(Press-News.org)
Researchers at the University of Toronto have developed an artificial intelligence system that can create proteins not found in nature using generative diffusion, the same technology behind popular image-creation platforms such as DALL-E and Midjourney.
The system will help advance the field of generative biology, which promises to speed drug development by making the design and testing of entirely new therapeutic proteins more efficient and flexible.
“Our model learns from image representations to generate fully new proteins, at a very high rate,” says Philip M. Kim, a professor in the Donnelly Centre for Cellular and Biomolecular Research at U of T’s Temerty Faculty of Medicine. “All our proteins appear to be biophysically real, meaning they fold into configurations that enable them to carry out specific functions within cells.”
Today, the journal Nature Computational Science published the findings, the first of their kind in a peer-reviewed journal. Kim’s lab also published a pre-print on the model last summer through the open-access server bioRxiv, ahead of two similar pre-prints from last December, RF Diffusion by the University of Washington and Chroma by Generate Biomedicines.
Proteins are made from chains of amino acids that fold into three-dimensional shapes, which in turn dictate protein function. Those shapes evolved over billions of years and are varied and complex, but also limited in number. With a better understanding of how existing proteins fold, researchers have begun to design folding patterns not produced in nature.
But a major challenge, says Kim, has been to imagine folds that are both possible and functional. “It’s been very hard to predict which folds will be real and work in a protein structure,” says Kim, who is also a professor in the departments of molecular genetics and computer science at U of T. “By combining biophysics-based representations of protein structure with diffusion methods from the image generation space, we can begin to address this problem.”
The new system, which the researchers call ProteinSGM, draws from a large set of image-like representations of existing proteins that encode their structure accurately. The researchers feed these images into a generative diffusion model, which gradually adds noise until each image becomes all noise. The model tracks how the images become noisier and then runs the process in reverse, learning how to transform random pixels into clear images that correspond to fully novel proteins.
Jin Sub (Michael) Lee, a doctoral student in the Kim lab and first author on the paper, says that optimizing the early stage of this image generation process was one of the biggest challenges in creating ProteinSGM. “A key idea was the proper image-like representation of protein structure, such that the diffusion model can learn how to generate novel proteins accurately,” says Lee, who is from Vancouver but did his undergraduate degree in South Korea and master’s in Switzerland before choosing U of T for his doctorate.
Also difficult was validation of the proteins produced by ProteinSGM. The system generates many structures, often unlike anything found in nature. Almost all of them look real according to standard metrics, says Lee, but the researchers needed further proof.
To test their new proteins, Lee and his colleagues first turned to OmegaFold, an improved version of DeepMind’s software AlphaFold 2. Both platforms use AI to predict the structure of proteins based on amino acid sequences.
With OmegaFold, the team confirmed that almost all their novel sequences fold into the desired and also novel protein structures. They then chose a smaller number to create physically in test tubes, to confirm the structures were proteins and not just stray strings of chemical compounds.
“With matches in OmegaFold and experimental testing in the lab, we could be confident these were properly folded proteins. It was amazing to see validation of these fully new protein folds that don’t exist anywhere in nature,” Lee says.
Next steps based on this work include further development of ProteinSGM for antibodies and other proteins with the most therapeutic potential, Kim says. “This will be a very exciting area for research and entrepreneurship,” he adds.
Lee says he would like to see generative biology move toward joint design of protein sequences and structures, including protein side-chain conformations. Most research to date has focussed on generation of backbones, the primary chemical structures that hold proteins together.
“Side-chain configurations ultimately determine protein function, and although designing them means an exponential increase in complexity, it may be possible with proper engineering,” Lee says. “We hope to find out.”
END
(MEMPHIS, Tenn. – May 04, 2023) Despite the astounding advances made in understanding the biologic underpinnings of cancer, many cancers are missing obvious genetic drivers. When scientists can’t pinpoint the factors that drive cancer, treating it can be much more difficult. Scientists at St. Jude Children’s Research Hospital hope to solve that problem with an updated way to analyze multi-omic (primarily transcriptomics and proteomics) data. The researchers created a next-generation computational tool to gain new insights from biological data ...
