{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003365771,0.0007227522,0.0005976821,0.000188574,0.0002369709,0.0008482003,0.003072336,0.000322953,0.0000436861],"category_scores_gemma":[0.00007976131,0.0006407673,0.00008963791,0.001108138,0.00007293992,0.0008967103,0.004652708,0.0011381,0.0004939511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001240343,"about_ca_system_score_gemma":0.001219825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003260231,"about_ca_topic_score_gemma":0.000005707167,"domain_scores_codex":[0.9958987,0.0001472482,0.000460599,0.001997211,0.0008486866,0.0006475109],"domain_scores_gemma":[0.9947981,0.00003620415,0.0004631665,0.003533605,0.000586547,0.000582439],"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":[0.0001544111,0.0005588545,0.0005126853,0.001771277,0.0003727858,0.001552898,0.00009805054,0.0002400512,0.9716631,0.01964601,0.00337636,0.00005354303],"study_design_scores_gemma":[0.003621991,0.0007230788,0.01589311,0.006955753,0.0002878953,4.987581e-7,0.00001480219,0.1430745,0.7195486,0.00006505528,0.1030569,0.006757803],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1550991,0.0007761787,0.8321725,0.005070017,0.001142721,0.002539517,0.0008631751,0.002278447,0.00005842837],"genre_scores_gemma":[0.6198041,0.00005068736,0.3761178,0.002574847,0.0007122951,0.0005495629,0.000003121467,0.0001759741,0.00001154871],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4647051,"threshold_uncertainty_score":0.9996043,"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."}}