The effects of aging on the human brain could potentially be slowed down with the help of artificial intelligence.
Machine learning algorithms that can predict the biological age of brain cells have helped scientists identify hundreds of potential anti-aging treatments to prevent age-related cognitive decline and neurodegeneration.
“Aging is the main risk factor for several neurodegenerative diseases that most older people eventually face,” said the researchers, led by Antonio del Sol, professor of computational biology at the Luxembourg Center for Systems Biomedicine (LCSB) and research professor at CIC bioGUNE in Spain. “The world’s population is aging rapidly, with more than 2 billion people predicted to be over 60 years of age by 2050. Therefore, it is important to find effective strategies to protect the aging population from neurodegeneration.”
To train the machine learning model, the team collected data from brain samples of 778 healthy individuals ranging in age from 20 to 97 years. Rather than looking at the genetic code, this model focuses on the transcriptome (the collection of RNA molecules transcribed from DNA) to measure the activity level of each gene in each brain sample.
The algorithm identified 365 gene transcripts that can accurately predict a person’s age to within five years from a brain sample. Only 25% of these genes were directly involved in brain processes. Instead, most of them are related to DNA repair and regulation, which are known to be closely associated with aging across all tissues.
In a sample of patients diagnosed with neurodegenerative diseases such as Alzheimer’s disease or traumatic brain injury, this “aging clock” model predicted that their brains were significantly older in biological age.
“This was particularly pronounced in samples taken from donors between 60 and 70 years old, with the age of transcription in neurodegenerative samples being 15 years older than in healthy individuals,” Dr. del Sol reported. “These findings show that transcriptional age is negatively correlated with brain function and support the view that neurodegeneration is a form of accelerated aging.”
The machine learning model then analyzed data from thousands of neuron and neural progenitor cell samples, looking for changes in gene expression that would reduce the sample’s predicted age. This allowed the computer algorithm to find 478 drugs that had a rejuvenating effect on brain cells.
“Although some compounds predicted by our model have been shown to extend lifespan, the majority have not been studied from a health or lifespan extension perspective,” del Sol added. “Furthermore, many of the predicted compounds are still in the experimental stage and their mechanisms of action remain unknown.”
The research team selected three compounds identified by the algorithm and tested their effects on old mice over a four-week period. Treatment with the three compounds significantly reduced anxiety, improved memory, and shifted brain cell gene expression toward a younger transcriptional profile in mice.
Although these preliminary results show promise, further research is needed to validate the effects of these and other compounds identified by the machine learning model. The goal is to one day develop drugs with powerful anti-aging and neuroprotective effects.
Del Sol and colleagues say the anti-aging field currently lacks a systematic drug discovery approach, making computer algorithms a valuable resource for identifying promising therapeutic compounds.
“Our computational platform provides a valuable resource for identifying interventions that have the potential to counter age-related declines in brain function,” del Sol concluded. “The hundreds of compounds predicted by our platform require validation across diverse multiple biological systems to assess their efficacy, providing extensive opportunities for future research and therapeutic development.”
Featured image credit: Michele Henderson from Unsplash
