{"id":"W4405216449","doi":"10.1007/s11222-024-10537-y","title":"funBIalign: a hierachical algorithm for functional motif discovery based on mean squared residue scores","year":2024,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec - Santé; Huck Institutes of the Life Sciences; Pennsylvania State University; Université Laval; University of Pennsylvania","keywords":"Mathematics; Residue (chemistry); Algorithm; Mean squared error; Artificial intelligence; Computer science; Statistics; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001347336,0.0001072915,0.00008338477,0.00004635669,0.0001409631,0.0001434544,0.00004934742,0.00006344042,0.00000624733],"category_scores_gemma":[0.00004004882,0.00009615734,0.00003968563,0.00005373864,0.0000419005,0.000002891993,0.00003161853,0.00006976854,0.000001412328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001188617,"about_ca_system_score_gemma":0.00008997102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005774046,"about_ca_topic_score_gemma":0.000005819931,"domain_scores_codex":[0.9992115,0.00003434331,0.0001465639,0.0003472728,0.0001204552,0.0001398764],"domain_scores_gemma":[0.9996532,0.00008186408,0.00003444673,0.0001255912,0.00005126052,0.00005368214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00027905,0.0001152113,0.0004840802,0.0002473352,0.00009226708,0.00001099274,0.0001173099,0.002882745,0.09143752,0.02961648,0.06786446,0.8068526],"study_design_scores_gemma":[0.0007355408,0.0005338712,0.005154439,0.0001413382,0.00003555517,0.000006097021,0.00007335389,0.9565831,0.0147259,0.002507023,0.01921093,0.0002928083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01468123,0.0002884706,0.9837468,0.0001742155,0.0004831927,0.000130859,0.0003318073,0.00001894317,0.0001444589],"genre_scores_gemma":[0.9665695,0.00001787005,0.03149133,0.0003031693,0.0005821263,0.00001686503,0.0005775602,0.00002057522,0.0004209538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9537004,"threshold_uncertainty_score":0.3921182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01478426957009913,"score_gpt":0.2748408735956864,"score_spread":0.2600566040255872,"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."}}