{"resourceId":"phys-org-ai-designed-proteases-hit-rates-202610","versions":[{"version":"external-d4902eb0918c6156a6426258d33959d95a0e02e0db00eb6460b954fa0398eaaa","resource":{"id":"phys-org-ai-designed-proteases-hit-rates-202610","title":"AI-designed proteases: 13 of 69 cysteine and 36% of 135 zinc protease designs cut their targets in laboratory tests","organization":"Phys.org (Science X) reporting on University of Washington (Baker lab) Nature papers","sector":"Higher education life-science research","geography":"United States","publishedAt":"16 October 2026","publicationDate":"2026-10-16","eventDate":null,"sourceName":"Phys.org","sourceLabel":"Phys.org research news report","sourceUrl":"https://phys.org/news/2026-10-ai-molecular-scissors-protein.html","evidenceClass":"independent-reporting","outcomeClass":"effective","topics":["knowledge-work","infrastructure"],"finding":"David Baker's group combined RFdiffusion2 (RFD2-MI), ProteinMPNN/EnhancedMPNN and AlphaFold 3 to design proteases from scratch, then tested them in bacteria. Of 69 cysteine protease designs, 13 cut their targets; 36% of 135 zinc protease designs did. AI-guided refinement made the top zinc protease cut 30 times faster, and some designs cut disease-relevant targets such as TDP-43. The enzymes have not been tested in human clinical trials.","sledRelevance":"Shows a university lab pipeline where compute-heavy AI design is judged by experimental hit rates. It is relevant to research computing capacity planning and to how research offices describe validated versus computational claims.","evidence":"Secondary news report (Phys.org, 16 Oct 2026, edited and reviewed) of two Nature papers (DOIs 10.1038/s41586-026-11143-w and 10.1038/s41586-026-11167-2). Opened the report only; the underlying Nature papers were not opened in this run.","architectureImplications":"The workflow chains several AI models, structure prediction checks and wet-lab assays, implying GPU capacity plus tight links between computation and experimental teams.","governanceImplications":"Report experimental hit rates alongside computational claims, and keep clear that clinical relevance is not demonstrated.","securityPrivacyImplications":"Not addressed by the report. Biological design tools raise dual-use questions that the report does not discuss.","caveats":"Secondary reporting; figures were not checked against the Nature papers. Hit rates are for bench cleavage of designed targets in bacteria-produced constructs, not therapeutic effect. Lab-specific, with unreported compute cost.","streamIds":["research"],"roles":{"sales":"Frame this as validated lab results from a university pipeline, not generic AI hype: 13 of 69 cysteine designs and 36% of 135 zinc designs worked at the bench, and the enzymes are not yet human-tested. Interpretation: it supports conversations with life-science research computing and core-facility buyers about GPU capacity and compute-to-lab handoffs. It cannot support claims about speed-to-market, therapeutic value or cost, and it comes from a news report of the papers.","engineering":"The pipeline strings together generative backbone design, sequence design, AlphaFold 3 structure checks and a bacterial cleavage assay. Interpretation: pre-sales should scope GPU queues, model licensing and a path to move candidate lists to wet-lab assay teams. Limits: the report gives no compute figures, job sizes or software versions, and the underlying Nature papers were not opened here.","delivery":"Delivery work centres on connecting compute and bench teams: candidate lists out, assay results back, refinement rounds repeated. Interpretation: assign a joint owner across research computing and the lab, track hit rate per round, and keep model and data provenance. Limited applicability: the report describes one lab's methods and says nothing about staffing, budgets or timelines."},"roleDetails":{"sales":{"customerProblem":"Life-science groups need AI design compute tied to measurable laboratory validation, and administrators need to describe results accurately.","stakeholders":["Research computing director","Core facility managers","Principal investigators in biochemistry and structural biology","Office of research communications"],"discoveryQuestions":["How are GPU hours currently allocated to design workloads?","How do computational candidates reach assay teams and results return?","How are experimental hit rates reported externally?"],"valueHypothesis":"Predictable GPU access and a defined compute-to-assay loop could shorten design-test cycles; the report does not measure cycle time or cost.","potentialEngagement":"A capacity and workflow assessment for one structural-biology or protein-design group.","unsupportedClaims":["Clinical or therapeutic benefit","Time or cost savings","That hit rates generalise to other enzyme classes or labs"]},"engineering":{"fit":"Fits GPU-heavy protein design groups with an assay partner; not a generic enterprise workload.","architectureIntegration":"Chain design models, structure prediction and ranking on GPU queues; export candidate sets to assay teams and ingest results for the next round.","prerequisites":["GPU capacity and scheduler policies","Licences and terms for the named models","Candidate and assay data tracking"],"constraints":["Compute and software details not reported","Secondary source","Biosecurity review expectations not stated"],"security":"Report does not discuss security; add dual-use and data-access review for biological design work.","proofOfValue":["Replicate a small design-test round and compare hit rate to the reported 13 of 69","Measure GPU hours per candidate that passes the assay","Check that candidate lists and results are traceable"]},"delivery":{"work":"Set up a recurring compute-to-assay workflow with shared tracking between research computing and a wet lab.","dependencies":["GPU allocation","Assay capacity","Model licences"],"ownership":"Principal investigator with the research computing lead as operational owner of the pipeline.","skillsAdoption":"Computational and bench staff need shared vocabulary for candidates, hit rates and failure modes.","governanceCheckpoints":["Biosafety and dual-use review before design campaigns","Review of reported hit rates against raw assay data","Provenance records for model versions"],"acceptanceCriteria":["Proposed: each round logs candidates, assay results and model versions","Proposed: hit rate is reported per round","Proposed: claims distinguish bench results from clinical relevance"],"risks":["Overstating results beyond bench assays","Compute bottlenecks stall rounds","Unclear ownership across compute and lab teams"]}},"retrievedAt":"2026-10-18T05:24:24-05:00","enrichedAt":"2026-10-18T05:24:24-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Needs staff who span AI model operation and assay work; the report says nothing on training or workforce.","procurementImplications":"Capacity planning should include GPU queues and model licensing; the report gives no cost data.","operatingModelImplications":"Success depends on a repeated compute-to-assay loop with shared ownership, not on computation alone.","sourceVerification":{"openedUrl":"https://phys.org/news/2026-10-ai-molecular-scissors-protein.html","referenceExcerpt":"Out of the 69 cysteine protease candidates, 13 successfully cut their targets.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}