{"id":"W2130468514","doi":"10.1186/1477-5956-11-s1-s8","title":"Ranking and compacting binding segments of protein families using aligned pattern clusters","year":2013,"lang":"en","type":"article","venue":"Proteome Science","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ranking (information retrieval); Representation (politics); Computational biology; Set (abstract data type); Protein family; Computer science; Sequence (biology); Data mining; Probabilistic logic; Protein sequencing; Sequence alignment; Multiple sequence alignment; Amino acid residue; Bioinformatics; Peptide sequence; Biology; Artificial intelligence; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003322073,0.0001131426,0.0001183354,0.00009405709,0.0001984273,0.0000696748,0.0002226328,0.00005121352,0.000004655527],"category_scores_gemma":[0.00008533993,0.00009874284,0.00002398681,0.000207076,0.0003610358,0.00003003212,0.0002440271,0.00004340513,0.000001220321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001856204,"about_ca_system_score_gemma":0.00006361963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001794421,"about_ca_topic_score_gemma":0.000004759213,"domain_scores_codex":[0.9989885,0.00002534182,0.0001911483,0.00030495,0.0002168261,0.0002732414],"domain_scores_gemma":[0.9994913,0.000004223839,0.0001520841,0.0001918459,0.00009231177,0.00006817626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005346921,0.000005019934,0.005793265,0.00003933442,0.000005599217,2.947943e-7,0.0001139096,0.0000581928,0.9874272,0.000006186903,5.558134e-7,0.0065451],"study_design_scores_gemma":[0.000281161,0.0000864921,0.002426853,0.00008330904,0.000004719929,0.00001275121,0.0002353225,0.006411373,0.9901584,0.0001282543,0.00001426139,0.000157139],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804345,0.00006611282,0.01855475,0.00002609083,0.00004608383,0.0007211358,0.000003530775,0.000007492322,0.0001402964],"genre_scores_gemma":[0.9859909,0.000004613913,0.01386755,0.0000404733,0.00002857153,0.00002754014,0.00000278285,0.000008584373,0.00002901717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006387962,"threshold_uncertainty_score":0.4026616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0102854221579762,"score_gpt":0.2500757926040623,"score_spread":0.2397903704460861,"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."}}