{"id":"W3170936754","doi":"10.1101/2021.06.10.447808","title":"CANT-HYD: A curated database of phylogeny-derived Hidden Markov Models for annotation of marker genes involved in hydrocarbon degradation","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Microbial bioremediation and biosurfactants","field":"Environmental Science","cited_by":4,"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; Gene; Computational biology; Hydrocarbon; Biology; Identification (biology); Genetics; Chemistry; Ecology; Organic chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001587094,0.002998846,0.001945334,0.004324014,0.001195028,0.001766028,0.00238712,0.001980985,0.008987879],"category_scores_gemma":[0.004553694,0.001382192,0.001635123,0.003657526,0.0004577372,0.00102973,0.001556795,0.001600601,0.004526674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001134145,"about_ca_system_score_gemma":0.002518011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003817688,"about_ca_topic_score_gemma":0.008269451,"domain_scores_codex":[0.9991174,0.0001880638,0.0001308873,0.0002857264,0.0002054007,0.00007237253],"domain_scores_gemma":[0.9981372,0.0009938052,0.0002250954,0.0003175327,0.0001927291,0.0001335064],"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":[0.005959249,0.0009678809,0.01974015,0.0169825,0.002156488,0.002829245,0.0009500796,0.0894098,0.257844,0.0165727,0.4191005,0.1674874],"study_design_scores_gemma":[0.001767595,0.0007833049,0.02855824,0.001232552,0.001089103,0.001441933,0.0004495157,0.4257677,0.09971038,0.02699024,0.411556,0.0006534588],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05770687,0.003027754,0.1479691,0.0003454501,0.0002535334,0.0004334669,0.6797469,0.1057921,0.004724813],"genre_scores_gemma":[0.06759545,0.001160652,0.1309708,0.0001259294,0.00005656608,0.0009638089,0.7931045,0.004873688,0.001148526],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.008987879,"threshold_uncertainty_score":0.03006744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01987544167243969,"score_gpt":0.218038897968501,"score_spread":0.1981634562960612,"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."}}