{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003558976,0.0002681374,0.0003332824,0.0001225276,0.0001772723,0.00002687988,0.0002707646,0.0001991631,0.0008174421],"category_scores_gemma":[0.00001300795,0.0002245874,0.00004453297,0.0004199907,0.0002207452,0.0001518984,0.0004103963,0.0005891454,0.00001993957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000284861,"about_ca_system_score_gemma":0.00003384853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002168572,"about_ca_topic_score_gemma":0.001295094,"domain_scores_codex":[0.9981881,0.0002117432,0.0003649815,0.0005803165,0.00007039978,0.0005844717],"domain_scores_gemma":[0.9994926,0.00006357706,0.0001555627,0.0002164394,0.000003863559,0.00006796816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002096443,0.00009585486,0.3069291,0.00001509268,0.00007294412,0.00002421402,0.0002418066,0.120309,0.5719073,0.00007741834,0.00001079835,0.0001067643],"study_design_scores_gemma":[0.009120707,0.001039911,0.01106105,0.0004135714,0.0002308388,0.0001875571,0.0002772896,0.801848,0.1642549,0.001848706,0.008245308,0.001472219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927396,0.00007677191,0.0005237267,0.0002083268,0.0002661426,0.0005723448,0.00001099856,0.0000552429,0.005546917],"genre_scores_gemma":[0.9967282,0.0000226565,0.001721525,0.0001131488,0.00003977387,0.00002921538,0.00006182322,0.00002080726,0.001262781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.681539,"threshold_uncertainty_score":0.9158408,"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."}}