The AI group DeepMind has revealed the structures of nearly every protein known to science.
The researchers achieved this feat using AlphaFold software, first developed by DeepMind in 2018 and released to the public in July 2021. The open-source software can predict the 3D structure of a protein from the sequence of amino acids, the building blocks that make up proteins. a proteinProtein structure dictates its functionality, so the database of 200 million protein structures identified by AlphaFold has the potential to help identify new protein groups that humans can benefit from.
For example, the database may include proteins that can help recycle plastic, according to Watchman (Opens in a new tab).
“It took us a long time to go through this huge database of structures, but [it] Unlocking this whole range of new 3D shapes we’ve never seen before that can actually break plastic,” John McGeehan, professor of structural biology at the University of Portsmouth in the UK, told The Guardian. There is a complete model makeover. We can really speed up where we’re going from here — and that helps us direct these precious resources to the things that matter.”
Dive deep into proteins
Proteins are like enigmatic little puzzles. They are produced by organisms ranging from bacteria From plants to animals, when made, they collapse in milliseconds, but their structures are so complex that trying to guess what shape they will take is almost impossible. Cyrus Leventhal, an American molecular biologist, pointed out the paradox that proteins fold quickly and precisely despite huge numbers of potential configurations. In a paper in 1969 (Opens in a new tab)estimating that a given protein may have 10^300 potential end-forms..
Thus, Leventhal wrote, if one tried to get to the correct protein conformation by trying each configuration one by one, it would take longer than Universe exist yet to arrive at the correct answer.
Scientists have ways of visualizing proteins and analyzing their structure, but this is a slow and difficult work. The most common way to image proteins is through X-ray crystallography, according to the journal temper nature (Opens in a new tab)involving cheery X ray in solid crystals of proteins and measure how these rays are deflected to determine how the protein is arranged. This experimental work identified the shape of about 190,000 proteins, according to deep mind (Opens in a new tab).
Last year, DeepMind made predictions about what the protein might look like for Every protein in the human body And in 20 research types, Live Science previously reported. Now, they’ve extended those expectations to basically everything proteins.
“This update includes the predicted structures of plants, bacteria, animals and other organisms, opening many new opportunities for researchers to use AlphaFold to advance their work on important issues, including sustainability, food insecurity and neglected diseases,” DeepMind representatives said in a statement (Opens in a new tab).
action of proteins
AlphaFold works by accumulating knowledge about amino acid sequences and interactions as it attempts to explain protein structures. The algorithm can now predict protein shapes in minutes with accuracy down to the level atoms.
Researchers are already using the fruits of AlphaFold’s work. According to The Guardian, the program enabled researchers to finally discern a key malaria parasite protein (Opens in a new tab) which were not amenable to X-ray crystallography. The researchers told the Guardian that this could improve the development of a vaccine against the disease.
At the Norwegian University of Life Sciences, honey bee researcher Vilde Leipart used AlphaFold to reveal the structure of vitellogenin — a reproductive and immune protein made by all eggs that lay eggs. Liepart writes that this discovery may lead to new ways to protect important egg-laying animals such as honeybees and fish from disease. Blog post for DeepMind (Opens in a new tab).
The program is also informing the search for new drugs, Rosanna Kappeler, CEO of ROME Therapeutics, said in a DeepMind statement.
“The speed and accuracy of AlphaFold speeds up the drug discovery process,” said Cappeler.
“And we’re just beginning to realize its impact in getting new drugs to patients faster.”
Originally published on Live Science.