{"id":"W4415887800","doi":"10.1101/2025.11.03.686256","title":"Exploring the Structural Lexicon of the Proteome via Metric Geometry","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Metric (unit); Proteome; Protein structure; Structural alignment; Protein superfamily; Information geometry; Computational geometry; Protein domain","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007736856,0.0003450385,0.0005022163,0.003067972,0.001043862,0.002982894,0.0007305618,0.0007069023,0.002048826],"category_scores_gemma":[0.004327255,0.0003681719,0.0006697819,0.002452487,0.001999231,0.003741575,0.00218444,0.0007584236,0.0007116449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008419609,"about_ca_system_score_gemma":0.0009333316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001657604,"about_ca_topic_score_gemma":0.001847901,"domain_scores_codex":[0.9993922,0.0002224474,0.00003947983,0.0001635525,0.0001462362,0.00003621426],"domain_scores_gemma":[0.9988346,0.0004459585,0.0002328134,0.0002509042,0.0001481604,0.00008772633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001443286,0.00003761045,0.004974022,0.000291621,0.00005759254,0.0004423814,0.0009865616,0.04080038,0.02815226,0.8568002,0.005442038,0.06187103],"study_design_scores_gemma":[0.0000123198,0.00004873831,0.003179209,0.0000466021,0.00002057404,0.000464451,0.0005133014,0.2283362,0.004873267,0.7324588,0.03000058,0.00004603823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2319125,0.001159423,0.7439868,0.00161663,0.00006214024,0.00008394419,0.004389658,0.001562388,0.01522667],"genre_scores_gemma":[0.6886546,0.001125449,0.3024894,0.0002020995,0.00008181578,0.0001865669,0.005102988,0.0005719394,0.001585052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003067972,"threshold_uncertainty_score":0.006853998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0156562618810581,"score_gpt":0.2211754745411298,"score_spread":0.2055192126600717,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}