Table 1.

Metrics comparison of 35 different ML regression models. Models were compared on the basis of their performance to predict MIC values of three antibiotics on test datasets.

	Names of models used	Ciprofloxacin		Cefixime		Azithromycin
		RMSE	R2	RMSE	R2	RMSE	R2
1	ADABoostRegressor	13.61701	0.12067	0.04143	0.66328	6.28431	0.14474
2	ADARegressor	9.58793	0.62305	0.04086	0.76301	1.61560	0.78313
3	BaggingRegressor	6.10417	0.69089	0.04038	0.67140	1.37854	0.7369
4	BayesianRidge	6.06775	0.69462	0.03931	0.68590	1.54538	0.70676
5	CATBoostRegressor	3.87531	0.77393	0.03807	0.74570	1.40781	0.79317
6	DecisionTreeRegressor	7.82284	0.54359	0.04396	0.61863	1.91145	0.66770
7	DummyRegressor	9.12458	0.31455	0.07010	1.2696e-32	2.84645	−0.00093
8	ElasticNet	7.39072	0.58821	0.07011	1.8281e-19	2.72904	0.65383
9	ElasticNetCV	0.03914	0.68890	0.68433	0.68433	1.51770	0.71596
10	ExtraTreeRegressor	8.01472	0.53616	0.04531	0.59814	1.81783	0.68063
11	ExtraTreesRegressor	0.04073	0.66861	0.04373	0.62071	1.75033	0.70090
12	GaussianProcessRegressor	0.04942	0.68436	0.04259	0.65792	1.99184	0.54625
13	GradientBoostingRegressor	6.02614	0.70108	0.03914	0.68890	1.44105	0.74478
14	HistGradientBoostingRegressor	5.71240	0.73384	0.03816	0.70486	1.35686	0.77633
15	HuberRegressor	6.68917	0.65186	0.04073	0.66861	1.59841	0.68702
16	KNeighborsRegressor	0.08358	0.63807	3.49214	0.63424	1.21033	0.71268
17	KernelRidge	9.60091	0.46778	0.03990	0.67779	1.62867	0.68134
18	LarsCV	9.51242	0.45764	0.04045	0.66715	1.55067	0.70463
19	Lasso	7.58347	0.57166	0.07010	1.883e-15	2.84645	0.73652
20	LassoCV	8.64752	0.54124	0.03942	0.68436	1.50917	0.71937
21	LassoLarsCV	0.03989	0.67792	0.04104	0.65787	1.52546	0.71292
22	LassoLarsIC	6.72328	0.63309	0.04039	0.66812	1.53725	0.70890
23	LinearRegression	8.41567	0.54621	0.34524	0.01717	1.76178	0.64022
24	MLPRegressor	6.61081	0.68461	0.05356	0.53807	1.57986	0.73443
25	NuSVR	7.65251	0.58619	0.03863	0.69966	2.20857	0.66841
26	OrthogonalMatchingPursuit	11.75760	0.31796	0.03991	0.67679	1.55638	0.70262
27	OrthogonalMatchingPursuitCV	6.73327	0.62534	0.04989	0.66592	1.54569	0.70547
28	PoissonRegressor	6.10017	0.69149	0.06490	0.58745	2.30000	0.46240
29	RandomForestRegressor	2.69214	0.77241	0.04104	0.75787	1.33418	0.79009
30	Ridge	9.60075	0.46806	0.03989	0.67792	1.62883	0.68132
31	RidgeCV	6.79794	0.64527	0.03931	0.68599	1.53935	0.70838
32	SGDRegressor	4.29214	0.68241	0.04483	0.67187	1.82504	0.70766
33	SVR	7.71597	0.58373	0.07486	0.57187	2.21276	0.66886
34	XGBoostRegressor	6.01090	0.70446	0.03859	0.79708	1.44787	0.76031
35	XGBoostRFRegressor	5.81138	0.72186	0.44421	0.68538	1.47658	0.73711

RMSE: root mean square error, R²: Coefficient of determination, NuSVR: Nu Support Vector Regression, SVR: Support Vector Regression.