{"id":"W3096124910","doi":"10.1101/2020.11.02.365809","title":"ntHits: <i>de novo</i> repeat identification of genomics data using a streaming approach","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Computer science; k-mer; DNA sequencing; Hybrid genome assembly; Genome; Identification (biology); Sequence assembly; Genomics; Algorithm; Set (abstract data type); Histogram; Copy number analysis; Computational biology; Data mining; Biology; Genetics; Artificial intelligence; Copy-number variation; DNA; Gene","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001324334,0.001003402,0.0006261052,0.00138028,0.0005995167,0.001411391,0.001386055,0.0006252531,0.004099386],"category_scores_gemma":[0.005312162,0.0004897331,0.0008341597,0.001173534,0.0005272404,0.001334395,0.001284995,0.0009257033,0.003355796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005641039,"about_ca_system_score_gemma":0.0008917697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002501911,"about_ca_topic_score_gemma":0.002967187,"domain_scores_codex":[0.9991116,0.000106069,0.00009614868,0.0003372866,0.0002923235,0.00005660387],"domain_scores_gemma":[0.9978975,0.0007347266,0.0002805184,0.0004576441,0.0004739176,0.0001556454],"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":[0.002183297,0.000272878,0.01437297,0.001078266,0.0004511299,0.0009266583,0.0006660332,0.06171767,0.1864553,0.0109021,0.06602967,0.654944],"study_design_scores_gemma":[0.0001215212,0.0001095918,0.003616899,0.00006043745,0.00004500832,0.0004897206,0.0001260585,0.8671421,0.09182517,0.009745644,0.02662167,0.00009618307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02996656,0.0002783171,0.8579327,0.0002197596,0.0001504289,0.0002029422,0.004631882,0.1048308,0.001786494],"genre_scores_gemma":[0.1417731,0.0001866564,0.8329504,0.0001934083,0.0001018291,0.0003237127,0.01574487,0.00530648,0.003419585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004099386,"threshold_uncertainty_score":0.01371384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03597599990610955,"score_gpt":0.245866908919075,"score_spread":0.2098909090129655,"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."}}