SMILES-based QSAR virtual screening to identify potential therapeutics for COVID-19 by targeting 3CLpro and RdRp viral proteins

Bazzi-Allahri, Faezeh; Shiri, Fereshteh; Ahmadi, Shahin; Toropova, Alla P.; Toropov, Andrey A.

doi:10.1186/s13065-024-01302-3

Table 3 the statistical properties of the inhibitor activity classification models of 3CL^Pro that were generated through the Monte Carlo method optimization for ten random splits

From: SMILES-based QSAR virtual screening to identify potential therapeutics for COVID-19 by targeting 3CL^pro and RdRp viral proteins

Split	Set	n	Sensitivity	Specificity	Accuracy	MCC
\(Inhibitory \,activity=- 1.2754379 (\pm 0.0016968) + 0.0549150(\pm 0.0000625){\times}DCW\left({1,25}\right)\)
1	Training	339	0.9917	0.9916	0.9916	0.9813
	Invisible training	368	0.9865	1	0.9948	0.9891
	Calibration	230	0.9444	0.9778	0.9644	0.9258
	Validation	231	0.8269	0.9701	0.9375	0.8739
\(Inhibitory \,activity=- 0.7655690 (\pm 0.0011840) +0.0538805(\pm 0.0000561){\times}DCW\left({1,22}\right)\)
2	Training	342	0.9835	1	0.9943	0.9874
	Invisible training	358	0.9733	1	0.9893	0.9778
	Calibration	233	0.9231	0.9574	0.944	0.8823
	Validation	235	0.9216	0.9933	0.9643	0.9266
\(Inhibitory \,activity=- 0.4847983 (\pm 0.0012123) +0.0509742 (\pm 0.0000518){\times}DCW\left({1,23}\right)\)
3	Training	354	0.9789	1	0.992	0.983
	Invisible training	341	1	0.9907	0.9938	0.9862
	Calibration	238	0.9541	0.9865	0.9728	0.9443
	Validation	235	0.8962	0.9533	0.9297	0.8547
\(Inhibitory \,activity=-0.5277815 (\pm 0.0011310) +0.0588772 (\pm 0.0000562){\times}DCW\left({1,25}\right)\)
4	Training	338	0.9778	1	0.9915	0.982
	Invisible training	339	0.9291	0.9811	0.9617	0.918
	Calibration	254	0.9072	0.9554	0.937	0.8662
	Validation	237	0.9029	0.9254	0.9156	0.8283
\(Inhibitory \,activity=-0.8095880 (\pm 0.0012977) +0.0540050 (\pm 0.0000485) {\times}DCW\left({1,22}\right)\)
5	Training	341	0.9416	1	0.9765	0.9519
	Invisible training	351	0.9568	0.9623	0.9601	0.9169
	Calibration	239	0.9375	0.965	0.954	0.9041
	Validation	237	0.9271	0.9149	0.9198	0.8358
\(Inhibitory \,activity=-0.5912367 (\pm 0.0010215) +0.0665357 (\pm 0.0000581) {\times}DCW\left({1,22}\right)\)
6	Training	336	0.9638	0.9956	0.9835	0.9659
	Invisible training	336	0.9481	0.9851	0.9702	0.9381
	Calibration	232	0.8969	0.9481	0.9267	0.8491
	Validation	237	0.9082	0.8849	0.8945	0.7862
\(Inhibitory \,activity=-0.8271686 (\pm 0.0011930) +0.0657067 (\pm 0.0000743) {\times}DCW\left({1,17}\right)\)
7	Training	344	0.9593	0.991	0.9797	0.9556
	Invisible training	338	0.9403	0.9804	0.9645	0.9257
	Calibration	250	0.9048	0.9517	0.932	0.8601
	Validation	236	0.9151	0.9692	0.9449	0.889
\(Inhibitory \,activity=-0.5998361 (\pm 0.0012035) +0.0646588 (\pm 0.0000541){\times}DCW\left({1,22}\right)\)
8	Training	363	0.9625	0.9951	0.9807	0.9611
	Invisible training	348	0.9638	0.9905	0.9799	0.958
	Calibration	242	0.8974	0.9329	0.9215	0.8224
	Validation	215	0.9457	0.9431	0.9442	0.8865
\(nhibitory \,activity=-0.6242973 (\pm 0.0012742) +0.0663009 (\pm 0.0000696){\times}DCW\left({1,22}\right)\)
9	Training	338	0.9242	0.9854	0.9615	0.9193
	Invisible training	336	0.9398	0.9901	0.9702	0.938
	Calibration	246	0.9439	0.9424	0.9431	0.8846
	Validation	248	0.8854	0.9211	0.9073	0.805
\(Inhibitory \,activity=-0.7964906 (\pm 0.0012467) + 0.0613058 (\pm 0.0000611){\times}DCW\left({1,22}\right)\)
10	Training	341	0.938	0.9906	0.9707	0.9378
	Invisible training	338	0.9771	0.9807	0.9793	0.9565
	Calibration	235	0.8641	0.9621	0.9191	0.8368
	Validation	254	0.7714	0.9597	0.8819	0.7587

Back to article page

ISSN: 2661-801X

Contact us

General enquiries: journalsubmissions@springernature.com

BMC Chemistry

Contact us