Google’s DeepMind unit has used artificial intelligence (AI) to catalogue millions of ‘missense’ mutations in human DNA that could be related to the development of genetic diseases.
Developed by DeepMind researchers as an extension of its AlphaFold database, the AlphaMissense AI tool has classified the effects of 71 million missense mutations and categorised 89% of them as either ‘likely’ or ‘unlikely’ to be linked to human diseases.
The AlphaFold database was originally released in 2021 and is freely used by researchers worldwide to predict the three-dimensional structures of the human proteome.
Around 350 million people worldwide are living with rare disorders, approximately 80% of which are genetic in origin, including AA amyloidosis, Adrenoleukodystrophy and Ehlers-Danlos syndrome.
Missense variants, which are genetic mutations affecting the structure and function of human proteins, can lead to diseases such as cystic fibrosis, sickle-cell anaemia or cancer.
In previous studies, scientists have only been able to categorise around 0.1% of missense mutations, and only 6% of them have been studied.
On average, a person carries over 9,000 missense variants, therefore, classifying them is important to understanding what can develop to diseases.
By utilising the AlphaMissense catalogue, which is also freely-available, and the AlphaFold database, research into molecular biology could be accelerated by understanding how harmful missense mutations can cause disease, potentially forming the basis of research into diagnostics and treatments.
DeepMind’s research scientists, Žiga Avsec and Jun Cheng, wrote: “With millions of possible mutations and limited experimental data, it’s largely still a mystery which ones could give rise to disease.”
They added: “Experiments to uncover disease-causing mutations are expensive and laborious – every protein is unique, and each experiment has to be designed separately, which can take months.
“By using AI predictions, researchers can get a preview of results for thousands of proteins at a time, which can help to prioritise resources and accelerate more complex studies.”