{"data":{"event":{"id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","slug":"divergence-labs-claude-ige-disruptor-2026","title":"Claude-orchestrated Divergence Labs campaign produces experimental IgE-disruptor VHH hits","short_summary":"On 27 October 2026 Anthropic and Divergence Labs reported a Claude-directed campaign that generated about 35,000 VHH designs toward a biparatopic IgE disruptor for food allergy. Competitive BLI found 20/91 disruptor hits, three of which removed more soluble IgE than omalizumab at 25–400 nM, plus three de novo anchors. The arms have not been paired, cells and animals were not tested, and the designs did not beat parent sdAb026 at controlled doses.","full_description":"Divergence Labs’ preprint, released with Anthropic’s 27 October 2026 drug-development update, describes an agentic computational campaign toward a biparatopic VHH that would strip receptor-bound IgE from FcεRI rather than only neutralize circulating IgE, the mechanism of omalizumab (Xolair). Erives, Ferrara, Michael, Mallipeddi, and Jing report that Claude, guided by the research team, decomposed the objective and ran 22 near-autonomous phases, 15 of them computational design. Anthropic says Claude then generated roughly 35,000 antibody designs in about a month; the preprint’s counts are 11,845 scored disruptor redesigns of the known allosteric VHH sdAb026 and 23,587 unique de novo anchor designs (~1,140 and 1,310 H100-hours). Sequences were produced by biomolecular generative models Claude directed (inverse folding, tempered redesign, interface-geometry losses, co-fold critics), not by Claude emitting sequences unaided. Humans set the therapeutic thesis and biparatopic architecture, dropped one redesign scope, constrained linker search, and ran the assays.\n\nIn Divergence’s laboratory, competitive bio-layer interferometry on soluble FcεRIα ectodomain found 20 of 91 nominated disruptors active. After purification, variants V1, V4, and V8 removed more IgE than omalizumab at every concentration from 25 to 400 nM, but did not improve on parent sdAb026. Three of 57 de novo anchors bound IgE with apparent KD 3.4, 32.5, and 235 nM; affinities may be confounded by avidity. The two arms were not assembled into a biparatopic. No cellular disruption, anaphylactogenicity, animal, or clinical data are reported. Sequences and a public dataset were not released. The disruption mechanism is known: Excellergy has already entered phase 1 on omalizumab-derived disruptors, and sdAb026 is a published Ablynx VHH. This ledger records an experimental hit-generation result, not a food-allergy medicine. Primary sources name Claude, not a SKU; Papex’s report of Claude Mythos 5.1 is not in the preprint or Anthropic post.","ledger_type":"benefit","primary_domain_id":"8f1af1b9-7302-4b51-aae9-fdfac04d158a","event_status":"provisional","event_date":"2026-10-27T00:00:00.000Z","discovery_date":"2026-10-27T00:00:00.000Z","first_published_date":"2026-10-27T00:00:00.000Z","last_reviewed_date":"2026-10-27T00:00:00.000Z","geographic_scope":"United States protein-design laboratory (Divergence Labs) with Anthropic partnership","affected_population":"Protein-design and allergy-drug researchers; food-allergy patients only if a paired, non-anaphylactogenic biparatopic is later validated","base_impact_tier":3,"base_score":"10.00","attribution_multiplier":"0.7500","evidence_multiplier":"0.3500","realization_multiplier":"0.5000","durability_multiplier":"0.5500","current_event_score":"0.721900","confidence_level":"medium","score_explanation":"Major (tier 3, base 10) as a substantial experimentally assayed protein-design campaign, scored like AlphaProteo and the Claude scorpion-binder work, not as a food-allergy medicine. Phase 2a remains the clinical Notable floor; these are unpaired in-vitro subcomponents. Attribution 0.75: Claude was a critical orchestrator of planning and 22 near-autonomous phases, while humans chose the known sdAb026/biparatopic thesis and ran wet lab, and separate biomolecular generative models produced sequences. Evidence 0.35 is a company preprint plus partner announcement, without peer review or independent replication. Realization 0.50 is competitive BLI of soluble proteins, not cellular disruption or a assembled drug. Durability 0.55: sequences exist at Divergence and can be reused, but they are unpublished and therapeutic value is untested. Claude is the only scored AI system (credit 1.00). Score: 10 × 0.75 × 0.35 × 0.50 × 0.55 × 1.00 = 0.7219 points.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-10-27T00:00:00.000Z","created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z","flags":["Version-unspecified Claude; primary sources do not name a SKU","Company laboratory BLI on soluble FcεRIα, not independent CRO or cellular assays","Disruptor arm is a redesign of known VHH sdAb026; did not beat parent at controlled doses","Arms not paired into a biparatopic; no cells, animals, or patients","No public sequences or dataset","IgE-disruption mechanism already in the literature; Excellergy is in phase 1"],"domain_name":"Biology","domain_slug":"biology","methodology_version":"0.2"},"contributions":[{"id":"f1ac046c-9b7a-41be-81d7-ad9bbd0e9cf3","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","model_id":"059c33b6-fc2e-4d3d-acdb-c0d966ee5e6e","role_description":"Version-unspecified Claude that, guided by Divergence Labs, decomposed the IgE-disruptor objective