{"id":"W2570372911","doi":"10.1093/bioinformatics/btw832","title":"ntCard: a streaming algorithm for cardinality estimation in genomics data","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; BC Cancer Agency; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"k-mer; Algorithm; Computer science; Hash function; Histogram; Cardinality (data modeling); Memory footprint; Genomics; Shotgun sequencing; Population; Hash table; Sequence assembly; Genome; Data mining; Biology; Artificial intelligence","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":[0.0003201505,0.0001135925,0.0001452088,0.00002365385,0.000217012,0.0000870495,0.0005187631,0.00008255294,5.098367e-7],"category_scores_gemma":[0.0001553547,0.0001124774,0.00004464491,0.00001350442,0.00005796867,0.000005467607,0.0004773638,0.00003593141,0.000002652367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001905247,"about_ca_system_score_gemma":0.00006765198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005212736,"about_ca_topic_score_gemma":0.00007469689,"domain_scores_codex":[0.9993164,0.000007524257,0.000256348,0.0001669053,0.00006399116,0.0001888292],"domain_scores_gemma":[0.9986744,0.00001177377,0.0001747019,0.001052209,0.00005005045,0.00003687498],"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":[0.0000336741,0.00005338876,0.007839037,0.0001269553,0.000166688,0.000001091116,0.0004461,0.0004929435,0.008929187,0.0001113188,0.001556832,0.9802428],"study_design_scores_gemma":[0.002263131,0.0002626483,0.06300217,0.00003940008,0.00009124816,0.00001513389,0.0007640629,0.8373643,0.01210395,0.0006499388,0.08278287,0.0006611351],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6872045,0.0006658542,0.3063846,0.0001807954,0.0005604558,0.0008906506,0.001551021,0.000007305585,0.0025548],"genre_scores_gemma":[0.6658081,0.0002978381,0.3328794,0.00007178251,0.0001762991,0.00002905133,0.000628978,0.00001608751,0.00009252012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9795817,"threshold_uncertainty_score":0.4586695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03918693709759102,"score_gpt":0.3018838107664112,"score_spread":0.2626968736688202,"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."}}