Meta, the parent company of Facebook and Instagram, has made a major technological breakthrough with the development of ESMFold. This AI-based computer program can predict the structure of millions of proteins. This achievement could revolutionize the development of pharmaceuticals. The Wall Street Journal reports that Meta AI, the company's research department, has used ESMFold to create a public database containing the predicted structure of 617 million proteins. Proteins are composed of long chains of amino acids, and a DNA genome determines their structures. In the human body, proteins play a critical role in the function of cells and organs. [tweet_embed]March 17, 2023[/tweet_embed] Pharmaceutical companies use proteins to develop drugs that treat many ailments and diseases, including some types of cancer, HIV, and heart disease. The use of AI in creating new drugs for diseases, some of which currently have no cure, is a growing trend. Google's parent company, Alphabet, has also developed its own AI program, AlphaFold, that predicts protein structure through its subsidiary company DeepMind Technologies. ESMFold, according to Meta, is less accurate than AlphaFold but faster, producing roughly one-third of predictions with high confidence. A study on ESMFold published in Science magazine, co-authored by Alexander Rives, a Meta research scientist, stated that proteins with similar structures usually have similar biological functions. With high-resolution structure predictions, the biochemical functions of these proteins can be analyzed. ESMFold uses the same large language model technology as OpenAI's ChatGPT. To generate predicted protein structures, ESMFold must be fed letters representing amino acids, and it learns as it goes by comparing its generated proteins to those that already exist. However, Olexandr Isayev, a computational biologist at Carnegie Mellon University, pointed out that ESMFold's success relies heavily on prior work. This technological breakthrough in protein structure prediction has enormous implications for the pharmaceutical industry. With the ability to predict protein structure accurately, drug development could be revolutionized, leading to the creation of new drugs for diseases that were previously incurable.