For half a century, predicting how protein folds into its unique three-dimensional shape has puzzled scientists and is also one of the major challenges in biology.
But experts announced that one of the biggest mysteries in the biological world is now essentially solved by artificial intelligence AI.
DeepMind (Deep Thinking), a British artificial intelligence company based in London, said they “basically solved this problem.”
Improved understanding and prediction of protein shapes will play a key role in the future development of new drugs. The technological advances made by DeepMind, a subsidiary of Google, are expected to accelerate research on a range of diseases, including the new crown.
Some independent scientists from the United States noted that the accuracy of DeepMind’s system for protein shape prediction is similar to those expensive and time-consuming laboratory methods.
Dr. Andriy Kryshtafovych of the University of California, Davis, a member of the scientific jury, described DeepMind’s achievement as “outstanding.”
Dr. Krestavovich that fast and accurate protein shape counting has the potential to revolutionize life sciences.
What is the shape of a protein?
Protein exists in all organisms and is the basis for cell survival. They play a central role in the chemical processes that are essential to life.
Proteins consist of polypeptide chains formed by the combination of amino acids in a specific order. They are folded into various delicate shapes in countless ways, and this is the key to their important role in the body.
Many diseases are linked to the role proteins play. For example, they can become enzymes that trigger chemical reactions, antibodies to fight disease, or the insulin hormone as a chemical messenger.
Dr. John Moult of the University of Maryland chairs the scientific jury. He explained that even a small rearrangement of these protein molecules would have a disastrous effect on human health. Therefore, to understand diseases and find new treatments, proteins need to be studied.
Mort further explained that there are thousands of human proteins alone, and there are billions of proteins in other species, including proteins from bacteria and viruses. Right now, just trying to interpret the shape of a protein requires years of time and expensive equipment.
In 1972, American biologist Christian Anfinsen won the Nobel Prize for his research on the relationship between amino acid sequence and biologically active conformation.
Anfinsen believes that it should be possible to determine the shape of a protein based on the sequence of its constituent amino acids.
Since then, every two years, dozens of research teams in more than 20 countries around the world have tried to get computers to predict the shapes of about 100 proteins through amino acid sequences.
At the same time, biologists use traditional techniques such as X-ray crystallography and nuclear magnetic resonance spectroscopy (NMR spectroscopy) to determine the three-dimensional structure of proteins in the laboratory to understand each protein molecule. The relative position of an atom.
Thereafter, a dedicated CASP team made up of scientists (equivalent to the Community Critical Assessment Experiment of Techniques for Protein Structure Prediction) used the computer to predict the three-dimensional structure of the protein and use the laboratory. The three-dimensional structure results obtained by the method are compared.
The CASP review team used a 0-100 measurement method to compare each team’s forecast accuracy. DeepMind’s artificial intelligence, AlphaFold, scored 90 points, which is comparable to the results predicted by the lab.
The speed of AI learning is incredible
In the latest round of prediction results (Casp-14), the accuracy of two-thirds of the protein shape predicted by AlphaFold was consistent with laboratory results. While some other prediction results scored high, they did not reach the same level of accuracy.
AlphaFold uses deep learning algorithms to learn and study known three-dimensional shapes of proteins stored in global databases. The structure of these folding proteins is presented in a spatial diagram.
BBC Science Affairs reporter Helen Briggs said the pace of AI learning was incredible, and it takes a few days to reach the level of research in the lab for decades.
Usage and meaning
Determining the three-dimensional structure of proteins is essential for the development of new drugs and the understanding of cancer, dementia and infectious diseases.
Taking the new crown as an example, scientists have been trying to study how the spike protein on the surface of the new crown virus interacts with receptors in human cells.
Professor Martin of University College London told the BBC correspondent that understanding how protein sequences fold into three-dimensional shapes is actually one of the most fundamental problems in biology. He explained that protein function depends entirely on its three-dimensional structure and shape, and protein function is linked to everything about our health and disease.
Therefore, understanding the three-dimensional structure of proteins helps people design new drugs and prevent and treat diseases, whether it is genetic or infectious.
One of the greatest mysteries of biology
Professor Dame Janet Thornton of the European Bioinformatics Institute said that folding proteins into unique and beautiful three-dimensional structures is one of the greatest mysteries in biology.
He explained that if we can better understand and predict protein structure, it means that humans will have a better understanding of life, evolution, disease and health and other issues.
Next, more scientists hope to test these data to determine the accuracy and precision of the AI method.
Currently, there are still gaps in human knowledge about proteins, including how many types of proteins are combined together, and how proteins interact with other molecules, such as deoxyribonucleic acid (DNA) and ribonucleic acid (RNA).
Dr. Krestavovich reported that the structural problem of a single protein is now essentially resolved. It opens the door to new ways of finding the future shape of protein complex structures. It is the co-operation of these numerous protein complexes that form the main mechanism of life and other functions.