{"id":"W2589379462","doi":"10.1101/gr.214346.116","title":"ABySS 2.0: resource-efficient assembly of large genomes using a Bloom filter","year":2017,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":740,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Bloom filter; Sequence assembly; Genome; Genomics; Computational biology; De Bruijn graph; Biology; Computer science; k-mer; Structural variation; Hybrid genome assembly; Reference genome; DNA sequencing; Genetics; Graph; Gene; Theoretical computer science; Algorithm","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":[0.003640443,0.001835862,0.001451405,0.001694311,0.001494554,0.002051567,0.002721232,0.001695367,0.004327426],"category_scores_gemma":[0.006032278,0.001744564,0.001597861,0.001895041,0.0009363639,0.002089334,0.001854325,0.002229541,0.004533736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001773436,"about_ca_system_score_gemma":0.002812772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007160204,"about_ca_topic_score_gemma":0.00586075,"domain_scores_codex":[0.9979104,0.0005294504,0.00024079,0.0004162308,0.000717062,0.000186036],"domain_scores_gemma":[0.997773,0.00100282,0.000200398,0.0004767529,0.0004119051,0.0001350647],"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":[0.002953467,0.0004930749,0.00910047,0.001654682,0.0006728836,0.0007004486,0.001919319,0.1943294,0.2881558,0.03944312,0.07260119,0.3879762],"study_design_scores_gemma":[0.0002823648,0.000203715,0.00105828,0.00009491903,0.00006470441,0.0002616306,0.00009882112,0.7815792,0.1459197,0.02041874,0.04982661,0.0001913435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02147736,0.0003607087,0.9012534,0.0002118605,0.000119334,0.0002813776,0.001724086,0.07242456,0.00214734],"genre_scores_gemma":[0.05056138,0.0003319815,0.9384486,0.0002148031,0.000035369,0.0007260383,0.003242291,0.004519038,0.001920583],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007160204,"threshold_uncertainty_score":0.01925272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08335564250981123,"score_gpt":0.3776353302280352,"score_spread":0.294279687718224,"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."}}