Researchers have adapted the AI network to search for genetic changes linked to ill health
Google DeepMind has wielded its revolutionary protein-structure-prediction AI in the hunt for genetic mutations that cause disease.
Many of the genetic mutations that directly cause a condition, such as those responsible for cystic fibrosis and sickle-cell disease, tend to change the amino acid sequence of the protein they encode. But researchers have observed only a few million of these single-letter ‘missense mutations’. Of the more than 70 million possible in the human genome, only a sliver have been conclusively linked to disease, and most seem to have no ill effect on health.
AlphaMissense also incorporates a type of neural network inspired by large language models like ChatGPT that has been trained on millions of protein sequences instead of words, called a protein language model. These have proven adept at predicting protein structures and designing new proteins. They are useful for variant prediction because they have learned which sequences are plausible and which are not, Žiga Avsec, the DeepMind research scientist who co-led the study, told journalists.
Its impact won’t be as significant as AlphaFold, which ushered in a new era in computational biology, agrees Joseph Marsh, a computational biologist at the MRC Human Genetics Unit in Edinburgh, UK. “It’s exciting. It’s probably the best predictor we have right now. But will it be the best predictor in two or three years? There’s a good chance it won’t be.”
France Dernières Nouvelles, France Actualités
Similar News:Vous pouvez également lire des articles d'actualité similaires à celui-ci que nous avons collectés auprès d'autres sources d'information.
Google AI tool predicts danger of genetic mutationsResearchers at Google DeepMind, the tech giant's artificial intelligence arm, on Tuesday introduced a tool that predicts whether genetic mutations are likely to cause harm, a breakthrough that could help research into rare diseases.
Lire la suite »
Google DeepMind's new AI tool can predict genetic diseasesGoogle DeepMind has come up with an AI model which can predict which genetic mutation is benign and which is hostile to the human body.
Lire la suite »
Dingoes found to have more harmful mutations than most inbred dog breedsGenome sequencing comparisons with wolves, strays and dogs across the world has found Australia's dingoes have the highest loads of harmful mutations—and diversity levels that are 36% lower than the most inbred dogs.
Lire la suite »
Genetic biomarker may predict severity of food allergyResearchers reported for the first time that a genetic biomarker may be able to help predict the severity of food allergy reactions. Currently there is no reliable or readily available clinical biomarker that accurately distinguishes patients with food allergies who are at risk for severe life-threatening reactions versus more mild symptoms.
Lire la suite »
New study on the genetic magnetization of living bacteria shows great potential for biomedicineMagnetic bacteria possess extraordinary capabilities due to the magnetic nanoparticles, the magnetosomes, which are concatenated inside their cells. A research team at the University of Bayreuth has now transferred all of the approximately 30 genes responsible for the production of these particles to non-magnetic bacteria in a broad series of experiments.
Lire la suite »