In silico prediction of rhabdomyolysis of compounds by self-organizing map and support vector machine

► A dataset of 303 compounds (including drugs) with diverse structures was collected. ► Molecular descriptors (1155) were calculated. ► Molecular descriptors (16) were selected to build the classification models. ► Two models can distinguish the compounds inducing and not inducing rhabdomyolysis. ► The fingerprints (ECFPs) reflecting the molecular structure features were analyzed.