
-
PSG eye becoming France's first 'Invincibles'
-
Late birdie burst lifts Ryder to Texas Open lead
-
Five potential Grand National fairytale endings
-
Trump purges national security team after meeting conspiracist
-
More work for McIlroy even with two wins before Masters
-
Trump hopeful of 'great' PGA-LIV golf merger
-
No.1 Scheffler goes for third Masters crown in four years
-
Where Trump's tariffs could hurt Americans' wallets
-
Trump says 'very close to a deal' on TikTok
-
Trump tariffs on Mexico: the good, the bad, the unknown
-
Postecoglou denies taunting Spurs fans in Chelsea defeat
-
Oscar-winning Palestinian director speaks at UN on Israeli settlements
-
With tariff war, Trump also reshapes how US treats allies
-
Fernandez fires Chelsea into fourth as pressure mounts on Postecoglou
-
South Korea court to decide impeached president's fate
-
Penguin memes take flight after Trump tariffs remote island
-
E.T., no home: Original model of movie alien doesn't sell at auction
-
Italy's Brignone has surgery on broken leg with Winter Olympics looming
-
Trump defiant as tariffs send world markets into panic
-
City officials vote to repair roof on home of MLB Rays
-
Rockets forward Brooks gets one-game NBA ban for technicals
-
Pentagon watchdog to probe defense chief over Signal chat row
-
US tariffs could push up inflation, slow growth: Fed official
-
New Bruce Springsteen music set for June 27 release
-
Tom Cruise pays tribute to Val Kilmer
-
Mexico president welcomes being left off Trump's tariffs list
-
Zuckerberg repeats Trump visits in bid to settle antitrust case
-
US fencer disqualified for not facing transgender rival
-
'Everyone worried' by Trump tariffs in France's champagne region
-
Italy's Brignone suffers broken leg with Winter Olympics looming
-
Iyer blitz powers Kolkata to big IPL win over Hyderabad
-
Russian soprano Netrebko to return to London's Royal Opera House
-
French creche worker gets 25 years for killing baby with drain cleaner
-
UK avoids worst US tariffs post-Brexit, but no celebrations
-
Canada imposing 25% tariff on some US auto imports
-
Ruud wants 'fair share' of Grand Slam revenue for players
-
Lesotho, Africa's 'kingdom in the sky' jolted by Trump
-
Trump's trade math baffles economists
-
Gaza heritage and destruction on display in Paris
-
'Unprecedented crisis' in Africa healthcare: report
-
Pogacar gunning for blood and thunder in Tour of Flanders
-
Macron calls for suspension of investment in US until tariffs clarified
-
Wall St leads rout as world reels from Trump tariffs
-
Mullins gets perfect National boost with remarkable four-timer
-
Trump tariffs hammer global stocks, dollar and oil
-
Authors hold London protest against Meta for 'stealing' work to train AI
-
Tate Modern gifted 'extraordinary' work by US artist Joan Mitchell
-
Mexico president welcomes being left off Trump's new tariffs list
-
Tonali eager to lead Newcastle back into Champions League
-
Lesotho hardest hit as new US tariffs rattle Africa

Google AI tool predicts danger of genetic mutations
Researchers 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.
The findings are "another step in recognising the impact that AI is having in the natural sciences," said Pushmeet Kohli, vice president for research at Google DeepMind.
The tool focuses on so-called "missense" mutations, where a single letter of the genetic code is affected.
A typical human has 9,000 such mutations throughout their genome; they can be harmless or cause diseases such as cystic fibrosis or cancer, or damage brain development.
To date, four million of these mutations have been observed in humans, but only two percent of them have been classified, either as disease-causing or benign.
In all, there are 71 million such possible mutations. The Google DeepMind tool, called AlphaMissense, reviewed these mutations and was able to predict 89 percent of them, with 90 percent accuracy.
A score was assigned to each mutation, indicating the risk of it causing disease (otherwise referred to as pathogenic).
The result: 57 percent were classified as probably benign, and 32 percent as probably pathogenic -- the remainder being uncertain.
The database was made public and available to scientists, and an accompanying study was published on Tuesday in the journal Science.
AlphaMissense demonstrates "superior performance" than previously available tools, wrote experts Joseph Marsh and Sarah Teichmann in an article also published in Science.
"We should emphasize that the predictions were never really trained or never really intended to be used for clinical diagnosis alone," said Jun Cheng of Google DeepMind.
"However, we do think that our predictions can potentially be helpful to increase the diagnosed rate of rare disease, and also potentially to help us find new disease-causing genes," Cheng added.
Indirectly, this could lead to the development of new treatments, the researchers said.
The tool was trained on the DNA of humans and closely-related primates, enabling it to recognize which genetic mutations are widespread.
Cheng said the training allowed the tool to input "millions of protein sequences and learns what a regular protein sequence looks like."
It then could identify a mutation and its potential for harm.
Cheng compared the process to learning a language.
"If we substitute a word from an English sentence, a person that is familiar with English can immediately see whether this word substitution will change the meaning of the sentence or not."
C.Garcia--AMWN