{"id":"W4220680270","doi":"10.3389/fmicb.2022.811495","title":"Machine Learning and Deep Learning Applications in Metagenomic Taxonomy and Functional Annotation","year":2022,"lang":"en","type":"review","venue":"Frontiers in Microbiology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Metagenomics; Genome; Computational biology; Annotation; Biology; False positive paradox; Shotgun sequencing; Robustness (evolution); DNA sequencing; Gene prediction; Gene Annotation; Artificial intelligence; Computer science; Gene; Genetics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002152486,0.0002491862,0.0006204964,0.0002174265,0.0001353442,0.00001175535,0.00008832338,0.0002205485,0.00001543524],"category_scores_gemma":[0.00003300097,0.0002514983,0.00007827271,0.0001168414,0.0001120463,8.039827e-7,0.0002555482,0.0003974346,8.918698e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005177297,"about_ca_system_score_gemma":0.00005062018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002217432,"about_ca_topic_score_gemma":0.00006656868,"domain_scores_codex":[0.9986157,0.0002870298,0.0003288376,0.000536496,0.00001764891,0.0002142413],"domain_scores_gemma":[0.9996334,0.00004503909,0.0001809384,0.0001021382,0.0000104333,0.00002808115],"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":[0.0000269803,0.00003737418,0.02993416,0.0007598985,0.0002981304,0.000002677249,0.0000809355,0.0001529423,0.003229391,0.00002840523,0.0001460188,0.9653031],"study_design_scores_gemma":[0.0002416794,0.00007526656,0.0002125528,0.00002797413,0.00007855649,0.00003593085,0.0001897396,0.00001870357,0.000006352017,0.00002100305,0.9988649,0.0002272988],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001668313,0.9963565,0.001087756,0.000005657294,0.0001693273,0.0005651808,0.00004370156,0.000002634771,0.0001008771],"genre_scores_gemma":[0.0006133032,0.9948077,0.00209441,0.00001800803,0.00005975026,0.0005377521,0.00162389,0.00002791216,0.0002172315],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9987189,"threshold_uncertainty_score":0.9999937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0182077084202622,"score_gpt":0.2391291566612233,"score_spread":0.2209214482409611,"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."}}