Table 1.

The structure of the summarized results of modeling. (ML: Machine learning algorithms, SR: train/test split ratio, expressed as the percentage of compounds assigned to the training set, NS: number of samples, NB: naïve Bayes, CV: cross-validation).

ML	SR	NS	Split	Performance Parameters
NB	50	100	CV	x1,1, …, x1,j
NB	60	100	CV
NB	70	100	CV
NB	80	100	CV
NB	50	500	CV
…	…	…	…	…
XGBoost	80	total	test	xi,1, …, xi,j