Introduction of rm2(rank) metric incorporating rank-order predictions as an additional tool for validation of QSAR/QSPR models

► Most of the commonly used validation metrics do not consider rank-order predictions. ► For rank-order predictions in QSAR, we introduce the new rm2(rank) metric. ► It exhibits lowest difference in ranking from the Spearman's rank correlation coefficient. ► The rm2(rank) metric may be used as an additional tool for validation of QSAR models.