{"id":"W6927552836","doi":"10.3389/fmicb.2021.764058.s005","title":"Table_2_CANT-HYD: A Curated Database of Phylogeny-Derived Hidden Markov Models for Annotation of Marker Genes Involved in Hydrocarbon Degradation.xlsx","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Analytical Chemistry and Sensors","field":"Chemical Engineering","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":[0.001282865,0.004802748,0.002529808,0.004127991,0.001596512,0.003115399,0.004935936,0.004093746,0.1458316],"category_scores_gemma":[0.005817913,0.001464529,0.002355548,0.005423822,0.0006357942,0.001909721,0.002325311,0.002632528,0.1175446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001568541,"about_ca_system_score_gemma":0.00226952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01265908,"about_ca_topic_score_gemma":0.02731418,"domain_scores_codex":[0.999092,0.0001423012,0.0001135359,0.00034496,0.0001868563,0.0001203434],"domain_scores_gemma":[0.9981706,0.00092519,0.0001842246,0.0003234359,0.0002282959,0.0001682503],"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":[0.0002322352,0.0000689122,0.002855589,0.004652426,0.000172961,0.0001269587,0.00005810737,0.001674145,0.00150425,0.0008655852,0.9828367,0.004952027],"study_design_scores_gemma":[0.001141891,0.0001147621,0.007907825,0.001033621,0.000220641,0.0002769618,0.0001397251,0.003506458,0.002602583,0.004399009,0.9785417,0.0001148778],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001670071,0.00009240917,0.0001670487,0.00002579524,0.00001448644,0.00001226985,0.9983852,0.0008558845,0.0002798316],"genre_scores_gemma":[0.0004205859,0.00006510401,0.0006561108,0.00003976848,0.000003638472,0.00007325225,0.9983706,0.0001853774,0.0001855822],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1458316,"threshold_uncertainty_score":0.4878553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04301659636739475,"score_gpt":0.2580304954836242,"score_spread":0.2150138991162294,"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."}}