{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002444651,0.001196627,0.001167029,0.002387843,0.0008988711,0.001802155,0.002452474,0.001189731,0.003395342],"category_scores_gemma":[0.01380385,0.0006869291,0.0009623097,0.002349499,0.0008515539,0.003159072,0.002247469,0.001792804,0.001973631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001456954,"about_ca_system_score_gemma":0.001993548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003422506,"about_ca_topic_score_gemma":0.004068254,"domain_scores_codex":[0.9975966,0.0003868928,0.000291329,0.0006921129,0.0008970861,0.000135991],"domain_scores_gemma":[0.9939336,0.002773249,0.0006449481,0.001419876,0.0009767435,0.0002515233],"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":[0.001588098,0.0002982395,0.01546429,0.0006146771,0.0002705085,0.0004430938,0.0005777373,0.1272913,0.0432149,0.02142752,0.03788225,0.7509273],"study_design_scores_gemma":[0.00009716174,0.00006889483,0.001431935,0.0000309052,0.0000196475,0.0003029589,0.00008736291,0.9560907,0.01566518,0.01743569,0.008727485,0.00004204346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01849528,0.0003663426,0.9653764,0.0002314713,0.0001310823,0.000252491,0.001941774,0.01244439,0.0007607889],"genre_scores_gemma":[0.07419363,0.0001508483,0.9170669,0.0001689184,0.00009791868,0.000343808,0.006007592,0.0007564113,0.001213954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003422506,"threshold_uncertainty_score":0.01292872,"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."}}