{"id":"W4226190998","doi":"10.3389/fmicb.2021.764058","title":"CANT-HYD: A Curated Database of Phylogeny-Derived Hidden Markov Models for Annotation of Marker Genes Involved in Hydrocarbon Degradation","year":2022,"lang":"en","type":"article","venue":"Frontiers in Microbiology","topic":"Biofuel production and bioconversion","field":"Engineering","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Government of Alberta; Genome Canada","keywords":"Metagenomics; Degradation (telecommunications); Gene; Phylum; Computational biology; Sequence database; Genome; Hydrocarbon; Biology; Database; Computer science; Chemistry; Genetics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002591721,0.0001120087,0.0002431389,0.0003557532,0.00002374114,0.000001798635,0.0001276183,0.00009087435,0.00002005686],"category_scores_gemma":[0.00001123601,0.0001245671,0.00003983845,0.0002917867,0.00005691285,0.00008262972,0.00004815838,0.0001198495,1.932526e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001335956,"about_ca_system_score_gemma":0.00003291351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002076569,"about_ca_topic_score_gemma":0.00008065478,"domain_scores_codex":[0.9991169,0.0001153598,0.0003481549,0.0002119024,0.00003657771,0.0001710908],"domain_scores_gemma":[0.9996865,0.00001711411,0.00009823473,0.0001471056,0.00003523206,0.00001584943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003296813,0.00004764296,0.004764269,0.0002083307,0.00003148421,9.101636e-7,0.0002595608,0.006331405,0.9828539,0.00000681995,0.002613315,0.002552692],"study_design_scores_gemma":[0.003010792,0.0001985556,0.001556977,0.00004431973,0.00003326997,0.000007808428,0.002031225,0.4485009,0.5411356,0.0004294263,0.002683951,0.000367162],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9864837,0.001903719,0.009756293,0.00005224202,0.0009277727,0.000482043,0.000346817,0.00002466069,0.00002275601],"genre_scores_gemma":[0.985856,0.0002725702,0.01238623,0.00002477918,0.00001533162,0.00006254988,0.001336554,0.00001639136,0.00002958301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4421695,"threshold_uncertainty_score":0.50797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01326671482194577,"score_gpt":0.2049205143376406,"score_spread":0.1916537995156948,"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."}}