{"id":"W4409148392","doi":"10.1038/s42003-025-07912-4","title":"Definition of the microbial rare biosphere through unsupervised machine learning","year":2025,"lang":"en","type":"article","venue":"Communications Biology","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of Ottawa","funders":"Fundação para a Ciência e a Tecnologia; Natural Sciences and Engineering Research Council of Canada; Centro Interdisciplinar de Investigação Marinha e Ambiental; Norsk Polarinstitutt; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Biosphere; Abundance (ecology); Relative species abundance; Rare species; Artificial intelligence; Ecology; Microbial population biology; Computer science; Machine learning; Taxon; Unsupervised learning; Biology; Paleontology; Bacteria","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":[0.005541739,0.0007819471,0.0009592259,0.004400257,0.000892952,0.002757899,0.001184413,0.0007104713,0.00100291],"category_scores_gemma":[0.01202754,0.0002700012,0.001140763,0.002490363,0.001427993,0.001664197,0.002948231,0.001495856,0.0006464823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008142351,"about_ca_system_score_gemma":0.001726836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002543912,"about_ca_topic_score_gemma":0.003739076,"domain_scores_codex":[0.9967383,0.001055244,0.0003475824,0.0009615577,0.0007067443,0.0001906501],"domain_scores_gemma":[0.9933903,0.003511985,0.00115026,0.0008902472,0.0008529908,0.0002042457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005395124,0.0003619825,0.2877318,0.003788309,0.001531908,0.0004974789,0.002240768,0.09890763,0.06446751,0.0454479,0.02680423,0.467681],"study_design_scores_gemma":[0.0001008616,0.0001944627,0.1105495,0.000622927,0.0002937728,0.0007752674,0.0009167239,0.6649583,0.03331508,0.1193407,0.06866925,0.0002632027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1139237,0.001816003,0.8660387,0.0004897364,0.00009590635,0.0004305787,0.008899548,0.003815122,0.004490715],"genre_scores_gemma":[0.3955585,0.0006520994,0.5847124,0.0004188576,0.0001109619,0.001056277,0.01586718,0.0007147596,0.0009089639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005541739,"threshold_uncertainty_score":0.0293079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02883959975848542,"score_gpt":0.2671740474658041,"score_spread":0.2383344477073187,"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."}}