As this open access paper notes, a great deal of the present work on developing biomarkers of aging involves machine learning. Researchers are sifting and arranging health metrics, blood markers, and epigenetic data to find combinations that predict risk of disease and mortality. The aim at the end of the day is to determine a good measure of biological age, one that accounts for all of the burden of cellular and molecular damage that leads to death and dysfunction, and will thus be a good, rapid measure of effectiveness for rejuvenation therapies. The biggest challenge in this line of work at the present time is that researchers don't have a good understanding of what exactly is being measured by many of these potential biomarkers. It is entirely plausible that they are only a measure of some types of the underlying damage of aging, and will thus be of no use in assessing many of the possible approaches to rejuvenation.

The recent hype cycle in artificial intelligence (AI) resulted in substantial investment in machine learning and increase in available talent in almost every industry and country. This wave of increased attention to AI was fueled by the many credible advances in deep learning that allowed machines to outperform humans in multiple tasks. The advantage of deep learning (DL) systems is in their ability to learn and generalize from a large number of examples. DL methods rapidly propagated into the many biomedical applications, starting primarily with the imaging, text, and genomic data. The availability of large volumes of data and new algorithms made it possible to use deep learning to start making predictions about the activity and pharmacological properties of small molecules, identify mimetics of the known geroprotectors, and discover new ones.

There are many biological features that demonstrated correlation with the chronological age such as telomere length, racemization of amino acids in proteins, and others. The epigenetic age predictors were proposed in 2011. But it was not until 2012 when the first epigenetic aging clock was published by Hannum. Hannum's group profiled the methylomes derived from peripheral blood samples of healthy individuals to develop the first epigenetic clock consisting of 71 CpG sites and demonstrated the root mean squared error of 4.9 years on independent data. A more precise and comprehensive multi-tissue aging clock was then published in 2013 by Horvath who coined the terms "DNAm clock" and "epigenetic aging clock" and rapidly gained popularity in the aging research community. Horvath used 353 CpG sites and achieved a median error of 3.6 years on the testing set. These clocks were developed using traditional machine learning approaches - notably linear regression with regularization and the use of a limited number of samples. Similar methylation aging clocks were developed for mice.

With the first deep-neural-network-based aging clocks published in 2016, significant progress has been made the past few years in deep learned biomarkers of human aging. The first DL clock was constructed using 41 blood test values of over 50,000 individuals. Making use of deep neural network abilities to capture nonlinear dependencies between input data and target variable, the initially proposed method was able to achieve mean absolute accuracy of 5.5 years on previously unseen 12,000 individuals. Additionally, this study demonstrated how the deep clock can be used for further interpretations of relations between aging and blood parameters. By employing feature importance analysis they identified top parameters related to age changes.

The deep biomarkers of aging and longevity have a broad range of applications in research and development, medical, insurance, and many other areas. Developing comprehensive granular multi-modal aging clocks will help obtain a better understanding of the aging processes, establish causal relationships, and identify preventative and therapeutic interventions. One of the many promising applications of the deep aging clocks built into the generative adversarial networks is generation of synthetic biological data with age as a generation condition. The deep aging clock research is expected to increase in popularity.

Link: https://doi.org/10.18632/aging.102475