{"data":{"event":{"id":"88c898e0-3aba-4708-8ff4-9fe605fd131a","slug":"a-foundation-model-learns-the-sequence-and-functional-grammar-of-fully-h-916a3a0087","title":"\n\nA foundation model learns the sequence and functional grammar of fully human heavy-chain-only antibodies \n\n","short_summary":"Antibody language models learn from large natural repertoires, but whether generic representations capture the constraints of specialized antibody formats remains unclear. We first characterized fully human heavy-chain-only antibodies (HCAbs) independently of HCAb-trained models. Source-aware comparisons with conventional human VH domains revealed a reproducible distributional shift localized predominantly to CDR1/2, CDR3 architecture and, where supported, a restricted framework region rather than widespread framework remodeling. These model-independent differences motivated repertoire-specifi","full_description":"Antibody language models learn from large natural repertoires, but whether generic representations capture the constraints of specialized antibody formats remains unclear. We first characterized fully human heavy-chain-only antibodies (HCAbs) independently of HCAb-trained models. Source-aware comparisons with conventional human VH domains revealed a reproducible distributional shift localized predominantly to CDR1/2, CDR3 architecture and, where supported, a restricted framework region rather than widespread framework remodeling. These model-independent differences motivated repertoire-specific pretraining. We developed HCAbLM, to our knowledge the first foundation model pretrained specifically on a large-scale fully human HCAb repertoire, using 31.8 million sequences from 73 independently immunized HCAb mice. HCAbLM learned a region-selective sequence-compatibility prior distinct from conventional antibody language models, and its frozen representations transferred to experimentally measured SEC purity, HIC behavior and thermal stability in grouped internal validation and retrospective cross-project evaluation. These findings identify repertoire composition as an important biological design variable for foundation models of specialized antibody formats.","ledger_type":"benefit","primary_domain_id":"8f1af1b9-7302-4b51-aae9-fdfac04d158a","event_status":"provisional","event_date":"2026-09-15T00:00:00.000Z","discovery_date":"2026-09-15T00:00:00.000Z","first_published_date":"2026-09-15T00:00:00.000Z","last_reviewed_date":"2026-09-15T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.1000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.001000","confidence_level":"low","score_explanation":"Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-09-16T04:00:52.045Z","created_at":"2026-09-16T04:00:52.045Z","updated_at":"2026-09-16T04:00:52.045Z","flags":[],"domain_name":"Biology","domain_slug":"biology","methodology_version":"0.2"},"contributions":[{"id":"1fb4f39e-0c47-4a96-9c0d-c4bd35f97ea9","event_id":"88c898e0-3aba-4708-8ff4-9fe605fd131a","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.001000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-15T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-16T04:00:52.055Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"5f0a7c92-2a91-46bf-ba36-b02351e64f77","event_id":"88c898e0-3aba-4708-8ff4-9fe605fd131a","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.10.750553v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.10.750553v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-15T00:00:00.000Z","retrieved_at":"2026-09-16T04:00:52.066Z","title":"\n\nA foundation model learns the sequence and functional grammar of fully human heavy-chain-only antibodies \n\n","excerpt":"Antibody language models learn from large natural repertoires, but whether generic representations capture the constraints of specialized antibody formats remains unclear. We first characterized fully human heavy-chain-only antibodies (HCAbs) independently of HCAb-trained models. Source-aware comparisons with conventional human VH domains revealed a reproducible distributional shift localized predominantly to CDR1/2, CDR3 architecture and, where supported, a restricted framework region rather th","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-16T04:00:52.066Z"}],"claims":[{"id":"10c1bd80-57ed-4c1c-839b-37ab65656ed4","event_id":"88c898e0-3aba-4708-8ff4-9fe605fd131a","claim_text":"\n\nA foundation model learns the sequence and functional grammar of fully human heavy-chain-only antibodies \n\n","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-16T04:00:52.072Z","updated_at":"2026-09-16T04:00:52.072Z"}],"revisions":[{"id":"9342f6d5-e7b9-47e1-885f-9e3683ce79e9","event_id":"88c898e0-3aba-4708-8ff4-9fe605fd131a","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-16T04:00:52.080Z"}],"secondary":[]},"methodology_version":"0.1"}