{"id":"W4413354762","doi":"10.1128/spectrum.03033-24","title":"Predicting hydrocarbon presence in marine cold seep sediments using machine learning models trained with benthic bacterial 16S rRNA taxonomy","year":2025,"lang":"en","type":"article","venue":"Microbiology Spectrum","topic":"Methane Hydrates and Related Phenomena","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Nova Scotia; Petroleum Technology Research Centre; Geological Survey of Canada; University of Calgary","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Foundation for Innovation; Genome Canada","keywords":"Cold seep; Benthic zone; Phylum; 16S ribosomal RNA; Geology; Microbial population biology; Hydrocarbon exploration; Context (archaeology); Ecology; Biology; Oceanography; Paleontology; Bacteria; Methane","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":[0.001304667,0.0009534518,0.000507488,0.0006428353,0.0002671851,0.0007278364,0.0004952885,0.0006544636,0.0004377528],"category_scores_gemma":[0.001954408,0.0003109305,0.000718206,0.0003410035,0.000215049,0.0004507627,0.0004305419,0.0006163977,0.0002434273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006893757,"about_ca_system_score_gemma":0.0007816167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01569475,"about_ca_topic_score_gemma":0.01219348,"domain_scores_codex":[0.9997898,0.00006341179,0.00001746031,0.00008047935,0.00001852033,0.00003052765],"domain_scores_gemma":[0.9992056,0.0004523079,0.0001009333,0.00004675849,0.0001433175,0.00005106753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002308055,0.0002951482,0.1176181,0.00004583028,0.0001976198,0.00007890855,0.0000570638,0.8431813,0.006151215,0.0001136565,0.0004091503,0.03162137],"study_design_scores_gemma":[0.000003505732,0.00004108343,0.005274125,0.000003476799,0.000008534473,0.000004175749,0.00001066419,0.9940975,0.0004502016,0.00006618258,0.00003627429,0.000004339248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830498,0.0001726167,0.01571841,0.0001223712,0.00002479941,0.00002797686,0.0003147337,0.0002269269,0.0003422544],"genre_scores_gemma":[0.9921224,0.00004712789,0.006988345,0.00003563379,0.0000121494,0.00002530805,0.0004617404,0.000008063669,0.0002992529],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01569475,"threshold_uncertainty_score":0.03120679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01229046257086386,"score_gpt":0.1969811356460826,"score_spread":0.1846906730752187,"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."}}