Approved research

Application of deep neural networks to human ageing biomarker development

Lay summary

Ageing is a complex process that has been observed in all biological systems at every level of organisation. Some anti-ageing interventions have been demonstrated life-extending effects in model organisms. However, the translation of these interventions in human clinical practice remains limited. The absence of comprehensive ageing biomarkers is one of the major impediments for the translation to the clinic. At the same time, multiple biomarkers proposed today are expensive and not as practically measurable (lack of the standardize assays and etc). The most accurate methods of calculating biological age are a subject of ongoing debate, and recent studies suggest that a suite of biomarkers, rather than any individual biomarker, constitute the most effective means of assessing the health status. It has also been shown that ageing biomarkers are population-specific, hence the age predicting models are needed to be trained upon population-specific data (Mamoshina et al., 2018). In this project, we aim to train the deep learning model (Deep Neural Networks) using UK Biobank datasets to validate the previously discovered biomarkers and to complete and complement the robust ageing biomarkers that may be easily targeted and measured. The developed biological age predicting measures will be based on the data, that most of the people already have, such as blood test and urine test, and electrocardiograms, and passive recordings, such as wearable devices. The results of the current research will lead to simple, minimally invasive, and affordable methods of tracking integrated biomarkers of ageing in humans. Mamoshina P, Kochetov K, Putin E, Cortese F, Aliper A, Lee WS, Ahn SM, Uhn L, Skjodt N, Kovalchuk O, Scheibye-Knudsen M, Zhavoronkov A / Population specific biomarkers of human aging: a big data study using South Korean, Canadian and Eastern European patient populations // J Gerontol A Biol Sci Med Sci. 2018