As artificial intelligence (AI) predicts the 3D shape of nearly every protein known to science, it has ushered in a new era of biological research – just a year after we first published the data.
Thanks to AlphaFold, an artificial intelligence tool developed by Google-owned DeepMind, more than 200 million protein structures are now shared online in a freely accessible and searchable database called AlphaFold DB.
This breakthrough paves the way for countless scientific discoveries of proteins, the building blocks of life.
Cardiologist Eric Topol of Scripps Research Translational said in a statement about the data release: “It now takes seconds to determine the 3D structure of a protein that used to take months or years.
And with the addition of these new structures that shed light on most of the protein world, we can expect to solve more and more biological puzzles every day.”
In collaboration with scientists at the European Molecular Biology Laboratory European Bioinformatics Institute (EMBL-EBI), DeepMind announced the first batch of AlphaFold predictions in July of last year.
AlphaFold was announced as a revolutionary tool to revolutionize biological research, accelerate drug discovery, and predict the 3D shape of proteins based on amino acid sequences.
Amino acid sequences are strung together into chains and store long proteins that are folded into folded sheets and twisted strips.
By understanding the way a protein folds, scientists can learn how it works and determine its key role in cells.
AlphaFold was designed to speed up this process and release more than 200 million structures estimated in this latest data for proteins found in plants, bacteria, animals and other organisms.
“This hope is becoming a reality faster than we thought,” DeepMind CEO Demis Hassabis said in a statement about the latest data release. Said.
Researchers have used the first batch of AlphaFold predictions to improve their understanding of deadly diseases like malaria, open the door to advanced vaccines, and solve biological puzzles about giant proteins that has puzzled scientists for decades. Not to mention the identification of previously unseen enzymes that could aid in the plastic pollution cycle.
Although the open-source AlphaFold software has been available to researchers since its launch last year, having millions of predicted protein structures in a searchable database will undoubtedly speed up the search.
According to EMBL-EBI, about a third of the more than 214 million predictions were rated as very accurate, consistent with protein structures derived from standard experimental methods such as X-ray crystallography and electron microscopy.
For decades, scientists have painstakingly extracted molecular structures from the blurry images produced by these methods – perhaps most famously the image of Rosalind Franklin’s helical DNA.
However, the quality of AlphaFold’s predictions is variable and may be less accurate for rare proteins that scientists know little about. Thus, in some cases, their predicted structure can be used to understand empirical data.
And despite the large body of data, AlphaFold missed a lot of life, including predictions about how proteins will interact when they come together.
Microbial proteins identified from traces of genetic material in soil and seawater are also not in the database – however, because scientists have cataloged only a small fraction of all microbial organisms in Earth, these microorganisms represent an untapped source for powerful compounds.
Some scientists have also expressed concerns about the staggering 23 terabytes of content that may be less accessible to some research teams due to the existence of the AlphaFold database and its excessive computing power and complex data analytics. which is required for cloud-based storage.
However, the immediate benefits to human health, which DeepMind says it has carefully weighed against the potential bioethical risks, are so great as to be almost inconceivable.
DeepMind and EMBL-EBI will continue to update the AlphaFold database periodically.
Source: Science Alert
Source: Arabic RT
