‘Transformational’ approach to machine learning could accelerate search for new disease treatments

‘Transformational’ approach to machine learning could accelerate search for new disease treatments
‘Transformational’ approach to machine learning could accelerate search for new disease treatments

Researchers have developed a new approach to machine learning that ‘learns how to learn’ and out-performs current machine learning methods for drug design, which in turn could accelerate the search for new disease treatments.

The method, called transformational machine learning (TML), was developed by a team from the UK, Sweden, India and Netherlands. It learns from multiple problems and improves performance while it learns.

TML could accelerate the identification and production of new drugs by improving the machine learning systems which are used to identify them. The results are reported in the Proceedings of the National Academy of Sciences.

Most types of machine learning (ML) use labelled examples, and these examples are almost always represented in the computer using intrinsic features, such as the colour or shape of an object. The computer then forms general rules that relate the features to the labels.

“It’s sort of like teaching a child to identify different animals: this is a rabbit, this is a donkey and so on,” said Professor Ross King from Cambridge’s Department of Chemical Engineering and Biotechnology, who led the research. “If you teach a machine learning algorithm what a rabbit looks like, it will be able to tell whether an animal is or isn’t a rabbit. This is the way that most machine learning works – it deals with problems one at a time.”

However, this is not the way that human learning works: instead of dealing with a single issue at a time, we get better at learning because we have learned things in the past.

“To develop TML, we applied this approach to machine learning, and developed a system that learns information from previous problems it has encountered in order to better learn new problems,” said King, who is also a Fellow at The Alan Turing Institute. “Where a typical ML system has to start from scratch when learning to identify a new type of animal – say a kitten – TML can use the similarity to existing animals: kittens are cute like rabbits, but don’t have long ears like rabbits and donkeys. This makes TML a much more powerful approach to machine learning.”

The researchers demonstrated the effectiveness of their idea on thousands of problems from across science and engineering. They say it shows particular promise in the area of drug discovery, where this approach speeds up the process by checking what other ML models say about a particular molecule. A typical ML approach will search for drug molecules of a particular shape, for example. TML instead uses the connection of the drugs to other drug discovery problems.

“I was surprised how well it works – better than anything else we know for drug design,” said King. “It’s better at choosing drugs than humans are – and without the best science, we won’t get the best results.”

Reference:
Ivan Olier et al. ‘Transformational Machine Learning: Learning How to Learn from Many Related Scientific Problems.’ Proceedings of the National Academy of Sciences (2021). DOI: 10.1073/pnas.2108013118



from ScienceBlog.com https://ift.tt/3d1V3Tp

Comments

Post a Comment

Popular

Words Matter When Discussing Alcohol Issues: A New Stigma-Free Vocabulary for Better AUD Outcomes

Image
Word choice may seem out of place among the myriad factors that can influence outcomes for a complex condition like alcohol use disorder (AUD). In fact, the stigma created by the language that is used to describe alcohol problems can decrease many people’s willingness to seek help for alcohol problems. It also can affect how people with AUD are treated in all aspects of life. “Stigmas are the negative attitudes toward people that are based on certain distinguishing characteristics,” says National Institute on Alcohol Abuse and Alcoholism (NIAAA) Director George F. Koob, Ph.D. “More than a decade of research has shown that stigma contributes significantly to negative health outcomes and can pose a barrier to seeking treatment for mental illness or substance use disorders.” In the United States, nearly 90 percent of people with substance use disorders and 35 percent of people with serious mental illness do not receive treatment. In a recent article published in  Neuropsychopharma...
Read more

‘Massive-scale mobilization’ necessary for addressing climate change, scientists say

Image
A year after a global coalition of more than 11,000 scientists declared a climate emergency, Oregon State University researchers who initiated the declaration released an update today that points to a handful of hopeful signs, but shares continued alarm regarding an overall lack of progress in addressing climate risks. “Young people in more than 3,500 locations around the world have organized to push for urgent action,” said Oregon State University’s William Ripple, who co-authored “The Climate Emergency: 2020 in Review,” published today in Scientific American. “And the Black Lives Matter movement has elevated social injustice and equality to the top of our consciousness. “Rapid progress in each of the climate action steps we outline is possible if framed from the outset in the context of climate justice – climate change is a deeply moral issue. We desperately need those who face the most severe climate risks to help shape the response.” One year ago, Ripple, distinguished profess...
Read more

Researchers advance science behind gut health and prebiotics

Image
When it comes to improving human gut health, approaches and the success of these approaches are based largely on an individual’s gut ecosystem: the bacteria present, its diversity and other factors. Therefore, trying to improve gut health through application of prebiotics or probiotics can have wildly variable results based on gut flora composition. Bruce Hamaker , director of the Whistler Center for Carbohydrate Research and Distinguished Professor of Food Science, and Thaisa Moro Cantu-Jungles, his postdoctoral research associate, recently discovered a way to select prebiotic fibers that have the potential to provide improvement of gut health where everyone would benefit. Their study, conducted in vitro, showed an increase in butyrate-producing bacteria with a selected fiber using this new approach. Butyrate is a short-chain fatty acid that supports many of the body’s essential functions from regulating the immune system to digestive health. In donors’ gut flora where these bacter...
Read more