{"id":"W6946355723","doi":"10.3389/fmicb.2021.764058.s001","title":"Data_Sheet_1_CANT-HYD: A Curated Database of Phylogeny-Derived Hidden Markov Models for Annotation of Marker Genes Involved in Hydrocarbon Degradation.zip","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Chemical synthesis and alkaloids","field":"Chemistry","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":[0.001399395,0.00374133,0.002111766,0.003323069,0.001178452,0.002603016,0.005151362,0.004090699,0.09242873],"category_scores_gemma":[0.005486128,0.001225999,0.001777776,0.005092619,0.0006677929,0.001645767,0.002093904,0.002823195,0.1194126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001561787,"about_ca_system_score_gemma":0.002346599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01456006,"about_ca_topic_score_gemma":0.02769283,"domain_scores_codex":[0.9991449,0.000138884,0.0001062449,0.0002994439,0.0001939898,0.0001165161],"domain_scores_gemma":[0.9983942,0.0006658518,0.0001839165,0.0003352844,0.0002466844,0.0001741032],"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":[0.0001746054,0.00006123973,0.001723523,0.002870381,0.0001043092,0.00008233172,0.00004178784,0.001497977,0.0008927212,0.000910302,0.9873169,0.004323778],"study_design_scores_gemma":[0.0007705679,0.00006126173,0.00390717,0.0005478334,0.0001068256,0.0001508399,0.00008354191,0.002067571,0.001581351,0.003299135,0.9873524,0.00007143796],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001292488,0.00006893729,0.0001251381,0.00002884596,0.00001024815,0.00001133213,0.9987689,0.0005595768,0.0002978374],"genre_scores_gemma":[0.000312509,0.00004436075,0.0004840035,0.00003367481,0.000002347133,0.00006535051,0.9987942,0.00008938414,0.0001742041],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.09242873,"threshold_uncertainty_score":0.3092049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04730051216846351,"score_gpt":0.263866681803023,"score_spread":0.2165661696345595,"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."}}