{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001587615,0.0003096994,0.0003370965,0.0001479189,0.000447201,0.0002304225,0.001173336,0.0002825897,0.00002173105],"category_scores_gemma":[0.000780568,0.0002292913,0.0003523971,0.0003702177,0.0003708448,3.379986e-7,0.00344549,0.000549503,0.00005040409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007563242,"about_ca_system_score_gemma":0.0005493845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002342183,"about_ca_topic_score_gemma":0.0001572376,"domain_scores_codex":[0.9972728,0.0002615163,0.0003432759,0.000822454,0.0006167754,0.0006831918],"domain_scores_gemma":[0.9972991,0.0001116691,0.0001325553,0.001489146,0.0007532549,0.0002143009],"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":[0.0006467937,0.0004166623,0.07786687,0.0004295197,0.01473124,0.0001119921,0.001566376,0.2706946,0.5235673,0.0004481124,0.07567988,0.03384073],"study_design_scores_gemma":[0.002203892,0.001015338,0.07849213,0.0001934792,0.00282037,0.00002740657,0.002835046,0.01942423,0.1374161,0.007622323,0.7436528,0.004296893],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783573,0.01722363,0.001442975,0.000571882,0.0004129729,0.0005873396,0.0003123273,0.00001498863,0.001076652],"genre_scores_gemma":[0.9918555,0.003206003,0.000938202,0.00008013412,0.0004937943,0.0001424806,0.0002753368,0.0000584701,0.002950066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6679729,"threshold_uncertainty_score":0.9350227,"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."}}