{"id":"W3196958573","doi":"10.3897/bdj.9.e71378","title":"Molecular Acquisition, Cleaning and Evaluation in R (MACER) - A tool to assemble molecular marker datasets from BOLD and GenBank","year":2021,"lang":"en","type":"article","venue":"Biodiversity Data Journal","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"GenBank; Construct (python library); Computer science; Upload; Component (thermodynamics); Process (computing); Data mining; Sequence (biology); Information retrieval; Data science; Biology; World Wide Web","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":[0.0004524038,0.0001197296,0.000128287,0.00004630432,0.0001488621,0.0001188511,0.0002136788,0.00007561337,0.00004600934],"category_scores_gemma":[0.0001141574,0.000133313,0.0000225379,0.00007187702,0.00003038181,0.000008620246,0.001170847,0.00008728146,0.000004662495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001944877,"about_ca_system_score_gemma":0.00007989962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007243493,"about_ca_topic_score_gemma":0.00006488116,"domain_scores_codex":[0.9989336,0.0001244917,0.0001529185,0.0004338263,0.0001822801,0.0001729168],"domain_scores_gemma":[0.9993086,0.00001049083,0.00005907266,0.0004124306,0.000105196,0.0001041616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00009291344,0.00004483341,0.05550924,0.000007784953,0.0001753471,0.0001599139,0.00008708575,0.0001055587,0.9258061,0.000007105119,0.01194208,0.006062027],"study_design_scores_gemma":[0.004137652,0.0002612975,0.8112,0.00007347511,0.0004581895,0.000350977,0.001097842,0.001176151,0.1131932,0.0004091594,0.06678078,0.0008613227],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9902025,0.006101581,0.0005071202,0.0004944847,0.00008144625,0.0001113035,0.00245163,0.000001104622,0.00004880261],"genre_scores_gemma":[0.9901693,0.00121432,0.004742557,0.000996615,0.00006794781,0.000001488329,0.002798601,0.000005917874,0.000003219835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.812613,"threshold_uncertainty_score":0.5436345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02641788231621638,"score_gpt":0.2679851368399678,"score_spread":0.2415672545237514,"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."}}