{"id":"W2125076371","doi":"10.1186/1471-2105-15-61","title":"CDSbank: taxonomy-aware extraction, selection, renaming and formatting of protein-coding DNA or amino acid sequences","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"GenBank; Computer science; Disk formatting; Sequence database; Redundancy (engineering); Web server; Data mining; Information retrieval; Database; Computational biology; Biology; The Internet; Genetics; World Wide Web","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":[0.007283201,0.004342565,0.002634099,0.007048734,0.002595103,0.005018158,0.004637651,0.002139788,0.04333566],"category_scores_gemma":[0.01577716,0.002836786,0.002356849,0.009542727,0.001038277,0.004774166,0.004365079,0.004327091,0.07261785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002164274,"about_ca_system_score_gemma":0.005701637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003570959,"about_ca_topic_score_gemma":0.003519512,"domain_scores_codex":[0.9963588,0.0006076841,0.0009386683,0.001076671,0.0007702681,0.0002478621],"domain_scores_gemma":[0.9932809,0.002034079,0.001028847,0.001355051,0.001629072,0.0006720012],"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":[0.001576538,0.0001743897,0.002806909,0.005328046,0.0001826041,0.0006635788,0.001005271,0.001034588,0.03564652,0.005123076,0.8738579,0.07260069],"study_design_scores_gemma":[0.0004450495,0.000189204,0.005704086,0.001234257,0.0001687022,0.0008572137,0.0004862267,0.005527087,0.03918941,0.008767234,0.9371659,0.0002657067],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.00719948,0.001437533,0.1402485,0.001344026,0.001300668,0.001276727,0.5995298,0.2365114,0.01115181],"genre_scores_gemma":[0.005815145,0.000957887,0.2181862,0.000570817,0.0001311142,0.001377539,0.7501715,0.01907645,0.003713325],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04333566,"threshold_uncertainty_score":0.1449722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02482944213963329,"score_gpt":0.2425919930497088,"score_spread":0.2177625509100755,"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."}}