The bacteria in your gut may offer an accurate way to measure your biological age, according to a new study.
In recent years, it has become increasingly apparent that the communities of bacteria, fungi, and other microbes living in our gut, known as the microbiome, are likely involved in aging, particularly the chronic age-related inflammation that accompanies it.
Our gut bacteria appear to regulate all kinds of things, including digesting food, controlling the immune system, and producing a variety of vitamins, amino acids, and short-chain fatty acids essential for cellular function. In a very real sense, you might consider the gut and its community of beneficial bacteria as a factory churning out the supplies that the rest of the body needs.
However, even though the gut plays a role in so many processes, we still know relatively little about how the microbiome works, why it changes with age, and what an average one even looks like. During aging, in general, the bacterial diversity in the gut declines as do the numbers of beneficial bacteria.
In both humans and rodents, the composition of the gut microbiome is considerably different when comparing young and aged individuals, and, in humans, the microbiota of centenarians is different from that of frail, aged people with histories of cancer [1-2].
The microbiome aging clock
Researchers who have been busy studying the microbiome have recently published a preprint paper which shows that the gut microbiota might be an accurate aging biomarker that can calculate the age of a person within a few years .
Researcher Dr. Alex Zhavoronkov and his team at InSilico Medicine collected and studied gut bacteria samples from 1165 healthy people from a variety of geographic regions. The age ranges were 20-39, 40-59, and 60-90, with grouping making roughly a third of the total number of people involved in the study.
Next, the team used an artificial intelligence technique known as machine learning to analyze the sample data. To do this, they trained the system to recognize 95 species of bacteria in the sample images along with the age of the person that each sample came from; they did this for 90% of the total collected samples.
The final step was to give the system the remaining 10% of samples and ask it what age the person was for each sample based on its previous knowledge of the 90% of samples that it had already seen. The end result was the system was able to predict someone’s biological age within a 4-year margin of error.
The human gut microbiome is a complex ecosystem that both affects and is affected by its host status. Previous analyses of gut microflora revealed associations between specific microbes and host health and disease status, genotype and diet. Here, we developed a method of predicting the biological age of the host based on the microbiological profiles of gut microbiota using a curated dataset of 1,165 healthy individuals (1,663 microbiome samples). Our predictive model, a human microbiome clock, has an architecture of a deep neural network and achieves the accuracy of 3.94 years mean absolute error in cross-validation. The performance of the deep microbiome clock was also evaluated on several additional populations. We further introduce a platform for biological interpretation of individual microbial features used in age models, which relies on permutation feature importance and accumulated local effects. This approach has allowed us to define two lists of 95 intestinal biomarkers of human aging. We further show that this list can be reduced to 39 taxa that convey the most information on their host’s aging. Overall, we show that (a) microbiological profiles can be used to predict human age; and (b) microbial features selected by models are age-related.
The findings also identified 39 species of bacteria that appeared to be the most influential in determining the age of a person. We already know from previous studies some of the populations of bacteria that change during aging, and this new study helps to build on that understanding .
If the microbiome aging clock can be validated in follow-up studies using greater participant numbers with very wide geographic diversity, it could potentially become a valuable biomarker of aging. It could join such standards as telomere length, the epigenetic clock, and circulating biomarkers of various kinds.
Such a collection of biomarkers could potentially form the basis for a comprehensive panel that might then be used to measure the effectiveness of interventions that directly target the aging processes. A panel of accurate aging biomarkers would mean that scientists could conduct longevity research without having to wait for people to die to make reliable predictions about interventions.
Let us hope that the follow-up studies to validate this model happen soon and that the results are positive. Aging research has an urgent need for accurate biomarkers, so we will be following developments with interest and will bring you an update once there is more data published.
 Biagi E, Nylund L, Candela M, et al. Through ageing, and beyond: gut microbiota and inflammatory status in seniors and centenarians. PLoS One 2010; 5: e10667.
 Jeffery IB, Lynch DB, O’Toole PW. Composition and temporal stability of the gut microbiota in older persons. ISME J 2016; 10: 170–82.
 Galkin, F., Aliper, A., Putin, E., Kuznetsov, I., Gladyshev, V. N., & Zhavoronkov, A. (2018). Human microbiome aging clocks based on deep learning and tandem of permutation feature importance and accumulated local effects. bioRxiv, 507780.
 Odamaki, T., Kato, K., Sugahara, H., Hashikura, N., Takahashi, S., Xiao, J. Z., … & Osawa, R. (2016). Age-related changes in gut microbiota composition from newborn to centenarian: a cross-sectional study. BMC microbiology, 16(1), 90.