{"id":"W2163059805","doi":"10.1093/bioinformatics/btv047","title":"KAPPA, a simple algorithm for discovery and clustering of proteins defined by a key amino acid pattern: a case study of the cysteine-rich proteins","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Computer science; Cluster analysis; Computational biology; Kappa; Data mining; Pairwise comparison; Cysteine; Set (abstract data type); Sequence (biology); Protein superfamily; Protein sequencing; Peptide sequence; Bioinformatics; Theoretical computer science; Artificial intelligence; Biology; Mathematics; Genetics; Biochemistry; Programming language","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":[0.0003945389,0.0002331041,0.0003038003,0.00005353343,0.00009493789,0.00004915884,0.0002771621,0.0001319169,7.268749e-7],"category_scores_gemma":[0.000273328,0.0001669981,0.00007724257,0.0001334454,0.00009710267,0.00003320925,0.000460209,0.0001133586,5.749156e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001956105,"about_ca_system_score_gemma":0.0001021664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002559504,"about_ca_topic_score_gemma":0.0002156643,"domain_scores_codex":[0.9985291,0.00005409553,0.0007462081,0.0001431867,0.0002755499,0.0002518168],"domain_scores_gemma":[0.9985518,0.00002497751,0.000592521,0.0005583876,0.0001835604,0.00008871478],"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":[0.001413982,0.00858556,0.1344132,0.01975018,0.003378038,0.0001060976,0.181422,0.005351408,0.1615518,0.0001217797,0.02376755,0.4601384],"study_design_scores_gemma":[0.01565729,0.01606229,0.0009595344,0.0002962855,0.0003503698,0.001853122,0.05361652,0.778487,0.1237019,0.00005346998,0.007508221,0.001453969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8042692,0.00007843689,0.193084,0.00002703837,0.00006255368,0.002105155,0.0002480557,0.0000111964,0.0001143141],"genre_scores_gemma":[0.9489313,0.000005164145,0.05054752,0.00007066382,0.00004502148,0.0001709786,0.00008964364,0.00002509697,0.0001145775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7731356,"threshold_uncertainty_score":0.6809987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01458941080966597,"score_gpt":0.2550236130755956,"score_spread":0.2404342022659296,"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."}}