{"id":"W2012080711","doi":"10.1111/j.1755-0998.2009.02651.x","title":"Efficient algorithms for the discovery of DNA oligonucleotide barcodes from sequence databases","year":2009,"lang":"en","type":"article","venue":"Molecular Ecology Resources","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Simon Fraser University; Agriculture and Agri-Food Canada","funders":"","keywords":"Biology; Oligonucleotide; Sequence (biology); Computational biology; Sequence database; DNA sequencing; DNA; Genetics; Database; Computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001643252,0.00016836,0.0002086799,0.00002824122,0.0001467145,0.00001844761,0.0003450967,0.00007358968,0.000003923913],"category_scores_gemma":[0.0001333832,0.0001261002,0.0001452524,0.00005663903,0.0002405512,6.61693e-7,0.0001474654,0.00005280109,0.000001421944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007321879,"about_ca_system_score_gemma":0.00003467097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005185187,"about_ca_topic_score_gemma":0.00005009545,"domain_scores_codex":[0.9989787,0.00006241311,0.0002302293,0.0003728165,0.00008981036,0.0002660635],"domain_scores_gemma":[0.9992031,0.0001200632,0.0001185068,0.0004586582,0.00006341995,0.00003629093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007961444,0.00006805773,0.001875688,0.000005577842,0.0001559194,0.000004220347,0.0001127163,0.004145563,0.9914879,0.0002413513,0.0002042982,0.001619144],"study_design_scores_gemma":[0.0008160167,0.0007245279,0.07815394,0.00001533313,0.000169893,0.0000102674,0.000367447,0.002044329,0.8961517,0.0006374472,0.02057307,0.0003360136],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881988,0.004460208,0.005939454,0.0005301106,0.0001109539,0.0003108676,0.0003243922,0.000004004121,0.0001211711],"genre_scores_gemma":[0.9958127,0.0001844796,0.002976015,0.0007257856,0.0001200832,0.00003598432,0.00006742282,0.00001519888,0.00006231747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09533613,"threshold_uncertainty_score":0.5142215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01867341585266136,"score_gpt":0.2610099011311425,"score_spread":0.2423364852784811,"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."}}