adplus-dvertising
Connect with us

Science

AlphaFold and AI Accelerate Design of New Liver Cancer Drug

Published

 on

New research uses AlphaFold, an artificial intelligence (AI)-powered protein structure database, to accelerate the design and synthesis of a drug to treat hepatocellular carcinoma (HCC), the most common type of primary liver cancer. It is the first successful application of AlphaFold to hit identification process in drug discovery. This study by an international team of researchers, published last week in Chemical Science, is led by the University of Toronto’s Acceleration Consortium director Alán Aspuru-Guzik, Chemistry Nobel laureate Michael Levitt, and Insilico Medicine founder and CEO Alex Zhavoronkov.

AI is revolutionizing drug discovery and development. In 2022, the AlphaFold computer program, developed by Alphabet’s DeepMind, predicted protein structures for the whole human genome––a remarkable breakthrough in both AI applications and structural biology. This free AI-powered database is helping scientists predict the structure of millions of unknown proteins, which is key to accelerating the development of new medicines to treat disease and beyond.

In this new Chemical Science paper, AlphaFold was successfully applied to an end-to-end AI-powered drug discovery platform called Pharma.AI, including a biocomputational engine, PandaOmics, and a generative chemistry engine, Chemistry42. Researchers discovered a novel target for HCC – a previously undiscovered treatment pathway – and developed a novel hit molecule – a molecule that could bind to that target – without the aid of an experimentally determined structure.  This was accomplished in just 30 days from target selection and after only synthesizing 7 compounds. In a second round of AI-powered compound generation, researchers discovered a more potent hit molecule.

“While the world was fascinated with advances in generative AI in art and language, our generative AI algorithms managed to design potent inhibitors of a target with an AlphaFold-derived structure,” said Alex Zhavoronkov, founder and CEO of Insilico Medicine.

300x250x1

Want more breaking news?

Subscribe to Technology Networks’ daily newsletter, delivering breaking science news straight to your inbox every day.

Subscribe for FREE

“AlphaFold broke new scientific ground in predicting the structure of all proteins in the human body,” said Feng Ren, co-author, Chief Scientific Officer and co-CEO of Insilico Medicine. “At Insilico Medicine, we saw that as an incredible opportunity to take these structures and apply them to our end-to-end AI platform in order to generate novel therapeutics to tackle diseases with high unmet need. This paper is an important first step in that direction.”

Without AI, scientists must rely on conventional trial and error methods of chemistry that are slow, expensive and limit the scope of their exploration. As COVID-19 has demonstrated, the speedy development of new drugs or new formulations of existing ones is needed and increasingly expected by the public. AI has the potential to deliver this speed by transforming materials and molecular discovery, as it has done with just about every branch of science and engineering over the last decade.

“This paper is further evidence of the capacity for AI to transform the drug discovery process with enhanced speed, efficiency, and accuracy,” said Michael Levitt, Nobel Prize winner in Chemistry, Robert W. and Vivian K. Cahill Professor of Cancer Research and Professor of Computer Science, Stanford University. “Bringing together the predictive power of AlphaFold and the target and drug design power of Insilico Medicine’s Pharma.AI platform, it’s possible to imagine that we’re on the cusp of a new era of AI-powered drug discovery.”

“What this paper demonstrates is that for healthcare, AI developments are more than the sum of their parts,” said Alan Aspuru-Guzik, a professor of chemistry and computer science at the University of Toronto and the Canada 150 Research Chair in Theoretical and Quantum Chemistry. “If one uses a generative model targeting an AI-derived protein, one can substantially expand the range of diseases that we can target. If one adds self-driving labs to the mix, we will be in uncharted territory. Stay tuned!”

Both Insilico Medicine and the Acceleration Consortium, a University of Toronto initiative that Aspuru-Guzik directs, are working actively to develop self-driving laboratories, an emerging technology that combines AI, automation and advanced computing to accelerate materials and molecular discovery. Accessible tools and data will help more scientists enter the field of AI for science, in turn helping to drive major progress in this area.

Insilico Medicine is a clinical stage company developing an AI-based end-to-end integrated pipeline for drug discovery and design, with the first AI-discovered and AI-designed drug, for idiopathic pulmonary fibrosis, to advance to positive Phase 1 topline results, and 30 other drugs in its pipeline, for cancer, fibrosis, immunity, central nervous system diseases, and aging-related diseases. Both Aspuru-Guzik and Levitt are advisors to Insilico. The Acceleration Consortium is a global community of academia, industry, and government working together to accelerate the discovery of new molecules and materials needed for a sustainable future.

