.03	0.84 ± 0.02	0.65 ± 0.03	0.93 ± 0.01	699	BRF	Fingerprints
	FGFR2	0.9 ± 0.02	0.96 ± 0.03	0.93 ± 0.02	0.77 ± 0.04	0.98 ± 0.01	264	BRF	Fingerprints
	FGFR3	0.95 ± 0.01	0.79 ± 0.06	0.87 ± 0.03	0.70 ± 0.05	0.96 ± 0.01	373	BRF	Fingerprints
	FGFR4	0.87 ± 0.03	0.89 ± 0.06	0.88 ± 0.03	0.56 ± 0.05	0.94 ± 0.02	270	SVM-SMOTE	Fingerprints
	HDEAC	0.85 ± 0.02	0.86 ± 0.04	0.86 ± 0.02	0.61 ± 0.04	0.92 ± 0.01	475	BRF	Fingerprints
	SMO	0.88 ± 0.02	0.85 ± 0.17	0.87 ± 0.08	0.35 ± 0.08	0.89 ± 0.09	149	BRF	Fingerprints
	WNT	0.94 ± 0.06	0.75 ± 0.20	0.84 ± 0.10	0.72 ± 0.18	0.87 ± 0.10	21	MLP	CDDD-VSURF
KF	COX1	0.81 ± 0.03	0.79 ± 0.02	0.80 ± 0.02	0.57 ± 0.03	0.87 ± 0.01	477	BRF	DRAGON-VSURF
	ACE	0.80 ± 0.04	0.84 ± 0.09	0.82 ± 0.05	0.55 ± 0.08	0.89 ± 0.04	115	BRF	DRAGON
	AT1R	0.90 ± 0.02	0.92 ± 0.03	0.91 ± 0.02	0.81 ± 0.03	0.96 ± 0.01	263	BRF-SMOTE	Fingerprints

For each model, the performance and the number of test chemicals (#test) are reported as the average of 100 training-test splits. The standard deviation associated with each metric is also included. The best models were selected based on the highest average BA on the test set

Back to article page

ISSN: 1758-2946

Contact us

Submission enquiries: journalsubmissions@springernature.com

You are viewing the site in preview mode

Table 2 Validation performance of the best models for each target associated with MIEs

Journal of Cheminformatics

Contact us