Help us: Donate
Follow us on:
×

Developing Deep Aging Biomarkers Using Artificial Intelligence

Share

A type of artificial intelligence technique is now being used to develop new drugs and therapies and could perhaps even help to solve aging.

An urgent need for aging biomarkers

There has long been an urgent need in our field to develop increasingly accurate biomarkers of aging so that the efficacy of interventions can be gauged. Deep learning is one of the more recent techniques being applied in the search for aging biomarkers.

Deep learning is a subset of the wider family of machine learning methods based on artificial neural networks. The technique is being used to develop deep age predictors that have the potential to help speed up research progress by establishing causal relationships in nonlinear systems.

The resulting so-called “deep aging clocks” could potentially be used to identify potential targets for therapeutic interventions and determine the efficacy of said interventions, and they may help predict future health trajectories of patients. Such a deep aging clock could potentially highlight potential health issues years down the road, thus allowing preventative measures to be taken much earlier and making positive health outcomes more likely. It could also be useful in seeing if interventions that target the aging processes directly have worked or not, which is critical if our field is to progress and translate therapies to humans in the coming decades.



A team of researchers, including Dr. Alex Zhavoronkov of Insilico Medicine, has published a review paper that gives an overview of the current state of research in regards to deep aging clocks and how their evolution has significant implications for the development of new drugs and interventions.

Understanding how to stay healthier with age

As humans, our lifecycle, like most other animals, is one of climbing a peak, reaching the summit, and then sliding into decline as aging takes its toll. In general, the optimal age where most of us are at our physical peak is somewhere between 20-30 years of age.

We often hear the phrase “healthy aging”, but that term is an oxymoron; aging is inherently bad for an organism. However, there are certainly ways that we can speed up or potentially slow down the rate at which we experience aging. Lifestyle factors such as diet, smoking, drinking, and other behaviors can modify the trajectory and the rate at which we peak and decline, or, in other words, how healthy we remain as we age.



Deep aging clocks could potentially allow us to understand the differences between people remain more healthy while aging compared to those who do not. As there is a myriad of potential factors that influence this rate of aging, deep learning is ideally suited to the task, as it is able to handle a vast array of variables and confounding factors in a way that only this sort of algorithm can. Using deep learning, it could be possible to develop a comprehensive panel of aging biomarkers to accurately assess a person’s biological age and likely rate of aging.

Multiple recent advances in machine learning enabled computer systems to exceed human performance in many tasks including voice, text, and speech recognition and complex strategy games. Aging is a complex multifactorial process driven by and resulting in the many minute changes transpiring at every level of the human organism. Deep learning systems trained on the many measurable features changing in time can generalize and learn the many biological processes on the population and individual levels. The deep age predictors can help advance aging research by establishing causal relationships in non-linear systems. Deep aging clocks can be used for identification of novel therapeutic targets, evaluating the efficacy of the various interventions, data quality control, data economics, prediction of health trajectories, mortality, and many other applications. Here we present the current state of development of the deep aging clocks in the context of the pharmaceutical research and development and clinical applications.

Conclusion

As has been said many times, there is an urgent need for accurate aging biomarkers, and if deep learning allows the creation of efficient deep aging clocks, then it will result in a positive development for the field. One of the key challenges in developing and getting therapies that directly target the aging processes in order to prevent, delay, or even reverse age-related diseases is the creation of suitable biomarkers for clinical trials; hopefully, deep aging clocks will give us the tools we need.



Literature

[1] Zhavoronkov, A., Li, R., Ma, C., & Mamoshina, P. (2019). Deep biomarkers of aging and longevity: from research to applications. Aging, 11.

About the author

Steve Hill

Steve serves on the LEAF Board of Directors and is the Editor in Chief, coordinating the daily news articles and social media content of the organization. He is an active journalist in the aging research and biotechnology field and has to date written over 500 articles on the topic, interviewed over 100 of the leading researchers in the field, hosted livestream events focused on aging, as well as attending various medical industry conferences. His work has been featured in H+ magazine, Psychology Today, Singularity Weblog, Standpoint Magazine, Swiss Monthly, Keep me Prime, and New Economy Magazine. Steve has a background in project management and administration which has helped him to build a united team for effective fundraising and content creation, while his additional knowledge of biology and statistical data analysis allows him to carefully assess and coordinate the scientific groups involved in the project.
No Comments
Write a comment:

*

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.

You have 3 free articles remaining this week. You can register for free to continue enjoying the best in rejuvenation biotechnology news. Already registered? Login here.