[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-ai-model-learns-biology-from-cell-experiments-not-text":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},5457,"new-ai-model-learns-biology-from-cell-experiments-not-text","New AI Model Learns Biology From Cell Experiments, Not Text","PertMind teaches an AI biological reasoning by training it on real cell experiment data instead of hand-written examples.","A new AI model learns how cells respond to genetic and chemical tweaks by training directly on lab data, not on someone's written summary of the science.\n\nResearchers built PertMind, a large language model refined with reinforcement learning on cellular perturbation atlases - large databases recording how cells react when a specific gene is switched off, mutated, or hit with a drug. Instead of hand-curated reasoning examples, the measured gene responses themselves supplied the reward signal, scored at the level of individual genes, whole pathways, and answer format. The model was trained on a single task, predicting how a cell responds to one perturbation, but it then handled jobs it never explicitly practiced: figuring out which perturbation caused an observed change, reasoning about two perturbations applied together, ranking candidates from phenotypic screens, and explaining the biological process behind a result.\n\nThat transfer is the interesting part. Most biological AI still depends on someone writing out expert reasoning chains for a model to imitate, which is slow and expensive to scale. Grading the model against real experimental outcomes instead means the training signal grows automatically as perturbation atlases expand, with no new text required.\n\nIt is the same trick that made models better at math and code - reward the right answer, skip the hand-holding - now aimed at cell biology, where the right answer is a lab measurement instead of a unit test.","[\"reinforcement-learning\",\"biology\",\"llm\",\"research\"]","2026-08-18T04:00:00.000Z","2026-08-18T21:01:45.410Z","2026-08-18T21:01:57.317Z","published",null,[],"ai",[26,27,28,29],"reinforcement-learning","biology","llm","research",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.16419",0,{"sections":36},[37,41,45,50,55,60,65,70,75,79,84,89,94,99],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",3293,"2026-08-20T04:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":40},"Security","security",435,{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",210,"2026-08-19T09:32:27.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",140,"2026-08-19T18:25:42.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Science","science",90,"2026-08-19T18:41:02.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":18},"Dev Tools","dev-tools",69,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Startups","startups",47,"2026-08-19T19:13:46.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",33,"2026-08-18T22:18:13.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]