Age-related conditions are the leading causes of death and healthcare costs. Retarding the ageing process would have enormous medical and financial benefits. A large number of genes and drugs extending lifespan in model organisms already exist, yet given long validation times, only a small fraction of them can be explored for humans clinical applications. Therefore, prioritizing drugs and gene targets is imperative. In this talk, I will present big data and machine learning approaches for predicting longevity genes and compounds, which we validated experimentally. I will also present integrative, multi-dimensional approaches that provide insights into longevity pathways and their role in age-related diseases. Overall, our data-driven approaches allow us to identify and prioritize further compounds with potential healthy longevity properties.