{"id":"W4377292690","doi":"10.1038/s41467-023-38716-x","title":"Linear time complexity de novo long read genome assembly with GoldRush","year":2023,"lang":"en","type":"article","venue":"Nature Communications","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Genome; Nanopore sequencing; Sequence assembly; Computer science; Scalability; Computational biology; Human genome; Hybrid genome assembly; Structural variation; Sequence (biology); Biology; Genetics; Gene","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":[0.001235812,0.001061706,0.00083919,0.0005419052,0.000616821,0.00120489,0.001780097,0.0008681808,0.005116394],"category_scores_gemma":[0.003169645,0.0006218863,0.001012366,0.0008632068,0.0005294043,0.001458814,0.001500574,0.001435103,0.003971036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103631,"about_ca_system_score_gemma":0.001717963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00316583,"about_ca_topic_score_gemma":0.006465496,"domain_scores_codex":[0.9986216,0.0002448125,0.0001033437,0.0004546204,0.0004547563,0.0001209103],"domain_scores_gemma":[0.9980952,0.0008272277,0.0001267074,0.0005879454,0.0002692375,0.00009360028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001303765,0.0003571064,0.003567859,0.001137712,0.000379778,0.0005005051,0.0008440548,0.1098734,0.200222,0.02491564,0.04586847,0.6110297],"study_design_scores_gemma":[0.000208441,0.0002725283,0.001614004,0.00004302043,0.00004721712,0.0003045621,0.0001965827,0.8300294,0.1236444,0.01730722,0.02623689,0.0000955633],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0440531,0.000463199,0.8913279,0.0004309102,0.0001872485,0.0001380249,0.001196369,0.05785296,0.004350431],"genre_scores_gemma":[0.09034748,0.0001085106,0.9027868,0.0001593891,0.00003886415,0.0001927262,0.002374245,0.00138335,0.00260875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005116394,"threshold_uncertainty_score":0.01711607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03006470799351714,"score_gpt":0.3009126560763167,"score_spread":0.2708479480827996,"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."}}