{"id":"W4414278761","doi":"10.1101/2025.09.12.675776","title":"Compression of protein secondary structures enables ultra-fast and accurate structure searching","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":"Centre de Santé et de Services Sociaux Cavendish","funders":"","keywords":"Protein structure; Representation (politics); ENCODE; Protein structure prediction; Data structure; Domain (mathematical analysis); Compression (physics); 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":[0.0003599504,0.0004029021,0.0003625992,0.0006555258,0.0001714885,0.0006099301,0.000435016,0.0003659291,0.001791668],"category_scores_gemma":[0.001186486,0.0001887973,0.0001758552,0.0006368419,0.0003090883,0.0008100623,0.0006510637,0.0004382158,0.0007923646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002727073,"about_ca_system_score_gemma":0.000243375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006797111,"about_ca_topic_score_gemma":0.000608062,"domain_scores_codex":[0.9997966,0.00003437508,0.00001555518,0.00003425113,0.0001020612,0.00001721944],"domain_scores_gemma":[0.9994935,0.0001928085,0.00006781329,0.0001328453,0.00008491662,0.00002806568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007833962,0.0001318761,0.003456424,0.0002260193,0.00004097209,0.0003144489,0.0001525831,0.04942426,0.7053042,0.009659769,0.004626777,0.2258794],"study_design_scores_gemma":[0.00005421832,0.0001899642,0.004069053,0.00002581312,0.00001995692,0.0004611375,0.00006460815,0.6207206,0.3577239,0.006745057,0.009899788,0.00002590244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5818412,0.001639492,0.4038548,0.0004336405,0.0001490123,0.00006269114,0.0008694159,0.007148718,0.004001053],"genre_scores_gemma":[0.7323543,0.0006376388,0.261933,0.00009980905,0.00008568393,0.00005763793,0.00202573,0.0003200232,0.002486245],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.001791668,"threshold_uncertainty_score":0.005993664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006343654695018458,"score_gpt":0.2253860195904852,"score_spread":0.2190423648954667,"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."}}