{"data":{"event":{"id":"e9d6239b-d442-468b-91a2-93d65579b92b","slug":"bell-biomodel-evidence-and-llm-based-logic-ca86a05709","title":"\n\nBELL: Biomodel Evidence and LLM-based Logic \n\n","short_summary":"Building accurate and predictive mechanistic models requires careful biological interaction curation and verification against existing knowledge. When done manually, these tasks become impractical, especially with massive extraction of interactions facilitated by advanced natural language processing methods and large language models (LLMs). We present BELL (Biomodel Evidence and LLM-based Logic), a biocuration support framework that automates evidence retrieval, scoring, and explanation for interaction-level verification. BELL processes each interaction through a five-step pipeline: entity gro","full_description":"Building accurate and predictive mechanistic models requires careful biological interaction curation and verification against existing knowledge. When done manually, these tasks become impractical, especially with massive extraction of interactions facilitated by advanced natural language processing methods and large language models (LLMs). We present BELL (Biomodel Evidence and LLM-based Logic), a biocuration support framework that automates evidence retrieval, scoring, and explanation for interaction-level verification. BELL processes each interaction through a five-step pipeline: entity grounding, database ranking, evidence retrieval from seven biological databases, a heuristic four-dimension programmatic scoring, and chain-of-thought explanation with a recommended curator action generated by LLMs. We applied BELL on 210 protein-protein interactions from a curated Glioblastoma Multiforme (GBM) model. Results show that 49.5% of interactions achieved HIGH confidence and 72.4% received a positive curator recommendation, while qualitative flags precisely directed curator attention to evidence gaps. BELL is integrated into the KALIMBA curation platform and available at www.boheme.pitt.edu/Kalimba.\n\nUpdate (2026-09-21): \n\nCorrelation-aware discovery of co-occurring mutational signatures in cancer \n\n. Somatic mutations in cancer genomes record the activities of diverse mutational processes. Mutational signature analysis has advanced mechanistic understanding of mutagenesis and informed clinical decision-making, yet existing methods assume independence among signatures--an unrealistic assumption that can produce composite or contaminated signatures, reduce detection power, and yield inconsistent results. Here we present Cornet (CORrelated NMF ExTraction), a framework for mutational signature discovery that explicitly models co-occurring processes and jointly infers signatures and their correlation structure. Benchmarking on simulated data shows Cornet more accurately recovers distinct signatures under strong correlations. Applied to cancer genomes, Cornet enables unsupervised discovery of the colibactin-associated signature SBS88 in oral cancers and identifies the tobacco smoking signature SBS4 in bladder cancer, where it was previously thought absent. Cornet also uncovers a novel mutational process implicated in early-onset colorectal cancer and a signature arising from the i","ledger_type":"benefit","primary_domain_id":"8f1af1b9-7302-4b51-aae9-fdfac04d158a","event_status":"provisional","event_date":"2026-09-20T00:00:00.000Z","discovery_date":"2026-09-20T00:00:00.000Z","first_published_date":"2026-09-20T00:00:00.000Z","last_reviewed_date":"2026-09-21T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.2000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.002000","confidence_level":"low","score_explanation":"Ingest update: independent source raised evidence; added a follow-up source. Score remains provisional until review.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-09-21T04:01:12.051Z","created_at":"2026-09-21T04:01:12.051Z","updated_at":"2026-09-21T15:01:00.196Z","flags":[],"domain_name":"Biology","domain_slug":"biology","methodology_version":"0.2"},"contributions":[{"id":"e781efcf-6eed-41df-8dcf-0840fdf8f309","event_id":"e9d6239b-d442-468b-91a2-93d65579b92b","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":"0.002000","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":"2026-09-20T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-21T04:01:12.059Z","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":"c1e4cadf-0954-4573-af04-80703138ee4b","event_id":"e9d6239b-d442-468b-91a2-93d65579b92b","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.18.721350v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.18.721350v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-20T00:00:00.000Z","retrieved_at":"2026-09-21T04:01:12.069Z","title":"\n\nBELL: Biomodel Evidence and LLM-based Logic \n\n","excerpt":"Building accurate and predictive mechanistic models requires careful biological interaction curation and verification against existing knowledge. When done manually, these tasks become impractical, especially with massive extraction of interactions facilitated by advanced natural language processing methods and large language models (LLMs). We present BELL (Biomodel Evidence and LLM-based Logic), a biocuration support framework that automates evidence retrieval, scoring, and explanation for inte","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-21T04:01:12.069Z"},{"id":"143d1cae-03d4-4e90-b8a6-7c0ce761c2d5","event_id":"e9d6239b-d442-468b-91a2-93d65579b92b","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.14.751548v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.14.751548v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-21T00:00:00.000Z","retrieved_at":"2026-09-21T15:01:00.181Z","title":"\n\nCorrelation-aware discovery of co-occurring mutational signatures in cancer \n\n","excerpt":"Somatic mutations in cancer genomes record the activities of diverse mutational processes. Mutational signature analysis has advanced mechanistic understanding of mutagenesis and informed clinical decision-making, yet existing methods assume independence among signatures--an unrealistic assumption that can produce composite or contaminated signatures, reduce detection power, and yield inconsistent results. Here we present Cornet (CORrelated NMF ExTraction), a framework for mutational signature d","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-21T15:01:00.181Z"}],"claims":[{"id":"97e5d697-da7c-475e-8210-8c36bb0f4401","event_id":"e9d6239b-d442-468b-91a2-93d65579b92b","claim_text":"\n\nBELL: Biomodel Evidence and LLM-based Logic \n\n","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-21T04:01:12.075Z","updated_at":"2026-09-21T04:01:12.075Z"}],"revisions":[{"id":"8df50b15-b554-499c-adfc-406b39c6af0d","event_id":"e9d6239b-d442-468b-91a2-93d65579b92b","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"tier":1,"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":"2026-09-21T04:01:12.087Z"},{"id":"a1c918b0-9ff8-4613-a675-f9eb71f42b65","event_id":"e9d6239b-d442-468b-91a2-93d65579b92b","model_id":null,"previous_score":"0.001000","new_score":"0.002000","previous_factors":{"tier":1,"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"new_factors":{"tier":1,"models":["535014f7-c941-4d39-aa9b-8f9c1d3d07b7"],"evidence":0.2,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Ingest update: independent source raised evidence; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["143d1cae-03d4-4e90-b8a6-7c0ce761c2d5"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-21T15:01:00.202Z"}],"secondary":[]},"methodology_version":"0.1"}