and ran 22 near-autonomous work phases directing biomolecular design tools.","attribution_multiplier":"0.7500","credit_share":"1.0000","contribution_score":"0.721900","attribution_rationale":"The preprint and Anthropic post attribute campaign planning and largely autonomous execution of ~35,000 designs to Claude. Humans set the therapeutic goal and architecture, intervened on scope and linkers, and performed BLI. Sequence generation used biomolecular generative models Claude directed. Primary sources name Claude, not Opus, Fable, or Mythos, so identity stays version-unspecified.","attribution_confidence":"medium","first_used_date":"2026-10-27T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-10-28T20:22:47.621Z","model_slug":"claude","model_name":"Claude","identity_class":"unknown","is_internal":false,"family_name":"Claude","family_slug":"anthropic-claude","organization_name":"Anthropic","organization_slug":"anthropic"}],"sources":[{"id":"e13a5147-fb64-4cd7-bf5a-63cdc1400e7f","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","url":"https://divergencelabs.com/publications/ige-preprint.pdf","canonical_url":"https://divergencelabs.com/publications/ige-preprint.pdf","source_type":"preprint","publisher":"Divergence Labs","author":null,"publication_date":"2026-10-27T00:00:00.000Z","retrieved_at":"2026-10-28T20:22:47.621Z","title":"Towards a best-in-class IgE disruptor for food allergy with Claude-enabled antibody design","excerpt":null,"content_hash":null,"source_reliability_class":"low","is_primary_source":true,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-10-28T20:22:47.621Z"},{"id":"fe9979b9-9a7d-4535-bbb3-71bca2162bee","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","url":"https://www.anthropic.com/research/early-progress-drug-development","canonical_url":"https://www.anthropic.com/research/early-progress-drug-development","source_type":"developer_announcement","publisher":"Anthropic","author":null,"publication_date":"2026-10-27T00:00:00.000Z","retrieved_at":"2026-10-28T20:22:47.621Z","title":"Early progress on accelerating drug development with Claude","excerpt":null,"content_hash":null,"source_reliability_class":"low","is_primary_source":true,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-10-28T20:22:47.621Z"},{"id":"28e7b412-953a-4878-8a87-2e06201d801f","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","url":"https://papex.org/blog/anthropic-drug-discovery-reports","canonical_url":"https://papex.org/blog/anthropic-drug-discovery-reports","source_type":"journalism","publisher":"Papex","author":null,"publication_date":"2026-10-27T00:00:00.000Z","retrieved_at":"2026-10-28T20:22:47.621Z","title":"Anthropic's drug discovery reports: what Claude did, and how each lab recorded it","excerpt":null,"content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-10-28T20:22:47.621Z"}],"claims":[{"id":"c62dd6b2-c960-4734-88bd-7b01a1173eec","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","claim_text":"Claude, guided by Divergence Labs, decomposed the IgE-disruptor objective and ran 22 near-autonomous phases that produced on the order of 35,000 VHH designs (11,845 disruptor redesigns and 23,587 unique anchors in the preprint).","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"},{"id":"3184bc5f-fcd0-4601-96a0-b159ee4829c1","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","claim_text":"Of 91 experimentally characterized disruptor designs, 20 were active by competitive BLI, and purified variants V1, V4, and V8 removed more soluble IgE than omalizumab at 25–400 nM.","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"},{"id":"a9a956e0-3bae-4b79-aa6a-58dce5f2851b","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","claim_text":"Three of 57 de novo anchor designs bound IgE with apparent KD 3.4, 32.5, and 235 nM in standard BLI.","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"},{"id":"c97afb53-4f1b-4bb4-952a-14f5a75be23a","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","claim_text":"The campaign produced a food-allergy medicine, an assembled biparatopic, or demonstrated IgE disruption on cells or in animals.","claim_type":"significance","claim_status":"disputed","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"},{"id":"2cf8db7f-f696-4c70-8499-e4a97ab958db","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","claim_text":"The purified disruptor variants improved on parent sdAb026 at controlled therapeutically relevant concentrations.","claim_type":"outcome","claim_status":"disputed","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"},{"id":"b68d6c81-1238-4542-88ca-7deff8b2a02c","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","claim_text":"The campaign used a named Claude release such as Mythos 5.1.","claim_type":"attribution","claim_status":"disputed","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"}],"revisions":[{"id":"6da0709d-e37a-44db-9609-a175d3677865","event_id":"e3b40dd1-2ecc-4181-93ff-2bc62deb5d58","model_id":null,"previous_score":"0.000000","new_score":"0.721900","previous_factors":{},"new_factors":{"evidence":0.35,"base_score":10,"durability":0.55,"attribution":0.75,"realization":0.5},"change_reason":"Imported events under methodology 0.2.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-28T20:22:47.621Z"}],"secondary":[{"name":"Medicine & Health","slug":"medicine-health"},{"name":"Chemistry","slug":"chemistry"}]},"methodology_version":"0.1"}