Discovery of novel JAK1 inhibitors through combining machine learning, structure-based pharmacophore modeling and bio-evaluation

Table 2 Description of the evaluation metrics

Evaluation metric	Equation
Accuracy	\(\frac{TP + TN}{TP + FN + FP + TN}\)
Precision	\(\frac{TP}{TP + FP}\)
Recall	\(\frac{TP}{TP + FN}\)
F1-score	\(2\frac{PrecisionRecall}{Precision + Recall}\)
Mcc	\(\frac{TPTN-FPFN}{\sqrt{\left(TP + FP\right)\left(TP + FN\right)\left(TN + FP\right)\left(TN + FN\right)}}\)

TP true positives, the number of correctly predicted active, TN true negatives, the number correctly predicted inactive, FP false positives, the number of incorrectly predicted active, FN false negatives, the number of incorrectly predicted inactive

ISSN: 1479-5876