Abstract Senescence is a cell-intrinsic tumour suppressive response. A one-two-punch cancer treatment strategy aims to induce senescence in cancerous cells before removing them with a senolytic. It is important to accurately recognise senescent cells to investigate the feasibility of such a treatment strategy and identify compounds that induce senescence in cancer. We focus specifically on the terminal brain cancer glioblastoma, firstly identifying senescent glioblastoma cells with conventional stains, before training a machine learning model to distinguish senescent cells using only a DAPI nuclear stain. To demonstrate how our method can aid drug discovery, we apply our pipeline to existing glioblastoma high-throughput phenotypic drug screening imaging data to identify compounds that induce senescence in glioblastoma and verify these predictions experimentally. Author Summary Damaged cells can enter a senescent cell state, in which they do not divide, but continue to interact with the environment around them. A novel potential cancer treatment strategy is to make tumor cells senescent, before removing senescent cancer cells with a targeted drug. To investigate this treatment strategy in the brain cancer glioblastoma, it is important to be able to accurately recognise senescent glioblastoma cells. As identifying senescent cells is challenging, we create a machine learning pipeline which can detect senescent glioblastoma cells in imaging data. We show that by applying our method to existing data we can discover compounds that induce senescence in glioblastoma. We verify our predictions by testing the compounds experimentally.

Machine learning recognises senescence in glioblastoma and discovers senescence-inducing compounds