{"id":"W3014463062","doi":"10.1101/2020.04.01.019984","title":"Fast protein database as a service with kAAmer","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centrale des Syndicats du Québec; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada","keywords":"Identification (biology); Computer science; Service (business); Computational biology; Database; Genomics; Biology; Genome; Gene; Genetics","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":[0.003759612,0.002647276,0.002598444,0.00507894,0.0009532143,0.005018106,0.004161695,0.002298895,0.06599821],"category_scores_gemma":[0.009852456,0.001791122,0.001033084,0.005347584,0.0006161104,0.005858636,0.005026022,0.003097112,0.1150078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001071386,"about_ca_system_score_gemma":0.002039204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009200023,"about_ca_topic_score_gemma":0.0007019245,"domain_scores_codex":[0.9976771,0.0003221757,0.0002613987,0.0005624015,0.0009251477,0.0002517561],"domain_scores_gemma":[0.9958122,0.0008396285,0.0002832763,0.001851285,0.0008070944,0.000406518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001963762,0.0001879586,0.001070577,0.0008678792,0.000242187,0.000362754,0.0001503488,0.001982851,0.01378567,0.02169299,0.7754884,0.1822047],"study_design_scores_gemma":[0.001190305,0.0002267528,0.001479212,0.0002572975,0.0001132047,0.001526164,0.0001397046,0.0998315,0.05390817,0.08204049,0.7589579,0.0003294171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.002260147,0.001218093,0.2791096,0.0006873378,0.000554065,0.0002679935,0.03280618,0.6721144,0.01098218],"genre_scores_gemma":[0.07342741,0.002993582,0.4741798,0.002223544,0.0007708766,0.001656626,0.3074168,0.09351286,0.04381841],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06599821,"threshold_uncertainty_score":0.220786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647349298543898,"score_gpt":0.2182477437813734,"score_spread":0.2017742507959344,"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."}}