Using machine learning models, the researchers identified three compounds that could fight aging. They say their method could be an effective way to identify new drugs, especially for complex diseases.
Cell division is necessary for the growth of our bodies and the self-renewal of tissues. Cellular senescence describes the phenomenon in which cells permanently stop dividing but remain in the body, leading to tissue damage and aging of body organs and systems.
Normally, senescent cells are cleared from the body by our immune system. However, as we age, our immune system becomes less efficient at clearing these cells and their numbers increase. Increases in senescent cells have been linked to cancer, diseases such as Alzheimer’s disease, and hallmarks of aging such as worsening vision and decreased mobility. Given the potentially harmful effects on the body, there has been a push to develop effective senescence drugs, compounds that clear senescent cells.
Previous studies have identified some promising senolytics, but they are often toxic to healthy cells. Now, a study led by researchers at the University of Edinburgh in Scotland has used a pioneering approach to find chemicals that can safely and effectively eliminate these defective cells.
They developed a machine learning model and trained it to identify key features of chemicals with aging properties. Model training data was drawn from multiple sources, including academic papers and commercial patents, and integrated with compounds from two existing chemical libraries containing various FDA-approved or clinical-stage compounds.
The full dataset contains 2,523 compounds, including those with antiaging and non-antiaging properties, so as not to bias the machine learning algorithm. The algorithm was then used to screen more than 4,000 chemicals, from which 21 potential candidates were identified.
After testing these candidates, the researchers found that three chemicals — ginkgoxanthin, ciprofloxacin and oleandrin — could remove senescent cells without harming healthy cells. Of the three, oleandrin was found to be the most effective. All three are natural products found in traditional herbal medicine.
Oleandrin is extracted from the oleander plant (Oleander) and has properties similar to digoxin, a drug used to treat heart failure and certain abnormal heart rhythms (arrhythmias). Studies have shown that oleandrin has anticancer, anti-inflammatory, anti-HIV, antibacterial, and antioxidant properties. Oleandrin has high toxicity beyond therapeutic levels, which is a very narrow window in humans, hindering its clinical application. Therefore, it has not been approved by regulatory agencies as a prescription drug or dietary supplement.
Like oleandrin, ginkgoxanthin has been shown to have anticancer, anti-inflammatory, antibacterial, antioxidant, and neuroprotective effects. Ginkgo biloba is extracted from Ginkgo biloba (Ginkgo biloba) tree, the oldest surviving tree species, whose leaves and seeds have been used as herbal medicine for thousands of years.highly concentrated Ginkgo biloba Extracts made from the dried leaves of the tree are available over the counter. It is one of the best-selling herbal supplements in the US and Europe.
Periplocin was isolated from the root bark of the Chinese silk vine (hedge hedge). Studies have shown that it improves heart function and stops cell growth and causes cancer cell death.
The researchers say their findings suggest that the compounds are as potent as or more potent than aging drugs described in previous studies. What’s more, they say, their machine-learning-based approach was so effective that it reduced the number of compounds that needed to be screened by more than 200-fold.
The researchers say their AI-based approach represents a milestone in identifying new drugs, especially for complex diseases.
“This study shows that artificial intelligence can be very effective in helping us identify new drug candidates, especially in the early stages of drug discovery and for diseases with complex biology or few known molecular targets,” said the study’s corresponding author Diego Oyarzún said.
They also say the approach is more cost-effective than standard drug screening methods such as preclinical and clinical trials.
“This work arose from a close collaboration between data scientists, chemists and biologists,” said Vanessa Smer-Barreto, lead author of the study. “Using the strengths of this interdisciplinary combination, we were able to build robust models and save screening costs by using only published data for model training. I hope this work will open up new ways to accelerate the application of this exciting technology.” Opportunity.”
The study was published in the journal natural communication.
source: University of Edinburgh