Machine learning delivers ‘human genome’ moment for proteins

An image of a protein structure appearing as blue and teal coloured helices and swirly patterns

Source: © DeepMind

Protein structure prediction tools AlphaFold and RoseTTAFold take the latest steps towards maturity and make their software open source

Scientific fields from drug discovery to plastic recycling have been transformed after artificial intelligence (AI)-based protein structure prediction researchers shared an enormous dataset and opened up their methods. On 22 July, London, UK-based Google offshoot DeepMind and the European Molecular Biology Laboratory (EMBL) released 350,000 protein structures computed by its AlphaFold system. These include all 20,000 proteins from the human proteome and will be followed by over 100 million more.