Cellular senescence is a stress response with broad pathophysiological implications. Senotherapies can induce senescence to treat cancer or eliminate senescent cells to ameliorate aging and age-related pathologies. This research uses nuclear morphology features of senescent cells to create machine-learning classifiers accurately predicting senescence induced by various stressors in different cell types and tissues. These classifiers are used to characterize senolytics, screen for drugs selectively inducing senescence in cancer cells, and assess senolytic drug efficacy in mouse models of liver cancer, aging, and fibrosis, and in patients with fatty liver disease. The findings suggest that senescence classifiers can aid in detecting pathophysiological senescence and discovering and validating potential senotherapies.

Imanol Duran, Joaquim Pombo, Bin Sun, Suchira Gallage, Hiromi Kudo, Domhnall McHugh, Laura Bousset, Jose Efren Barragan Avila, Roberta Forlano, Pinelopi Manousou, Mathias Heikenwalder, Dominic J. Withers, Santiago Vernia, Robert D. Goldin, Jesús Gil