According to a recent report on the website of the British “New Scientist” magazine, the British-based artificial intelligence company “Deep Mind” announced that it will publish the structures of more than 200 million proteins. In just 18 months, the company’s “Alpha Fold” algorithm has predicted the structure of nearly every protein catalogued to date, cracking one of biology’s greatest challenges, and will help tackle antibiotic resistance, accelerate Drug development and revolutionize basic science.
Determining the shape of a protein from its amino acid sequence has been a challenge in biology for decades. At the end of 2020, “Deep Mind” announced that the company’s “Alpha Fold” algorithm can accurately predict the structure of folded proteins; by mid-2021, the artificial intelligence has been able to map 98.5% of the proteins in the human body. Recently, the company announced that it will publish the structures of more than 200 million proteins, almost all of which have been compiled into UniProt, a globally recognized protein research library.
“Deep Mind” is also cooperating with the European Institute of Bioinformatics under the European Molecular Biology Laboratory to create a searchable database “Alpha Fold Protein Structure Database”. Becomes almost as easy as a web search tool.
Many scientists are using “alpha folds” to advance research in many fields. For example, Matt Higgins of Oxford University and others are studying a protein they believe is a key to interrupting the life cycle of malaria parasites, hoping to develop an effective malaria vaccines; it has also been used by scientists to design new enzymes to break down plastic waste and learn more about the proteins that make bacteria resistant to antibiotics.
Keith Williamson of Imperial College London said Alpha Folding has transformed biological research, but there are still some problems, such as its inability to extract arbitrary amino acid sequences and accurately model how they fold, nor to reveal how proteins are structured. complex interactions, and in addition, its accuracy needs to be improved.
DeepMind said it is now working to improve the accuracy of the tool to learn more about how proteins are made and how cells work.
News Source: Deepmind.com
