{"id":"W4295367167","doi":"10.1038/s41597-022-01665-z","title":"A georeferenced rRNA amplicon database of aquatic microbiomes from South America","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Agencia Santafesina de Ciencia, Tecnología e Innovación; Consejo Nacional de Investigaciones Científicas y Técnicas; Agencia Nacional de Promoción Científica y Tecnológica; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Georeference; Ecology; Geography; Microbiome; Biology; Biodiversity; Database; Physical geography; Computer science; Bioinformatics","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":[0.00134923,0.0007597455,0.0009015657,0.008889553,0.00131363,0.001170123,0.0009000465,0.0005878914,0.00312098],"category_scores_gemma":[0.002979623,0.0005038362,0.0006448827,0.0119672,0.0003811468,0.001067895,0.00228816,0.000752957,0.002539328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007919989,"about_ca_system_score_gemma":0.005646736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01282373,"about_ca_topic_score_gemma":0.02966826,"domain_scores_codex":[0.9987901,0.00009299186,0.0002617922,0.0003658273,0.0003161405,0.0001731521],"domain_scores_gemma":[0.9979108,0.0002502176,0.0005132849,0.0003389652,0.0006862477,0.0003003453],"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":[0.002299778,0.0004435077,0.1557553,0.01088679,0.0007167176,0.00190106,0.007673353,0.002273679,0.4617217,0.002473525,0.09003922,0.2638154],"study_design_scores_gemma":[0.000102276,0.0002057449,0.4748389,0.001008821,0.0004492064,0.001049959,0.001633653,0.001610984,0.03119106,0.001214483,0.4865545,0.0001402482],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2127458,0.003495152,0.00902217,0.000225954,0.00007927838,0.0003193472,0.7666059,0.001666552,0.00583986],"genre_scores_gemma":[0.05101354,0.001534595,0.03131398,0.0001034681,0.00001979529,0.0004991189,0.9141675,0.0003190409,0.00102895],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01282373,"threshold_uncertainty_score":0.02549815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0461665178413495,"score_gpt":0.2564124567701193,"score_spread":0.2102459389287697,"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."}}