Cells have a fascinating feature to neatly organize their interior by using tiny protein machines called molecular motors that generate directed movements. Most of them use a common type of fuel, a kind of chemical energy, called ATP to operate. Now researchers from the Max Planck Institute of Molecular Cell Biology and Genetics (MPI-CBG), the Cluster of Excellence Physics of Life (PoL) and the Biotechnology Center (BIOTEC) of the TU Dresden in Dresden, Germany, and the National Centre for Biological Sciences (NCBS) in Bangalore, India, discovered a novel molecular system that uses an alternative chemical energy and employs a novel mechanism ...
For decades, scientists have looked to seaweed as an indicator of the health of coral reefs lying underneath.
But what if the seaweed was misleading them?
New UBC research reveals it was, and scientists need new ways to determine whether human activity is harming a particular reef.
"This is especially critical today, given that reefs globally are threatened by climate-driven stressors,” said Dr. Sara Cannon, a postdoctoral fellow at the UBC Institute for the Oceans and Fisheries and the study's lead author.
Local species ...
Perovskite solar cells (PVSCs) are a promising alternative to traditional silicon-based solar cells because of their high power-conversion efficiency and low cost. However, one of the major challenges in their development has been achieving long-term stability. Recently, a research team from City University of Hong Kong (CityU) made a breakthrough by developing an innovative multifunctional and non-volatile additive which can improve the efficiency and stability of perovskite solar cells by modulating perovskite film growth. This simple and effective strategy has great potential for facilitating the commercialisation of PVSCs.
“This type of multifunctional ...
Evidence from West Africa about human evolution remains scarce, but recent research has indicated unique patterns of cultural change in comparison to other regions of the continent. A new article in the journal Nature Ecology and Evolution adds to our understanding with a study of the oldest directly dated archaeological site in West Africa. The site shows technological continuity spanning roughly 140,000 years and offers insights into the ecological stability of the region.
Our species emerged in Africa around 300 thousand years ago and ...
BRONX, NY—May 4, 2023—Acute radiation dermatitis (ARD)—characterized by red, sore, itchy or peeling skin—affects up to 95% of people undergoing radiation treatment for cancer. Severe cases can cause significant swelling and painful skin ulcers that can severely impair quality of life, yet little is known about why this condition occurs and no standardized treatments for preventing severe ARD have been widely adapted.
Researchers at Montefiore Einstein Cancer Center (MECC) have found that many cases of ARD involve a common skin bacterium and that a simple, low-cost treatment ...
SEATTLE, WA — May 4, 2023 — A new Fred Hutchinson Cancer Center study in the journal Obstetrics & Gynecology investigated how endometriosis, uterine leiomyomas (also known as fibroids) and a common intervention for these conditions—hysterectomy—changed ovarian cancer risk in Black and white women.
Scientists found fibroids were associated with an increased risk of ovarian cancer in both Black and white women, with hysterectomy modifying the risk of cancer in both groups. However, researchers also found that while Black and white women with endometriosis had a higher risk of ovarian cancer overall, hysterectomy only ...
Vanishing glaciers threaten alpine biodiversity
With glaciers melting at unprecedented rates due to climate change, invertebrates that live in the cold meltwater rivers of the European Alps will face widespread habitat loss, warn researchers.
Many of the species are likely to become restricted to cold habitats that will only persist higher in the mountains, and these areas are also likely to see pressures from the skiing and tourism industries or from the development of hydroelectric plants.
The research study – led jointly by the University of Leeds and ...
BIRMINGHAM, Ala. – Neuropathic pain — abnormal hypersensitivity to stimuli — is associated with impaired quality of life and is often poorly managed. Estimates suggest that 3 percent to 17 percent of adults suffer from neuropathic pain, including a quarter of people with diabetes and a third of people with HIV.
In a paper published in the journal Neuron, researchers report that a mechanism involving the enzyme Tiam1 in dorsal horn excitatory neurons of the spinal cord both initiates and maintains neuropathic pain. Moreover, they show that targeting spinal Tiam1 with anti-sense oligonucleotides injected ...
Researchers at Baylor College of Medicine and collaborating institutions have identified a strategy cancerous tumors use to remotely disrupt the development of an immune response that could stop their growth.
Published in the journal Cell Stem Cell, the study shows in animal models that breast cancer tumors send molecular signals to the bone marrow, the birthplace of immune cells. The signals alter the natural environment of the bone marrow in such a way that it suppresses the response to fight back the tumor. Interestingly, ...