Washington [US], October 10: Yesterday (October 9), the Royal Swedish Academy of Sciences (KVA) announced the identities of three scientists awarded this year's Nobel Prize in Chemistry for their work related to protein structure prediction and design.
According to the announcement yesterday afternoon, the 2024 Nobel Prize in Chemistry worth 11 million krona (26.3 billion VND) was awarded half to Mr. David Baker at the University of Washington (USA) for his achievements in "computer-aided protein design" and the other half was jointly awarded to Mr. Demis Hassabis and Mr. John M. Jumper of Google DeepMind Company (UK) for "protein structure prediction".
Mr Hassabis and Mr Jumper have successfully used artificial intelligence (AI) to predict the structures of most known proteins, while Mr Baker has created entirely new proteins.
Protein maker
Proteins are large biological molecules, composed primarily of chains of amino acids. They play a very important role in most biological processes in the body. Proteins also have many functions such as catalysis, immunity, transport and tissue structure.
Proteins are typically made up of 20 different amino acids, also known as the building blocks of life. In 2003, Baker succeeded in using these building blocks to design an entirely new protein. Since then, his team has created protein after protein, including ones that could be used in pharmaceuticals, vaccines, nanomaterials and tiny sensors. The American computational biologist is considered a leader in a technological revolution that has the potential to transform science and medicine.
Baker has co-founded 17 companies and has been granted more than 100 patents, according to KVA. His Rosetta software is a powerful tool for modeling protein structures and designing new proteins. For his research, Baker was awarded the $3 million Breakthrough Prize in Life Sciences in 2021. The prize is awarded by a group of tech entrepreneurs, including billionaire Mark Zuckerberg, to outstanding scientists in the fields of physics, mathematics, and life sciences. In May, Baker was also named to Time magazine's list of the 100 most influential people in health .
50 year problem solved
While Mr. Baker was honored for his unprecedented protein designs, two scientists at Google DeepMind developed an AI model to solve a problem that has remained unsolved for 50 years: predicting the complex structures of proteins.
In proteins, amino acids are linked together in long chains that fold to form a three-dimensional structure that determines the protein's function. Since the 1970s, researchers have tried to predict the structure of proteins from amino acid sequences, but this has been extremely difficult.
According to El Pais , calculating all the possible shapes of a single protein using conventional methods would take more than 13.7 billion years, equal to the age of the universe. Meanwhile, there are hundreds of millions of different proteins in nature. In 2020, the AI model AlphaFold2 introduced by Hassabis and Jumper was able to predict the shapes of almost all known proteins, more than 200 million of them. This historic achievement can now be achieved in a short time thanks to deep learning systems. These algorithms mimic the way neurons in the human brain work, and while they are not yet as powerful as a real brain, they are very effective at finding patterns in huge databases. Thanks to these systems, predicting the shape of a protein can now be done in just a few minutes instead of years.
In a statement yesterday, KVA said AlphaFold2 has been used by more than 2 million people in 190 countries. Among its myriad scientific applications, researchers can now better understand antibiotic resistance and image enzymes that can break down plastic.
Source: Thanh Nien Newspaper
