{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001395515,0.0001510889,0.0002280416,0.0001156697,0.0007657463,0.0000817145,0.0007478814,0.0001283394,0.00004075249],"category_scores_gemma":[0.0001639826,0.0001408445,0.0001264062,0.00007396937,0.0002982511,6.410032e-7,0.001224691,0.0001568102,0.00001422652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002642339,"about_ca_system_score_gemma":0.0001363191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000710743,"about_ca_topic_score_gemma":0.00002786469,"domain_scores_codex":[0.998144,0.0001331918,0.0002513153,0.0004443305,0.0003653081,0.0006618199],"domain_scores_gemma":[0.9982712,0.00002923366,0.0001287129,0.001159259,0.0002962214,0.0001153174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006646755,0.0001036072,0.005449607,0.00003850833,0.0001185082,0.000006621871,0.0002366454,0.0003327446,0.9925345,0.000112289,0.0002162906,0.0007842698],"study_design_scores_gemma":[0.00221951,0.0008836328,0.1143709,0.00005121226,0.00005606275,0.00002918667,0.001078988,0.001697431,0.3630888,0.0002024421,0.5156049,0.0007170854],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896219,0.005064144,0.0001293639,0.0001379739,0.00006760468,0.0002788679,0.0001510396,0.000001549831,0.004547527],"genre_scores_gemma":[0.9974923,0.0004415627,0.0007703315,0.00002710129,0.0003172777,0.00001668253,0.00002057224,0.00003078207,0.0008833628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6294457,"threshold_uncertainty_score":0.5889578,"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."}}