A DNA tool can assess the risk of disease by predicting the size of the person

Washington, Oct. 6 Scientists say they have developed a new DNA tool using machine learning to accurately predict the size of people and assess the risk of serious diseases such as heart disease and cancer.

The tool, or algorithm, builds predictors of human characteristics such as height, bone density and even the level of education that a person can achieve, based solely on his or her genome, according to the research published in the journal Genetics.

"While we have validated this tool for these three findings, we can now apply this method to predict other complex traits related to health risks such as heart disease, diabetes, and breast cancer," said Stephen Hsu of Michigan State University (MSU) in the US.

Other applications have the potential to significantly advance the practice of precision health, allowing doctors to intervene as early as possible in patient care and prevent or delay the disease, have said the researchers.

The research analyzed the complete genetic makeup of nearly 500,000 adults in the UK using machine learning, where a computer learns from data.

The computer accurately predicted the size of each to an inch or so.

Although the predictors of bone density and level of education were not as accurate, they were accurate enough to identify peripheral people who were at risk of having very low bone density associated with osteoporosis. or fight at school.

Traditional genetic tests typically look for a specific change in a person's genes or chromosomes that may indicate a higher risk of diseases such as breast cancer.

The Hsu model takes into account many genomic differences and builds a predictor based on tens of thousands of variations.

Using data from the UK Biobank, an international resource for health information, Hsu and his team applied the algorithm, evaluating the DNA of each participant and teaching them about the problem. computer to clear these distinct differences.

"The algorithm takes into account the genetic makeup and size of each person," Hsu said.

"The computer learns from each person and ultimately produces a predictor that can determine the height of their genome alone," Hsu said. SAR MRJ