(Press-News.org) The AI tool AlphaFold has been improved so that it can now predict the shape of very large and complex protein structures. Linköping University researchers have also succeeded in integrating experimental data into the tool. The results, published in Nature Communications, are a step toward more efficient development of new proteins for, among other things, medical drugs.
In all living organisms, there is a huge variety of proteins that regulate cell functions. Basically, everything that happens in the body, from controlling muscles and forming hair to transporting oxygen into the blood and digesting food, involves proteins. But proteins are also found outside the body in, for example, detergents and medical drugs.
Proteins are large molecules consisting of 20 different amino acids that stick together in long rows, much like beads in a necklace. The sequences, or chains, can be anything from 50 up to a few thousand amino acids long. This gives rise to several billion different combinations, which in turn determine the three-dimensional shape of the protein. Depending on the shape of the protein chain, that is, the way it is folded, the protein has completely different functions.
For over 50 years, researchers have been trying to both predict and design different protein structures to gain a deeper understanding of the body’s mechanisms, various diseases, and to develop new types of medical drugs. This has been a laborious and expensive task involving a lot of manual handling.
But in 2020, the company Deepmind released open source software called AlphaFold. It is an artificial intelligence, based on so-called neural networks, that can predict with great accuracy how proteins will fold, and thus what functions they will have. This was a breakthrough that also resulted in the Nobel Prize in Chemistry 2024.
However, the programme has had its limitations. Among other things, it has not been able to predict very large protein compounds nor draw conclusions from experimental or incomplete data.
Researchers at Linköping University have now developed AlphaFold further to overcome these shortcomings. The tool, which they call AF_unmasked, can now take in information from experiments and partial data as well as predict very large and complex protein structures.
“We’re giving a new type of input to AlphaFold. The idea is to get the whole picture, both from experiments and neural networks, making it possible to build larger structures. But you can also have a draft of a structure that you feed into AlphaFold and get a relatively accurate result,” says Claudio Mirabello, docent at the Department of Physics, Chemistry and Biology at Linköping University.
The idea behind AF_unmasked is for researchers to refine the experiments carried out by providing guidance on how the researchers could design the protein. This is a step toward even better understanding of the functions of proteins and designing new types of protein drugs.
The AlphaFold breakthrough was made possible by researchers around the world collecting data since the 1970s on the structure of approximately 200,000 different proteins in a database. This database provided training data for AlphaFold. What finally made it work on a large scale was the technological development of supercomputers that use GPUs for heavy calculations.
Björn Wallner is a professor of bioinformatics at Linköping University and has worked with one of the three Nobel Prize winners.
“The possibilities for protein design are endless, only the imagination sets limits. It’s possible to develop proteins for use both inside and outside the body. You always have to find new, more difficult problems when you have solved the old ones. And within our field, finding problems is no problem,” says Björn Wallner.
Together with Claudio Mirabello, he developed a precursor to AlphaFold that also inspired Deepmind in developing the tool. Thanks to the resources of the Google-owned company, they were then able to develop what is now an indispensable tool for the world’s protein scientists.
“AlphaFold wasn’t the first tool to use deep neural networks to solve the problem. In fact, one of the most important characteristics of AlphaFold is that it encodes the evolutionary history of a protein inside the neural network, an idea that actually originated here at LiU and was published by Björn and me in 2019. So, you could say that AlphaFold was based on our idea, and now we are building on AlphaFold,” says Claudio Mirabello.
END
LiU researchers make AlphaFold predict very large proteins
2024-11-04
ELSE PRESS RELEASES FROM THIS DATE:
Fossil of huge terror bird offers new information about wildlife in South America 12 million years ago
2024-11-04
**EMBARGOED UNTIL RELEASE MONDAY, NOV. 4, AT 1 A.M. ET**
Researchers including a Johns Hopkins University evolutionary biologist report they have analyzed a fossil of an extinct giant meat-eating bird — which they say could be the largest known member of its kind — providing new information about animal life in northern South America millions of years ago.
The evidence lies in the leg bone of the terror bird described in new paper published Nov. 4 in Palaeontology. The study was led by Federico J. Degrange, a terror bird ...
Scientists create a world-first 3D cell model to help develop treatments for devastating lip injuries
2024-11-04
We use our lips to talk, eat, drink, and breathe; they signal our emotions, health, and aesthetic beauty. It takes a complex structure to perform so many roles, so lip problems can be hard to repair effectively. Basic research is essential to improving these treatments, but until now, models using lip cells — which perform differently to other skin cells — have not been available. In a new study published in Frontiers in Cell and Developmental Biology, scientists report the successful immortalization of donated lip cells, ...
