Designer DNA Could Revolutionise Cures for Diseases
By Sarah Knapton – Science Editor
Scientists hope AlphaGenome programme ushers in new era of personalised medicine.
Fixing gene defects with designer DNA is on the horizon after Google DeepMind launched a pioneering new AI tool.
The programme, called AlphaGenome, can interpret long strands of DNA – up to a million base pairs – and predict how subtle mutations and variants are influencing biological processes.
It allows scientists to see how changes drive disease, and could be used to design new synthetic DNA to activate or deactivate genes in specific parts of the body to treat medical conditions.
This cannot be done with gene therapy currently, and could usher in a new era of personalised medicine.
Create entirely new DNA
Ziga Avsec, who leads the genomics initiative in DeepMind’s science programme, said AlphaGenome could be used to create entirely new DNA.
“AlphaGenome could be used to generate short stretches of non-coding DNA that don’t exist in nature,” he said.
“In a gene therapy context, you would include this synthetic code in your delivery vector alongside the therapeutic gene.
“This ‘synthetic switch’ could help ensure that the therapy only turns on in the specific target tissue – like the retina or liver – while remaining silent in the rest of the body.”
The genome is a person’s complete set of DNA which acts like a cellular instruction manual, guiding every aspect of a living organism.
But tiny variations in DNA can make a person more susceptible to disease, or alter how the body responds to certain environmental factors, such as cigarette smoke, stress or pathogens.
Deciphering how these tiny changes impact health and longevity has been a major goal in biological research, and scientists are only scratching the surface of what DNA is doing.
The genome is made up of around two per cent of genes which code for proteins and, until recently, the remaining genetic material was thought to be “junk”.
Now it is recognised that most of the critical changes are happening in this area of “junk DNA”, which regulates genes, boosts or silences activity, and plays a major role in disease and cell health.
DeepMind previously released programmes which could interpret the effects of genes – but crucially AlphaGenome can also interpret the impact of the “junk DNA” – which accounts for 98 per cent of the genome.
As well as building synthetic DNA, it will also help researchers pinpoint what mutations are causing disease, as well as being able to spot beneficial changes that could lead to new therapies.
Google DeepMind’s AlphaGenome programme can predict how subtle mutations and variants are influencing biological processes
The model has been trained using human and mouse genomes, so that it can understand how different DNA sequences drive various biological processes.
Commenting on the research, Dr Robert Goldstone, head of genomics at the Francis Crick Institute in London, said: “DeepMind’s AlphaGenome represents a major milestone in the field of genomic AI.
“This level of resolution, particularly for non-coding DNA, is a breakthrough that moves the technology from theoretical interest to practical utility, allowing scientists to programmatically study and simulate the genetic roots of complex disease.
“One of the most remarkable demonstrations is its ability to predict gene expression from DNA sequence alone.”
Experts hope the model could also be used to help interpret the DNA of plants, animals and microbes that have not been studied in detail.
Prof Rivka Isaacson, a molecular biophysicist at King’s College London, added: “This work is an exciting step forward in illuminating the ‘dark genome’.
“We still have a long way to go in understanding the lengthy sequences of our DNA that don’t directly encode the protein machinery whose constant whirring keeps us healthy.
“There are so many interwoven possibilities, and complex feedback mechanisms, that I doubt the whole thing will ever be fully untangled. AlphaGenome gives scientists whole new and vast datasets to sift and scavenge for clues.”
The research was published in the Nature journal.
Original source: https://www.telegraph.co.uk/news/2026/01/28/designer-dna-revolutionise-cures-diseases-google-deepmind/
