{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00232113,0.002008013,0.001316175,0.004947561,0.001647605,0.002410711,0.002382577,0.001457436,0.006357848],"category_scores_gemma":[0.007469988,0.0009284127,0.001593489,0.003727408,0.0008371147,0.002144867,0.00206273,0.001283359,0.003560348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000776754,"about_ca_system_score_gemma":0.002307255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003379939,"about_ca_topic_score_gemma":0.005738139,"domain_scores_codex":[0.9987431,0.0002433315,0.0001414886,0.0004089324,0.0003495588,0.0001136565],"domain_scores_gemma":[0.9982723,0.0007941719,0.0002464845,0.0002161912,0.0003147246,0.0001561073],"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":[0.001585757,0.0004229134,0.02184459,0.002979635,0.0008496525,0.001020589,0.001984132,0.03626695,0.05602678,0.02315473,0.07842453,0.7754397],"study_design_scores_gemma":[0.0004268909,0.0004040288,0.007498662,0.0003743129,0.0002862249,0.002288095,0.001232671,0.8095387,0.02939107,0.06300107,0.0854008,0.0001574541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02816074,0.0008106108,0.9361836,0.000334402,0.0001321722,0.0004771875,0.002483579,0.02857079,0.002846926],"genre_scores_gemma":[0.0500384,0.000316167,0.941664,0.0001364645,0.00002770534,0.0003535322,0.003504702,0.002085701,0.001873226],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006357848,"threshold_uncertainty_score":0.02126914,"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."}}