Abstract
DeepMind started as a start-up and working on artificial intelligence (AI) technology. Established in London in September 2010 and was acquired by Google in 2014 with the acquisition price of $500 million. DeepMind’s AlphaFold digital engineers worked with advanced neural network models and proved that it could predict the 3D shapes of proteins with high accuracy in 2020. This was a groundbreaking discovery, chemists became excited about the promise of using the open-source artificial-intelligence (AI) programme for accurate 3D protein structures and use the results to discover new drugs more quickly and cheaply. Predicting the 3D structure of a protein from its 1D amino acid sequence was a revolutionary scientific discovery. DeepMind’s AlphaFold digital engineers worked with advanced neural network models and proved that it could predict the 3D shapes of proteins with high accuracy in 2020. This was a groundbreaking discovery, chemists became excited about the promise of using the open-source artificial-intelligence (AI) programme for accurate 3D protein structures and use the results to discover new drugs more quickly and cheaply. Predicting the 3D structure of a protein from its (one dimensional) amino acid sequence was fundamental scientific discovery. These results created the AlphaFold Protein Structure Database (AlphaFold DB) to freely share this scientific knowledge with the world scientists. In July 2022, DeepMind announced that over 200 million predicted protein 3D structures, representing virtually all known proteins, would be released on the AlphaFold database. The company merged with Google AI‘s Google Brain division to become Google DeepMind in April 2023. DeepMind and EMBL’s European Bioinformatics Institute (EMBL-EBI) have partnered to create AlphaFold DB to make these predictions freely available to the scientific community. AlphaFold touted as next big thing for drug discovery — but is it? Questions remain about whether the AI tool for predicting protein structures can really shake up the pharmaceutical industry [Nature, News , 25.9.2023,. Doi: http://doi.org/10.1038/d41586-023-02982-w]. This accomplishment was made possible by several other enabling discoveries, including the predicted structures derived from the AlphaFold2 database for more than 15,000 human proteins containing more than 80,000 potential binding pockets, This review some of the most important articles and reviews of the last 5 years on the subject of 3D protein structures by Ai platforms and their application in new drug discoveries. AlphaFold touted as next big thing for drug discovery — but is it? Questions remain about whether the AI tool for predicting protein structures can really shake up the pharmaceutical industry. Recently the highly informed journalists of the prestigious scientific journal Nature explained the complicated issues with very interesting and analytical reviews.