Reference: Ren F, Ding X, Zheng M, et al. AlphaFold accelerates artificial intelligence powered drug discovery: efficient discovery of a novel CDK20 small molecule inhibitor. Chem Sci. 2023. doi: 10.1039/D2SC05709C

This article has been republished from the following materials. Note: material may have been edited for length and content. For further information, please contact the cited source.

728x90x4

Source link

Continue Reading

Science

Green comet making its closest approach to Earth in 50,000 years – Yahoo Movies Canada

Published

 on


A rare green comet, that has not been seen for 50,000 years, is about to make its closest pass by Earth, becoming visible in a once-in-a-lifetime opportunity.

Called C/2022 E3 (ZTF), this celestial object hails from the Oort cloud at the outermost edge of the solar system.

Its green glow is a result of ultraviolet radiation from the sun lighting up the gases surrounding the comet’s surface.

300x250x1

The icy ball orbits the sun once every 50,000 years, which means the last time it went past the planet was during the Stone Age – when Neanderthals roamed the Earth.

It is due to pass closest to the planet – still some 42 million kilometres away –  on Wednesday night, into the early hours of Thursday and in a very dark sky will appear as a faint smudge to those looking for it with the naked eye.

However, even if the moon is too bright for stargazers to spot the comet on Wednesday night, they might be able to catch a glimpse of it a week later when it passes Mars.

Professor Don Pollacco, from the department of physics at the University of Warwick, told the PA news agency: “Comet C/2022 E3 passes closest to Earth tonight, on 1 February.

“It has been christened the “Green Comet” as pictures show the head of the Comet to have a striking colour.

“We understand this as due to light emitted from carbon molecules ejected from the nucleus due to the increase in heat etc during its closest approach to the sun, which happened around 12 January.

“Some comets approach the sun much closer and are completely evaporated by the intense radiation.”

He added: “As the comet approaches Earth (it’s still 42 million km away, so no chance of a collision) it appears to move more quickly across the sky on a night-by-night basis.

“Tonight the comet is about halfway between the pole star and the bright star Capella, overhead about 11pm.

“However, the waxing moon will make the Comet much harder to spot. To see it you’ll need a clear sky, binoculars and a bit of luck.

“Alternately, if you wait a few days to around 10 February, the moon will be less bright and the comet will be clearer to see in the southern part of the sky, passing Mars.”

The Greenwich Royal Observatory says that from the northern hemisphere, the comet is already visible in the night sky using a telescope or some binoculars.

It adds: “Comet C/2022 E3 (ZTF) will be closest to Earth on February 1. This will also be the moment the comet appears at its brightest, and currently it is expected to reach a brightness magnitude of +6. That would mean it would be visible to the naked eye.

“It’s worth noting, however, that comets can be unpredictable, and it’s hard to say with accuracy how bright the comet will be or what it will look like ahead of time.

“The comet looks like a fuzzy green ball or smudge in the sky. This green glow is a result of UV radiation from the sun lighting up the gases streaming off of the comet’s surface.”

Advising on where the comet can be seen in the night sky, the Observatory says: “When it passes near Earth in February, the green comet will be in the constellation of Camelopardalis.

“After its closest approach, the green comet will move through Auriga and end up in Taurus mid-February.

“The comet will dim over the month as it moves away from us, and the time that it will be up in the sky during the night will get shorter and shorter.”

Adblock test (Why?)

728x90x4

Source link

Continue Reading

Science

New AI algorithm helps find 8 radio signals from space

Published

 on

A new artificial intelligence algorithm created by a Toronto student is helping researchers search the stars for signs of life.

Peter Xiangyuan Ma, a University of Toronto undergraduate student and researcher, said he started working on the algorithm while he was in Grade 12 during the pandemic.

“I was just looking for projects and I was interested in astronomy,” he told CTV News Toronto.

The idea was to help distinguish between technological radio signals created by human technologies and signals that were potentially coming from other forms of life in space.

300x250x1

“What we’re looking for is signs of technology that signifies if the sender is intelligent or not. And so unsurprised to us, we keep on finding ourselves,” Ma explained. “We don’t want to be looking at our own noisy signals.”

Using this algorithm, Ma said researchers were able to discover eight new radio signals being emitted from five different stars about 30 to 90 light years away from the Earth.

These signals, Ma said, would disappear when researchers looked away from it, which rules out, for the most part, interference from a signal originating from Earth. When they returned to the area, the signal was still there.

“We’re all very suspicious and scratching our heads,” he said. “We proved that we found things that we wanted to find … now, what do we do with all these? That’s another separate issue.”

