Top

Machine learning technique may detect age-related muscle wasting

The technique predicts the biological age of a muscle and may help combat sarcopenia.

Scientists have developed a novel machine learning technique that predicts the biological age of a muscle and may help combat sarcopenia, the degenerative loss of skeletal muscle and its function.

Age-associated muscle wasting remains an important clinical challenge that impacts hundreds of millions of older adults.

It is associated with serious negative health outcomes such as falls, impaired standing balance, physical disability, and mortality.

Researchers from US-based artificial intelligence company, Insilico Medicine, developed a novel deep-learning based model that predicts the biological age of a muscle and can be used to estimate the relevant importance of the genetic and epigenetic factors driving this process within many age groups.

The research, published in the journal Frontiers in Genetics, explains one of the simple models for applying the age predictors developed using several machine learning techniques.

"We are working on multiple biomarkers using deep learning and including blood biochemistry, transcriptomics, and even imaging data to be able to track the effectiveness of the various interventions we are developing," said Polina Mamoshina, deep learning scientist at Insilico Medicine.

"We believe that the most effective anti-ageing therapy should be tissue-specific, so we focused on the development of tissue-specific biomarkers of ageing," said Mamoshina.

The scientists applied a state of the art signalling pathway analysis algorithm, iPANDA, to compare transcriptomic signatures of 'old' and 'young' tissues and utilised several machine learning methods to predict the age of samples based on their transcriptomic signatures.

Ultimately, the trained age predictors were used to identify tissue-specific ageing clocks, researchers said.

This combined data-driven approach demonstrates that age prediction models can become a powerful tool for identifying prospective targets for geroprotectors.

Next Story