{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001269705,0.0004419092,0.0007630968,0.000186908,0.00005318,0.00002927311,0.0008939324,0.0003635818,0.2913091],"category_scores_gemma":[0.00100727,0.0004710887,0.0002122433,0.0003460417,0.00002335191,0.0002413556,0.0005111734,0.0003628928,0.000008069227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000149633,"about_ca_system_score_gemma":0.0002552877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004404222,"about_ca_topic_score_gemma":0.0002356015,"domain_scores_codex":[0.9974535,0.00006052399,0.000922965,0.0007130254,0.0005007659,0.0003491871],"domain_scores_gemma":[0.9972672,0.0005377299,0.0008809836,0.001039107,0.0001776092,0.00009731871],"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":[0.0003128414,0.0002012908,0.000005874297,0.004773429,0.00009954782,0.00000922549,0.00001344411,0.00003060816,0.1131382,7.138463e-7,0.8799174,0.001497386],"study_design_scores_gemma":[0.001758249,0.00005242354,0.0000300046,0.004653696,0.0002117335,0.000003511747,0.0001373619,0.009330787,0.2225495,0.00007681389,0.7601889,0.001007039],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.003741079,0.001192819,0.000001434224,0.0000115623,0.00003360218,0.0004261689,0.9944833,0.00002463374,0.00008541593],"genre_scores_gemma":[0.002727865,0.0001806546,0.0002328947,0.00003065976,0.00009148946,0.001028908,0.9955937,0.00006113564,0.00005269562],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.291301,"threshold_uncertainty_score":0.9997741,"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."}}