MechanoAge, a machine learning platform to identify individuals susceptible to breast cancer based on mechanical properties of single cells

Existing breast cancer risk models inadequately identify individuals at latent risk, particularly among women without known genetic mutations or family history. Risk is often underestimated or overestimated due to reliance on population-level data and neglect of cellular aging and mechanobiological alterations. We profiled primary human mammary epithelial cells (HMECs) from women of varying ages and risk backgrounds using mechano-node-pore sensing (mechano-NPS), a high-throughput microfluidic platform that captures single-cell mechanical properties. Using machine learning, we developed a classifier, MechanoAge, to predict age-related mechanical phenotypes and introduce a novel index, mechano-RISQ, to quantify deviations linked to breast cancer risk. We further assessed the cytoskeletal protein keratin 14 (KRT14) as a molecular mediator of these mechanical states through overexpression and knockdown experiments. Cells from younger women carrying BRCA1/2 mutations or with a family history of breast cancer exhibited accelerated mechanical aging compared to age-matched controls. Elevated mechano-RISQ scores reflected an increased proportion of cells with “older” mechanical profiles. KRT14 overexpression induced an aged mechanical phenotype in younger cells, while knockdown partially reversed this state in older cells. CyTOF profiling and modeling showed KRT14 modulation impacted protein expression signatures associated with aging and risk, particularly in luminal cells. Mechanical properties of breast epithelial cells reflect biologic aging and cancer susceptibility. Mechano-RISQ offers a new approach for identifying individuals at elevated risk, especially among average-risk populations, and may complement existing risk models by incorporating biophysical measures of epithelial aging.