One-third of patients with cancer visit EDs in months before diagnosis
2024-11-04
About 1 in 3 patients diagnosed with cancer in Ontario visited an emergency department (ED) in the 90 days before diagnosis, found a new study published in CMAJ (Canadian Medical Association Journal) https://www.cmaj.ca/lookup/doi/10.1503/cmaj.240952.
In a study that included more than 650 000 patients diagnosed with cancer between 2014 and 2021 in Ontario, 35% (229 683) had visited an ED in the 90 days before diagnosis. Among patients with ED visits before their cancer diagnosis, 64% had visited once, 23% had visited twice and 13% had 3 or more visits. ...
Adolescent exam anxiety can be intensified by pressure to achieve, says academic
2024-11-04
Former teacher Professor of Education David Putwain says ‘heavy-handed’ messages around test results can fuel extreme worry among some 16 to 18-year-olds, even when others respond well to such messages.
Putwain identifies several risk factors, for example students with certain personality traits, including those who are highly self-critical, can underachieve because of severe anxiety in exams. Certain demographics also report higher exam anxiety, including female persons and those from economically deprived backgrounds.
‘Temperature checks’ to identify at-risk ...
A digital health behavior intervention to prevent childhood obesity
2024-11-03
About The Study: A health literacy-informed digital intervention improved child weight-for-length trajectory across the first 24 months of life and reduced childhood obesity at 24 months. The intervention was effective in a racially and ethnically diverse population that included groups at elevated risk for childhood obesity.
Corresponding Author: To contact the corresponding author, William J. Heerman, MD, MPH, email Bill.Heerman@vumc.org.
To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/
(doi:10.1001/jama.2024.22362)
Editor’s ...
Preventing obesity in very young children could be in the palm of parents’ hands
2024-11-03
A study co-led by a Johns Hopkins Children’s Center clinician-researcher shows that adding text messaging and other electronic feedback to traditional in-clinic health counseling for parents about feeding habits, playtime and exercise prevents very young children from developing obesity and potentially lifelong obesity-related problems.
Findings from the study, which was co-led by Eliana Perrin, M.D., M.P.H., Bloomberg Distinguished Professor of Primary Care at the Johns Hopkins University Schools of Medicine, Nursing and Public Health, will be published in JAMA and presented at the Obesity Society’s “Obesity Week” in San Antonio, both on Nov. ...
Mathematical model illuminates how environment impacts life choices of salmon
2024-11-02
Tokyo, Japan – Researchers from Tokyo Metropolitan University have created a mathematical model that models how the evolutionary strategies of organisms are affected by the environment. They studied salmonid fishes which choose either to migrate to the sea then return to lay eggs or stay in the river depending on their individual features. Their model correctly predicts how the proportion choosing to migrate changes with environmental conditions, predicting how environmental change can trigger eco-evolutionary responses.
Salmonids (or salmon-like) fish are known to face a tough choice early in their lives. They can either stay where they are ...
Houston Methodist researchers shed light on increased rates of severe human infections caused by Streptococcus subspecies
2024-11-01
HOUSTON-(Nov. 1, 2024) – A concerning increase in global rates of severe invasive infections becoming resistant to key antibiotics has a team of infectious disease researchers at the Houston Methodist Research Institute studying a recently emerged strain of bacteria called Streptococcus dysgalactiae subspecies equisimilis (SDSE). SDSE infects humans via the skin, throat, gastrointestinal tract and female genital tract to cause infections ranging in severity from strep throat (pharyngitis) to necrotizing fasciitis (flesh-eating disease).
Closely related to group A streptococcus (also commonly known as Streptococcus pyogenes), which has been very well studied, ...
Auburn University hosts 62nd Hands-On Workshop on Computational Biophysics, featuring the new VMD 2.0
2024-11-01
AUBURN, Ala. – The NIH Center for Macromolecular Modeling and Visualization and Auburn University are pleased to announce the 62nd Hands-On Workshop on Computational Biophysics, taking place from December 16-20, 2024, at Auburn University’s Department of Physics. This prestigious workshop series, first launched in June 2003 by the Theoretical and Computational Biophysics Group at the University of Illinois at Urbana-Champaign, has become a premier global training event in molecular modeling. Supported by NIH, the workshop provides a unique platform for researchers across disciplines to master the latest computational biophysics techniques.
This year’s ...
The Salton Sea — an area rich with lithium — is a hot spot for child respiratory issues
2024-11-01
Windblown dust from the shrinking Salton Sea harms the respiratory health of children living nearby, triggering asthma, coughing, wheezing and disrupted sleep, USC research shows.
The findings also indicate that children living closest to the sea, who are exposed to more dust in the air, may be the most affected.
The study, published in Environmental Research, found that 24% of children in the area have asthma — which is far higher than the national rate of 8.4% for boys and 5.5% for girls. The abnormally high rate raises health experts’ concerns about the children’s health in this predominantly low-income community of color 150 miles southeast of Los Angeles.
Furthermore, ...