![\"A](\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/02\/d41586-026-00365-7_52074748.jpg\"\/)
<\/p>\n <\/p>\n
The AI tool includes predictions of how proteins interact with potential therapeutic molecules.Credit: Isomorphic Labs<\/p>\n
Nearly two years after Google DeepMind released an updated AlphaFold3 geared at drug discovery<\/a>, its biopharmaceuticals spin-off, Isomorphic Labs, announced an even more powerful artificial-intelligence model \u2014 and they\u2019re keeping it all to themselves.<\/p>\n Isomorphic Labs, based in London, touted the capacities of its \u2018drug-discovery engine\u2019 \u2014 which it calls IsoDDE \u2014 in a 27-page technical report, released on 10 February<\/a>. Achievements, including precise predictions of how proteins interact with potential drugs and antibody structures, have impressed scientists working in the field.<\/p>\n Yet unlike the AlphaFold AI systems for predicting protein structure \u2014 which were made accessible to other researchers and described in depth in journal articles1<\/a>,2<\/a> \u2014 IsoDDE is proprietary, and the technical paper offers scant insight into how to achieve similar results.<\/p>\n AlphaFold is five years old \u2014 these charts show how it revolutionized science<\/p>\n <\/a><\/p>\n \u201cIt\u2019s a major advance, on the scale of an AlphaFold4,\u201d referring to an unreleased future generation of Google DeepMind\u2019s technology,says Mohammed AlQuraishi, a computational biologist at Columbia University in New York City who is working to develop fully open-source versions of AlphaFold. \u201cThe problem, of course, is that we know nothing of the details.\u201d<\/p>\n Drug\u2013protein interactions <\/p>\n AlphaFold 3 was developed with drug discovery in mind. Unlike its Noble-prizewinning predecessor AlphaFold2<\/a>, the model could predict the structures of proteins interacting with other molecules \u2014 including potential drugs.<\/p>\n Similar AIs modelled after AlphaFold 3<\/a> have come close to fully matching its performance and have new capabilities. An open-source model called Boltz-2, developed by scientists at the Massachusetts Institute of Technology in Cambridge and released last year3<\/a>, could predict the strength to which potential drugs glom onto proteins, or binding affinity. This is a key property for developing therapeutics and is usually predicted with computationally intensive physics-based methods.<\/p>\n![\"\"](\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/02\/d41586-026-00365-7_51790766.jpg\"\/)
<\/p>\n