Journal of Cheminformatics

Table 3 Overall predictivity of the linear models produced for CS1

From: QSAR-Co-X: an open source toolkit for multitarget QSAR modelling

Classification^a	FS-LDA			SFS-LDA
Classification^a	Str^d	Ts^e	Vd^f	Str^d	Ts^e	Vd^f
TP	332	77	110	333	77	110
TN	102	32	36	106	33	36
FP	9	3	8	5	2	8
FN	9	2	6	8	2	6
Sn (%)	91.89	91.43	81.82	95.49	94.29	81.82
Sp (%)	97.36	97.47	94.83	97.65	97.47	94.83
Acc (%)	96.02	95.61	91.25	97.12	96.49	91.25
F1 score (%)	97.36	96.85	94.02	98.08	97.47	94.02
MCC^b	0.892	0.896	0.778	0.923	0.917	0.778
AUROC^c	0.946	0.944	0.883	0.966	0.959	0.883

The most significant results are highlighted in bold
^aTP: True positive, TN: True negative, FP: False positive, FN: False negative, Sn: Sensitivity, Sp: Specificity, Acc: Accuracy.
^bMatthews correlation coefficient.
^cScore for the area under the receiver operating characteristic curve.
^dSub-training set.
^eTest set.
^fValidation set

Back to article page

ISSN: 1758-2946

Contact us

Submission enquiries: journalsubmissions@springernature.com