
-
Indian army says new exchange of gunfire with Pakistan
-
Epstein accuser Virginia Giuffre takes own life in Australia: family
-
Hundreds of buildings damaged, dozens injured in 6.3 Ecuador quake
-
India and Pakistan's Kashmir fallout hits economy too
-
Francis's funeral to be grand farewell to 'pope of the poor'
-
Pogacar faces defiant Evenepoel at Liege-Bastogne-Liege
-
Chelsea eye great escape against Barcelona in Women's Champions League
-
Iran, US to hold new round of high-level nuclear talks
-
'Energy and effort' pay off for Reds as Blues' woes continue
-
Albatross and closing birdie lift China's Liu to LPGA Chevron lead
-
On the horizon? Wave of momentum for high seas treaty
-
Developing countries should fast-track US trade deals: World Bank president
-
Grizzlies' Morant 'doubtful' for must-win game 4 v Thunder
-
Trump in Rome for pope funeral in first foreign trip of new term
-
Trump says Russia-Ukraine deal 'very close' after new Kremlin talks
-
US rookies lead PGA pairs event with McIlroy and Lowry in hunt
-
Trump tariff promises get a reality check
-
Warriors coach Kerr 'relatively optimistic' injured Butler will play game 3
-
Postecoglou hopes 'Stonecutter's Credo' can inspire Spurs
-
PSG lose unbeaten Ligue 1 record ahead of Arsenal showdown
-
Venezuela accuses El Salvador president of 'human trafficking'
-
Own goal takes Sundowns to African final against Pyramids
-
Scores of buildings damaged, 20 injured in Ecuador quake
-
US stocks extend rally as market eyes busy calendar next week
-
Pope's death triggers surge of disinformation he fought against
-
Rovanpera takes control of Rally Islas Canarias
-
Zelensky insists Crimea is Ukrainian as US envoy meets Putin
-
Patel and Mendis help Sunrisers beat Kings in Dhoni's 400th T20
-
Copa del Rey ref statements 'unacceptable': Real Madrid after boycotting final build-up
-
Insurance CEO's accused killer pleads not guilty to federal murder charges
-
FBI arrests Wisconsin judge for shielding undocumented migrant
-
Brazil ex-president Collor de Mello jailed for corruption
-
Zelensky insists Crimea 'belongs' to Ukraine as US envoy meets Putin
-
Real Madrid boycott Copa del Rey build-up over referee complaints
-
Trinidad and Tobago votes for parliament, PM, with opposition in lead
-
IMF chief hails 'constructive' Spring Meetings held under tariff uncertainty
-
Iran FM Araghchi in Oman ahead of nuclear talks with US
-
Dozens of buildings destroyed, 20 injured in Ecuador quake
-
Young Barca must 'enjoy' Real Madrid Copa final fight: Flick
-
Pakistan and India border closure separates families
-
Brazil's Bolsonaro 'stable' after post-surgery setback
-
Catholics in secular Cuba hail Francis as 'bridge'
-
US envoy Witkoff, Putin discuss 'possibility' of direct Russia-Ukraine talks
-
Community seeks answers after French school knife killing
-
German prosecutors seek jail terms in VW 'dieselgate' trial
-
Sabalenka makes winning start at Madrid Open
-
EU, US should de-escalate and negotiate trade deal: IMF Europe director
-
Russia accuses Ukraine of killing general in car bombing
-
Emery wants FA Cup glory and Champions League berth for Villa
-
Buildings destroyed, one injured in Ecuador quake

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