Scientists are using machine learning to interpret “dark matter” DNA

Scientists at Gladstone Institutes are using machine learning to target genetic disorders in so-called genomic “dark matter”.

The computational method being used, called TargetFinder, predicts where non-coding DNA – the DNA that does not code for proteins – interacts with genes. By analysing big data, researchers are abble to connect mutations in genomic “dark matter” with the genes they affect, potentially revealing new targets for genetic disorders.

In the study, published in Nature Genetics, the team from Gladstone Institutes looked at fragments of non-coding DNA called enhancers which act like an instruction manual for a gene, dictating when and where a gene is turned on.

“Most genetic mutations that are associated with disease occur in enhancers, making them an incredibly important area of study,” said the study’s senior author, Katherine Pollard. “Before now, we struggled to understand how enhancers find the distant genes they act upon.”

dna

The new study revealed that, on a strand of DNA, enhancers can be millions of letters away from the gene they influence.

However, using machine learning technology, the researchers were able to analyse hundreds of existing datasets to look for patterns in the genome and identify where a gene and enhancer interact.

They discovered that when an enhancer is far away from the gene it affects, the two connect by forming a three-dimensional loop, like a bow on the genome.

“It’s remarkable that we can predict complex three-dimensional interactions from relatively simple data,” said biostatistician at Gladstone, Sean Whalen. “No one had looked at the information stored on loops before, and we were surprised to discover how important that information is.”

dna1

The new computational approach is a much cheaper and a less time-consuming way to identify gene-enhancer connections in the genome as performing experiments in the can take millions of dollars and years of research.

The technology also gives an insight into how DNA loops form and how they might break in disease.

“Our ability to predict the gene targets of enhancers so accurately enables us to link mutations in enhancers to the genes they target,” said Pollard. “Having that link is the first step towards using these connections to treat diseases.”

Gladstone is set to offer all of the code and data from TargetFinder online for free.

School will use facial analysis to identify students who are dozing off

In September the ESG business school in Paris will begin using artificial intelligence and facial analysis to determine whether students are paying attention in class. The school says the technology will be used to improve performance of students and professors.

Source: The Verge

Company offers free training for coal miners to become wind farmers

A Chinese wind-turbine maker wants American workers to retrain and become wind farmers. The training program was announced at an energy conference in Wyoming, where the American arm of Goldwind, a Chinese wind-turbine manufacturer is located.

Source: Quartz

Google AI defeats human Go champion

Google's DeepMind AI AlphaGo has defeated the world's number one Go player Ke Jie. AlphaGo secured the victory after winning the second game in a three-part match. DeepMind founder Demis Hassabis said Ke Jie "pushed AlphaGo right to the limit".

Source: BBC

Vegan burgers that taste like real meat to hit Safeway stores

Beyond Meat, which promises its plant-based burgers bleed and sizzle like real ground beef and is backed by investors like Bill Gates, will begin distributing its plant-based burgers in more than 280 Safeway stores in California, Hawaii and Nevada.

Source: Bloomberg

The brain starts to eat itself after chronic sleep deprivation

Brain cells that destroy and digest worn-out cells and debris go into overdrive in mice that are chronically sleep-deprived. The discovery could explain why a chronic lack of sleep puts people at risk of neurological disorders like Alzheimer’s disease.

Source: New Scientist

"We can still act and it won’t be too late," says Obama

Former US President Barack Obama has written an op-ed piece in the Guardian giving his views on some of the greatest challenges facing the world – food and climate change – and what we can do about them. "We can still act and it won’t be too late," writes Obama.

Source: The Guardian

Juno mission: Jupiter’s magnetic field is even weirder than expected

It has long been known that Jupiter has the most intense magnetic field in the solar system, but the first round of results from NASA’s Juno mission has revealed that it is far stronger and more misshapen than scientists predicted.

Announcing the findings of the spacecraft’s first data-collection pass, which saw Juno fly within 2,600 miles (4,200km) of Jupiter on 27th August 2016, NASA mission scientists revealed that the planet far surpassed the expectations of models.

Measuring Jupiter’s magnetosphere using Juno’s magnetometer investigation (MAG) tool, they found that the planet’s magnetic field is even stronger than models predicted, at 7.766 Gaus: 10 times stronger than the strongest fields on Earth.

Furthermore, it is far more irregular in shape, prompting a re-think about how it could be generated.

“Juno is giving us a view of the magnetic field close to Jupiter that we’ve never had before,” said Jack Connerney, Juno deputy principal investigator and magnetic field investigation lead at NASA’s Goddard Space Flight Center in Greenbelt, Maryland.

“Already we see that the magnetic field looks lumpy: it is stronger in some places and weaker in others.

An enhanced colour view of Jupiter’s south pole. Image courtesy of NASA/JPL-Caltech/SwRI/MSSS/Gabriel Fiset. Featured image courtesy of NASA/SWRI/MSSS/Gerald Eichstädt/Seán Doran

At present, scientists cannot say for certain why or how Jupiter’s magnetic field is so peculiar, but they do already have a theory: that the field is not generated from the planet’s core, but in a layer closer to its surface.

“This uneven distribution suggests that the field might be generated by dynamo action closer to the surface, above the layer of metallic hydrogen,” said Connerney.

However, with many more flybys planned, the scientists will considerable opportunities to learn more about this phenomenon, and more accurately pinpoint the bizarre magnetic field’s cause.

“Every flyby we execute gets us closer to determining where and how Jupiter’s dynamo works,” added Connerney.

With each flyby, which occurs every 53 days, the scientists are treated to a 6MB haul of newly collected information, which takes around 1.5 days to transfer back to Earth.

“Every 53 days, we go screaming by Jupiter, get doused by a fire hose of Jovian science, and there is always something new,” said Scott Bolton, Juno principal investigator from the Southwest Research Institute in San Antonio.

A newly released image of Jupiter’s stormy south pole. Image courtesy of NASA/JPL-Caltech/SwRI/MSSS/Betsy Asher Hall/Gervasio Robles

An unexpected magnetic field was not the only surprise from the first data haul. The mission also provided a first-look at Jupiter’s poles, which are unexpectedly covered in swirling, densely clustered storms the size of Earth.

“We’re puzzled as to how they could be formed, how stable the configuration is, and why Jupiter’s north pole doesn’t look like the south pole,” said Bolton. “We’re questioning whether this is a dynamic system, and are we seeing just one stage, and over the next year, we’re going to watch it disappear, or is this a stable configuration and these storms are circulating around one another?”

Juno’s Microwave Radiometer (MWR) also threw up some surprises, with some of the planet’s belts appearing to penetrate down to its surface, while others seem to evolve into other structures. It’s a curious phenomenon, and one which the scientists hope to better explore on future flybys.

“On our next flyby on July 11, we will fly directly over one of the most iconic features in the entire solar system – one that every school kid knows – Jupiter’s Great Red Spot,” said Bolton.

“If anybody is going to get to the bottom of what is going on below those mammoth swirling crimson cloud tops, it’s Juno and her cloud-piercing science instruments.”