Elmadani M, Khan S, Tenhunen O, et al. - Given an unmet need for methods to predict cardiotoxicity associated with the treatment of cancer patients with some of the kinase inhibitors (KIs), researchers used a new computational method to recognize protein kinases important for cardiomyocyte viability. In cultured neonatal cardiomyocytes, they screened 140 KIs for their toxicity. They used a new machine learning method for target deconvolution that merges the information from the toxicity screen and from the kinase profiling assays, to determine the principal kinases mediating the toxicity of KIs to cardiomyocytes. Phosphoinositide 3-kinase catalytic subunit alpha, mammalian target of rapamycin, and insulin-like growth factor 1 receptor were discovered as top kinases, using the model. The knockdown of the individual kinases in cardiomyocytes corroborated their role in regulating cardiomyocyte viability. In this study, a new method to predict cardiomyocyte toxicity of KIs is proposed by integrating the data from examination of KI toxicity on cardiomyocytes and KI target profiling.