{"id":"W6927400462","doi":"10.3389/fmicb.2021.764058.s002","title":"Data_Sheet_2_CANT-HYD: A Curated Database of Phylogeny-Derived Hidden Markov Models for Annotation of Marker Genes Involved in Hydrocarbon Degradation.docx","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Metagenomics; Hydrocarbon; Hidden Markov model; Genome; Annotation; Gene; Degradation (telecommunications); Markov chain","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001657265,0.003524102,0.001988726,0.003709339,0.001263283,0.002575069,0.004988015,0.003537515,0.135138],"category_scores_gemma":[0.006541223,0.0014102,0.002110171,0.004849439,0.0007045087,0.001711089,0.002211528,0.002976263,0.1136931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001751492,"about_ca_system_score_gemma":0.002442249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01694421,"about_ca_topic_score_gemma":0.03429114,"domain_scores_codex":[0.9991112,0.0001600033,0.0001311219,0.0002832195,0.0001797906,0.0001345563],"domain_scores_gemma":[0.9977902,0.0009053369,0.0002589724,0.0004449604,0.0003396024,0.0002609093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000161589,0.0000550229,0.002111926,0.002853013,0.000103004,0.00006523098,0.00004320634,0.001055179,0.0006107659,0.0006406903,0.9892145,0.003085979],"study_design_scores_gemma":[0.00107762,0.00007501529,0.007241889,0.0008159131,0.0001361984,0.000173653,0.0001318895,0.002041138,0.001553829,0.002971752,0.9836992,0.0000818892],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00009807244,0.00003606603,0.00008666112,0.00002559814,0.000009642594,0.00001264529,0.9991124,0.000430508,0.0001883685],"genre_scores_gemma":[0.0003310721,0.00003566884,0.0004669703,0.0000398411,0.000003267442,0.00008469682,0.9987466,0.0001034542,0.0001883227],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.135138,"threshold_uncertainty_score":0.4520816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07515715983014613,"score_gpt":0.2730198081695681,"score_spread":0.197862648339422,"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."}}