Discovery of senolytics using machine learning.

Cellular senescence is a stress response involved in ageing and diverse disease processes including cancer, type-2 diabetes, osteoarthritis and viral infection. Despite growing interest in targeted elimination of senescent cells, only few senolytics are known due to the lack of well-characterised molecular targets. Here, we report the discovery of three senolytics using cost-effective machine learning algorithms trained solely on published data. We computationally screened various chemical libraries and validated the senolytic action of ginkgetin, periplocin and oleandrin in human cell lines under various modalities of senescence. The compounds have potency comparable to known senolytics, and we show that oleandrin has improved potency over its target as compared to best-in-class alternatives. Our approach led to several hundred-fold reduction in drug screening costs and demonstrates that artificial intelligence can take maximum advantage of small and heterogeneous drug screening data, paving the way for new open science approaches to early-stage drug discovery.

Cytoplasmic innate immune sensing by the caspase-4 non-canonical inflammasome promotes cellular senescence.

Cytoplasmic recognition of microbial lipopolysaccharides (LPS) in human cells is elicited by the caspase-4 and caspase-5 noncanonical inflammasomes, which induce a form of inflammatory cell death termed pyroptosis. Here we show that LPS-mediated activation of caspase-4 also induces a stress response promoting cellular senescence, which is dependent on the caspase-4 substrate gasdermin-D and the tumor suppressor p53. Furthermore, we found that the caspase-4 noncanonical inflammasome is induced and assembled in response to oncogenic RAS signaling during oncogene-induced senescence (OIS). Moreover, targeting caspase-4 expression in OIS showed its critical role in the senescence-associated secretory phenotype and the cell cycle arrest induced in cellular senescence. Finally, we observed that caspase-4 induction occurs in vivo in mouse models of tumor suppression and ageing. Altogether, we are showing that cellular senescence is induced by cytoplasmic LPS recognition by the noncanonical inflammasome and that this pathway is conserved in the cellular response to oncogenic stress.