Google unveiled an artificial intelligence tool Wednesday that its scientists said would help unravel the mysteries of the human genome — and could one day lead to new treatments for diseases.
The deep learning model AlphaGenome was hailed by outside researchers as a “breakthrough” that would let scientists study and even simulate the roots of difficult-to-treat genetic diseases.
While the first complete map of the human genome in 2003 “gave us the book of life, reading it remained a challenge,” Pushmeet Kohli, vice president of research at Google DeepMind, told journalists. “We have the text,” he said, which is a sequence of three billion nucleotide pairs represented by the letters A, T, C and G that make up DNA.
Photo courtesy of Wikimedia Commons
However “understanding the grammar of this genome — what is encoded in our DNA and how it governs life — is the next critical frontier for research,” said Kohli, co-author of a new study in the journal Nature.
Only around two percent of our DNA contains instructions for making proteins, which are the molecules that build and run the body.
The other 98 percent was long dismissed as “junk DNA” as scientists struggled to understand what it was for.
Photo: Reuters
However this “non-coding DNA” is now believed to act like a conductor, directing how genetic information works in each of our cells.
These sequences also contain many variants that have been associated with diseases. It is these sequences that AlphaGenome is aiming to understand.
A MILLION LETTERS
Photo courtesy of Wikimedia Commons
The project is just one part of Google’s AI-powered scientific work, which also includes AlphaFold, the winner of 2024’s chemistry Nobel.
AlphaGenome’s model was trained on data from public projects that measured non-coding DNA across hundreds of different cell and tissue types in humans and mice. The tool is able to analyze long DNA sequences then predict how each nucleotide pair will influence different biological processes within the cell.
This includes whether genes start and stop and how much RNA — molecules which transmit genetic instructions inside cells — is produced.
Other models already exist that have a similar aim. However they have to compromise, either by analyzing far shorter DNA sequences or decreasing how detailed their predictions are, known as resolution. DeepMind scientist and lead study author Ziga Avsec said that long sequences — up to a million DNA letters long — were “required to understand the full regulatory environment of a single gene.”
And the high resolution of the model allows scientists to study the impact of genetic variants by comparing the differences between mutated and non-mutated sequences.
“AlphaGenome can accelerate our understanding of the genome by helping to map where the functional elements are and what their roles are on a molecular level,” study co-author Natasha Latysheva said.
The model has already been tested by 3,000 scientists across 160 countries and is open for anyone to use for non-commercial reasons, Google said.
“We hope researchers will extend it with more data,” Kohli added.
‘BREAKTHROUGH’
Ben Lehner, a researcher at Cambridge University who was not involved in developing AlphaGenome but did test it, said the model “does indeed perform very well.”
“Identifying the precise differences in our genomes that make us more or less likely to develop thousands of diseases is a key step towards developing better therapeutics,” he explained.
However AlphaGenome “is far from perfect and there is still a lot of work to do,” he added.
“AI models are only as good as the data used to train them” and the existing data is not very suitable, he said.
Robert Goldstone, head of genomics at the UK’s Francis Crick Institute, cautioned that AlphaGenome was “not a magic bullet for all biological questions.”
This was partly because “gene expression is influenced by complex environmental factors that the model cannot see,” he said.
However the tool still represented a “breakthrough” that would allow scientists to “study and simulate the genetic roots of complex disease,” Goldstone added.
The column Taiwan in Time will return to this page on Sunday next week.
Jason Han says that the e-arrival card spat between South Korea and Taiwan shows that Seoul is signaling adherence to its “one-China” policy, while Taiwan’s response reflects a reciprocal approach. “Attempts to alter the diplomatic status quo often lead to tit-for-tat responses,” the analyst on international affairs tells the Taipei Times, adding that Taiwan may become more cautious in its dealings with South Korea going forward. Taipei has called on Seoul to correct its electronic entry system, which currently lists Taiwan as “China (Taiwan),” warning that reciprocal measures may follow if the wording is not changed before March 31. As of yesterday,
The Portuguese never established a presence on Taiwan, but they must have traded with the indigenous people because later traders reported that the locals referred to parts of deer using Portuguese words. What goods might the Portuguese have offered their indigenous trade partners? Among them must have been slaves, for the Portuguese dealt slaves across Asia. Though we often speak of “Portuguese” ships, imagining them as picturesque vessels manned by pointy-bearded Iberians, in Asia Portuguese shipping between local destinations was crewed by Asian seamen, with a handful of white or Eurasian officers. “Even the great carracks of 1,000-2,000 tons which plied
On Thursday, former Taipei mayor and founder of the Taiwan People’s Party (TPP) Ko Wen-je (柯文哲) was sentenced to 17 years in prison and had his civil rights suspended for six years over corruption, embezzlement and other charges. Seven others related to the case were also handed prison sentences, while two were found not guilty. It has been a bad week for the TPP. On Tuesday, prosecutors charged Chinese immigrant Xu Chunying (徐春鶯) with suspicion of taking part in Beijing-directed election interference. Xu has strong links to the TPP, which once offered her a party list legislator nomination. Tuesday also
Nuclear power is getting a second look in Southeast Asia as countries prepare to meet surging energy demand as they vie for artificial intelligence-focused data centers. Several Southeast Asian nations are reviving mothballed nuclear plans and setting ambitious targets and nearly half of the region could, if they pursue those goals, have nuclear energy in the 2030s. Even countries without current plans have signaled their interest. Southeast Asia has never produced a single watt of nuclear energy, despite long-held atomic ambitions. But that may soon change as pressure mounts to reduce emissions that contribute to climate change, while meeting growing power needs. The
RSS