Clinical laboratories could soon have new tests for determining how fast a patient’s digestive system is aging as part of a precision medicine treatment protocol
When it comes to assessing human age and longevity, much research has focused on telomeres in recent years. Now clinical laboratory managers and pathologists will be interested to learn that provocative new research demonstrates that the human microbiome may also contain useful information about aging. Microbes that can be diagnostic biomarkers may be one result of this research.
From preventing weight loss to improving cancer treatments to stopping aging, human microbiome—especially gut bacteria—are at the heart of many near miraculous discoveries that have greatly impacted clinical pathology and diagnostics development. Dark Daily has reported on so many recent studies and new diagnostic tools involving human gut bacteria it’s a wonder there’s anything left to be discovered. Apparently, however, there is!
Using artificial intelligence (AI) and deep-learning algorithms, researchers at Insilico Medicine in Rockville, Md., have developed a method involving gut bacteria that they say can predict the age of most people to within a few years. Located at Johns Hopkins University, Insilico develops “artificial intelligence for drug discovery, biomarker development, and aging research” notes the company’s website.
According to a paper published on bioRxiv, an online biomedical publications archive operated by Cold Spring Harbor Laboratory, the Insilico scientists have “developed a method of predicting [the] biological age of the host based on the microbiological profiles of gut microbiota” as well an “approach [that] has allowed us to define two lists of 95 intestinal biomarkers of human aging.”
Clinical Laboratories Might Be Able to Use AI and Gut Bacteria to Predict Age
To perform the study, the researchers collected 3,663 gut bacteria samples from 10 publicly available data sets containing age metadata and then analyzed the samples using a machine learning algorithm. The samples originated from 1,165 healthy individuals who were between the ages of 20 and 90. The individuals used for the study were from Austria, China, Denmark, France, Germany, Kazakhstan, Spain, Sweden, and the US.
The researchers divided the samples equally among three age groups:
- 20 to 39 years old (young);
- 40 to 59 years old (middle aged); and,
- 60 to 90 years old (old).
The samples were then randomly separated into training and validation sets with 90% of the samples being used for training and the remaining 10% making up the validation set.
The scientists trained a deep neural network regressor to predict the age of the sample donors by looking at 95 different species of bacteria in the microbiome of the 90% training set. The algorithm was then asked to predict the ages of the remaining 10% of the donors by looking only at their gut bacteria.
They discovered that their computer program could accurately predict an individual’s age within four years based on their microbiome. They also were able to determine that 39 of the 95 species of bacteria examined were most beneficial in predicting a person’s age.
In addition, the researchers found that certain bacteria in the gut increase with age, while other bacteria decrease as people age. For example, the bacterium Eubacterium hallii, which is associated with metabolism in the intestines, was found to increase with age. On the other hand, one of the most plentiful micro-organisms in the gut, Bacteroides vulgatus, which has been linked to ulcerative colitis, decreases with age.
Understanding Microbiome’s Link to Disease
The human microbiome consists of trillions of cells including bacteria, viruses, and fungi, and its composition varies from individual to individual. Scientific research, like that being conducted at Insilico Medicine, expands our understanding of how gut bacteria affects human health and how diseases such as inflammatory bowel disease, arthritis, autism, and obesity, are linked to the microbiome.
This type of research could be used to determine how the microbiomes of people living with certain illnesses deviate from the norm, and possibly reveal unique and personalized ways to create healthier gut bacteria. It also could help researchers and physicians determine the best interventions, drugs, and treatments for individual patients dealing with diseases related to aging. Such advancements would be a boon to precision medicine.
“Age is such an important parameter in all kinds of diseases. Every second we change,” Zhavoronkov told Science. “You don’t need to wait until people die to conduct longevity experiments.”
Further research is needed to develop these findings into diagnostic tests acceptable for use in patient care. However, such tests could provide microbiologists and clinical laboratories with innovative tools and opportunities to help physicians diagnose patients and make optimal treatment decisions.