Steve Croft, Project Scientist for Breakthrough Listen on the Green Bank Telescope, the institute whose open source data was the inspiration for Ma’s algorithm, said that finding radio signals in space is like trying to find a needle in a haystack.

“You’ve got to recognize the haystack itself and make sure that you don’t throw the needle away as you’re looking at the individual pieces of hay,” Croft, who collaborated on Ma’s research, told CTV News Toronto.

Croft said algorithms being used to discover these signals have to account for multiple characteristics, including the position they are coming from in the sky and whether or not the transmission changes over time, which could indicate if it’s coming from a rotating planet or star.

“The algorithm that Peter developed has enabled us to do this more efficiently,” he said.

The challenge, Croft says, is recognizing that false positives may exist despite a signal meeting this criteria. What could be signs of extraterrestrial life may also just be a “weirdly shaped bit of a haystack,” he added.

“And so that’s why we have to go back and look again and see if the signal still there. And with these particular examples that Peter found with his algorithm, the signal was not there when we pointed the telescope back again. And so we sort of can’t say one way or another, is this genuine?”

Researchers have been searching the sky for technologically-generated signals since the 1960s, searching thousands of stars and galaxies for signs of intelligent life. The process is called “SETI,” or “the Search for Extraterrestrial Intelligence.”

But interference from our own radio signals has always proven to be a challenge. Croft says most pieces of technology have some kind of Bluetooth or wireless wave element that creates static, resulting in larger amounts of data needed to be collected.

“That’s a challenge but also computing provides the solution,” he said.

“So the computing and particularly the machine-learning algorithms gives us the power to search through this big haystack, looking for the needle of an interesting signal.”

Ma said that while we may not have found a “technosignal” just yet, we shouldn’t give up. The next step would be to employ multiple kinds of search algorithms to find more and more signals to study.

Peter Ma

While the “dream” is to find evidence of life, Ma says he is more focused on the scientific efforts of actively looking for it.

This sentiment is echoed by Croft, who said he is most fascinating in working towards answering the question of whether humans are alone in this universe.

“I don’t show up to work every day, thinking I’m going to find aliens, but I do show up for work. So you know, I’ve got sort of some optimism.”

728x90x4

Source link

Continue Reading

Science

How to spot the green comet in Manitoba

Published

 on

Space enthusiasts in the province will get the chance to potentially see a rare green comet over the next couple of days.

The comet was discovered by astronomers in southern California last year and it was determined the last time it passed Earth was around 50,000 years ago.

Mike Jensen, the planetarium and science gallery program supervisor at the Manitoba Museum, said the time between appearances and the colour of the comet makes this unique compared to others.

“The last time it would have appeared anywhere within the region of visibility to Earth, we’re talking primitive humans walking the Earth,” said Jensen. “And then yes, its colour. Most people associate comets, they’re often referred to as ghosts of the night sky because they often have a bit of a whitish-blue appearance. This one’s got a bit of green to it. Comets are all made up of different types of material, this just happens to have a bit more of some carbon elements in it.”

300x250x1

Jensen notes the green tint on the comet will be subtle, comparing it to the subtle red that surrounds Mars in the night sky.

Wednesday and Thursday are the best days to see the comet as Jensen said that’s when it will be closest to Earth – 42 million kilometres away.

“That proximity to us means it does get to its best visibility for us. The added advantage is it’s also appearing sort of high up in the northern sky, which puts it amongst the circumpolar stars of our night sky. In other words, the stars that are circling around the North Star.”

Now, just because the comet is close enough to be visible doesn’t mean it will be the easiest to see in the night sky according to Jensen. He said there are a few factors that play into having a successful sighting.

First, he suggests getting out of the city and away from the lights, noting, the darker it is, the better. If people head outside city limits, Jensen recommends people dress warmly, saying comet watching in the winter is not for the “faint of heart.”

Secondly, he said even though it might be possible to see the comet with the naked eye, he still suggests bringing binoculars to improve people’s chances. He also recommends checking star maps before leaving to get the most accurate location of where the comet may be.

Lastly, even if all of that is achieved, Jensen notes people will have to battle with the light of the moon, as it is close to a full moon.

“I’m not trying to dissuade anybody from going out to see it, but certainly, there’s going to be some hurdles to overcome in order to be able to spot it on your own.”

If people don’t want to go outside to see it, he said there are plenty of resources online to find digital views.

 – With files from CTV News’ Michael Lee

728x90x4

Source link

Continue Reading

Trending