{"id":"W3092758170","doi":"10.1128/aem.01928-20","title":"A Need for Improved Cellulase Identification from Metagenomic Sequence Data","year":2020,"lang":"en","type":"article","venue":"Applied and Environmental Microbiology","topic":"Biofuel production and bioconversion","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Government of Canada","keywords":"Metagenomics; Cellulase; Identification (biology); Categorization; Computational biology; Biology; Resource (disambiguation); Annotation; Computer science; Biotechnology; Data science; Bioinformatics; Cellulose; Gene; Genetics; Ecology; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.07112538,0.002318292,0.005465577,0.01187285,0.001651364,0.01156877,0.004885681,0.004874899,0.002569871],"category_scores_gemma":[0.1206541,0.00225084,0.003189847,0.008525109,0.002212028,0.01958803,0.003951368,0.01306338,0.006895219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002312438,"about_ca_system_score_gemma":0.00785645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003336239,"about_ca_topic_score_gemma":0.007542992,"domain_scores_codex":[0.9719397,0.01241021,0.004656129,0.004260042,0.005969006,0.0007649207],"domain_scores_gemma":[0.8195689,0.07175034,0.01183498,0.02661628,0.06485645,0.005373029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006466126,0.0006237834,0.0257789,0.01886225,0.001289374,0.0006125789,0.001730247,0.003979998,0.2678453,0.009007479,0.04975768,0.6198658],"study_design_scores_gemma":[0.000292892,0.0008278304,0.05672909,0.01892637,0.002068212,0.003260258,0.004384609,0.02682011,0.09264135,0.0889791,0.703615,0.001455148],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0601746,0.1131132,0.6466858,0.1284443,0.008192098,0.001647209,0.01824566,0.01577843,0.007718704],"genre_scores_gemma":[0.02088522,0.02096841,0.9156067,0.01054261,0.001771293,0.0004995291,0.02739742,0.001275244,0.001053534],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07112538,"threshold_uncertainty_score":0.3761514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02373002907140862,"score_gpt":0.1859508628048064,"score_spread":0.1622208337333978,"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."}}