{"id":"W1954100204","doi":"10.12688/f1000research.6924.1","title":"The khmer software package: enabling efficient nucleotide sequence analysis","year":2015,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":424,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; National Institute of Food and Agriculture; National Institutes of Health; U.S. Department of Agriculture; California Institute of Technology; Gordon and Betty Moore Foundation","keywords":"De Bruijn sequence; Python (programming language); De Bruijn graph; Computer science; Software; Software package; Programming language; Graph; Biology; Theoretical computer science; Discrete mathematics; Mathematics","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":[0.00412745,0.003141441,0.004767775,0.003419295,0.001755713,0.004108682,0.003946457,0.001835655,0.1019746],"category_scores_gemma":[0.013944,0.002958548,0.002644758,0.003636885,0.0009845495,0.003382487,0.003005996,0.00589247,0.1545464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008562886,"about_ca_system_score_gemma":0.002549934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002370042,"about_ca_topic_score_gemma":0.003240202,"domain_scores_codex":[0.9972059,0.000709939,0.0003412651,0.0008794601,0.000647834,0.0002155481],"domain_scores_gemma":[0.9973042,0.001289426,0.0003337857,0.0005565762,0.0003636049,0.0001523764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001083335,0.0001740846,0.002523247,0.007433761,0.0007905541,0.0007909482,0.001013562,0.006916008,0.02687119,0.02247539,0.7559379,0.17399],"study_design_scores_gemma":[0.0007816346,0.0002424529,0.003770998,0.001334044,0.0004559421,0.001700904,0.0002865282,0.0615425,0.03625266,0.07407945,0.8189614,0.0005914253],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.003881983,0.00211892,0.5373536,0.0004177813,0.0008223575,0.000477765,0.1438259,0.3024778,0.00862395],"genre_scores_gemma":[0.01642006,0.001615934,0.6828462,0.0007722676,0.0002460625,0.002479393,0.1633582,0.1233533,0.00890848],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1019746,"threshold_uncertainty_score":0.3411391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05689399194246028,"score_gpt":0.3394192060284997,"score_spread":0.2825252140860394,"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."}}