\n<\/p>\n
February 21, 2026<\/p>\n
3 min read<\/p>\n
Add Us On Google<\/span>Add SciAm<\/span><\/span><\/p>\n \u2018An AlphaFold 4\u2019\u2014scientists marvel at DeepMind drug spin-off\u2019s exclusive new AI<\/p>\n Isomorphic Lab\u2019s proprietary drug-discovery model is a major advance, but scientists developing open-source tools are left guessing how to achieve similar results<\/p>\n The AI tool includes predictions of how proteins interact with potential therapeutic molecules.<\/p>\n Nearly two years after Google DeepMind released an updated AlphaFold3 geared at drug discovery, 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. 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 articles \u2014 IsoDDE is proprietary, and the technical paper offers scant insight into how to achieve similar results.<\/p>\n If you’re enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.<\/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 AlphaFold 3 was developed with drug discovery in mind. Unlike its Nobel-prizewinning predecessor AlphaFold2, the model could predict the structures of proteins interacting with other molecules \u2014 including potential drugs.<\/p>\n Similar AIs modelled after AlphaFold 3 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 year, 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 According to Isomorphic\u2019s report, its new AI outperforms both Boltz-2 and physics-based methods at determining binding affinity. Predictions of how antibodies \u2014 which form the basis for therapies that rack up tens of billions of pounds in sales annually \u2014 interact with their targets is also state of the art, the report claims.<\/p>\n AlQuraishi says he is especially impressed by the IsoDDE\u2019s ability to predict drug\u2013protein interactions of molecules that are vastly different from the data that the model was trained on. \u201cThat\u2019s the really hard problem, and suggests that they must\u2019ve done something pretty novel,\u201d he says.<\/p>\n The models behind IsoDDE are \u201cprofoundly different\u201d from other efforts, says Max Jaderberg, Isomorphic\u2019s president. But the company has no plans to reveal the \u2018secret sauce\u2019 behind it. \u201cLike with most big machine-learning and AI advancements, it’s a combination of compute, data [and] algorithms,\u201d Jaderberg adds. He hopes his team\u2019s report will \u201cgalvanize\u201d the efforts of other teams building drug-discovery AIs.<\/p>\n “This report comes after extensive efforts to partner with industry and potentially access their private structural data, so we don\u2019t know how impactful that extra data is\u201d to IsoDDE\u2019s performance, Diego del Alamo, a computational structural biologist at Takeda Pharmaceuticals, who is based in Cambridge, wrote on the social-media site X.<\/p>\n Isomorphic has struck drug-development deals, potentially worth billions of pounds, with pharmaceutical companies Johnson and Johnson, Eli Lilly and Novartis. It also has its own internal pipeline, with clinical trials on the horizon. Jaderberg says that the company has developed different versions of IsoDDE from the one used for the technical report, including for work with its partners, that incorporate different data sources.<\/p>\n His colleague Michael Schaarschmidt, Isomorphic\u2019s director of machine learning, says the company\u2019s data strategy is \u201cquite comprehensive,\u201d incorporating publicly available data, synthetic training data and data sources that they will \u201ctry to lisense.\u201d<\/p>\n Gabriele Corso, a machine-learning scientist who co-developed Boltz-2 and now leads the non-profit company Boltz in London, does not think that proprietary data played an essential part in the reported performance of Isomorphic\u2019s tool, on the basis of gains his team is seeing. \u201cThere are a lot of improvements we can make with the data that are out there,\u201d he says. \u201cI think this is a new baseline to match \u2014 but also to pass.\u201d<\/p>\n This article is reproduced with permission and was first published on February 19, 2026.<\/p>\n If you enjoyed this article, I\u2019d like to ask for your support. Scientific American<\/span> has served as an advocate for science and industry for 180 years, and right now may be the most critical moment in that two-century history.<\/p>\n I\u2019ve been a Scientific American<\/span> subscriber since I was 12 years old, and it helped shape the way I look at the world. SciAm <\/span>always educates and delights me, and inspires a sense of awe for our vast, beautiful universe. I hope it does that for you, too.<\/p>\n If you subscribe to Scientific American<\/span>, you help ensure that our coverage is centered on meaningful research and discovery; that we have the resources to report on the decisions that threaten labs across the U.S.; and that we support both budding and working scientists at a time when the value of science itself too often goes unrecognized.<\/p>\n In return, you get essential news, captivating podcasts, brilliant infographics, can’t-miss newsletters, must-watch videos, challenging games, and the science world’s best writing and reporting. You can even gift someone a subscription.<\/p>\n There has never been a more important time for us to stand up and show why science matters. I hope you\u2019ll support us in that mission.<\/p>\n","protected":false},"excerpt":{"rendered":" February 21, 2026 3 min read Add Us On GoogleAdd SciAm \u2018An AlphaFold 4\u2019\u2014scientists marvel at DeepMind drug spin-off\u2019s exclusive new AI Isomorphic Lab\u2019s proprietary drug-discovery model is a major advance, but scientists developing open-source tools are left guessing how to achieve similar results By Ewen Callaway & Nature magazine The AI tool includes predictions<\/p>\n","protected":false},"author":1,"featured_media":44920,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[58],"tags":[23221,23220,19402,252,6527,4683,23222],"class_list":{"0":"post-44919","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-science","8":"tag-4scientists","9":"tag-alphafold","10":"tag-deepmind","11":"tag-drug","12":"tag-exclusive","13":"tag-marvel","14":"tag-spinoffs"},"_links":{"self":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/posts\/44919","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=44919"}],"version-history":[{"count":0,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/posts\/44919\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/media\/44920"}],"wp:attachment":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=44919"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=44919"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=44919"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}On supporting science journalism<\/h2>\n
Drug\u2013protein interactions<\/h2>\n
Secret sauce<\/h2>\n
It\u2019s Time to Stand Up for Science<\/h2>\n