{"id":"W6964967232","doi":"10.3389/fmicb.2021.764058.s007","title":"Table_4_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":"Forest Ecology and Biodiversity Studies","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":[0.001292768,0.004196451,0.002345986,0.003995863,0.001505395,0.002902634,0.004752759,0.003476314,0.1586262],"category_scores_gemma":[0.00541361,0.001422187,0.002279837,0.005364311,0.000620375,0.001900465,0.002328232,0.002622784,0.1108497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001650122,"about_ca_system_score_gemma":0.002277781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01343626,"about_ca_topic_score_gemma":0.03171459,"domain_scores_codex":[0.9991273,0.0001516153,0.0001141352,0.0003167175,0.0001656773,0.0001245197],"domain_scores_gemma":[0.9982314,0.00087504,0.0001922285,0.0003095912,0.0002183294,0.0001734713],"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":[0.0002112973,0.00006628891,0.002919536,0.004575863,0.0001755141,0.0001088997,0.00006784214,0.001429531,0.001257937,0.0009446939,0.9838532,0.004389357],"study_design_scores_gemma":[0.00118452,0.00009560923,0.009046952,0.001049881,0.0002049334,0.0002284611,0.0001594312,0.00292108,0.002163393,0.004036068,0.9787982,0.0001114868],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001636739,0.00008024718,0.0001512735,0.00002338022,0.00001345875,0.00001174605,0.998462,0.0008120484,0.0002822016],"genre_scores_gemma":[0.0004729443,0.00006251172,0.0007258049,0.00003936152,0.000003655711,0.00008225699,0.9981976,0.0002122382,0.0002036995],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1586262,"threshold_uncertainty_score":0.5306576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05592549175014479,"score_gpt":0.235554992640425,"score_spread":0.1796295008902802,"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."}}