{"id":"W3081286367","doi":"10.1186/s12859-021-03997-w","title":"geneRFinder: gene finding in distinct metagenomic data complexities","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Vale Canada Limited","keywords":"Metagenomics; Benchmark (surveying); McNemar's test; Gene prediction; Computational biology; Gene Annotation; Computer science; Data mining; Annotation; Biology; Gene; Machine learning; Artificial intelligence; Statistics; Genetics; Genome; Mathematics; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004271376,0.001914586,0.001210947,0.004182331,0.0008248259,0.001924608,0.002726877,0.001683987,0.00692341],"category_scores_gemma":[0.01602702,0.000713992,0.001685089,0.002546718,0.000835878,0.003037434,0.00203354,0.001877793,0.002422317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008622598,"about_ca_system_score_gemma":0.001675118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00157463,"about_ca_topic_score_gemma":0.002879092,"domain_scores_codex":[0.9980457,0.0004137955,0.0001793934,0.0006269967,0.0005874228,0.0001467036],"domain_scores_gemma":[0.9935287,0.004741692,0.000508829,0.0006080373,0.0003965058,0.0002162354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003876469,0.0005515772,0.08699232,0.003115376,0.001249189,0.001564728,0.0006979867,0.1171492,0.03711923,0.01125303,0.127203,0.609228],"study_design_scores_gemma":[0.0002421663,0.0004086002,0.007518785,0.0002060062,0.0001803529,0.000999536,0.0002187665,0.9020886,0.03545986,0.02415501,0.02838032,0.0001420322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1072444,0.002362288,0.626229,0.0012973,0.0003939681,0.000347025,0.03086203,0.2284723,0.002791665],"genre_scores_gemma":[0.2906195,0.0006257326,0.6603079,0.0006750437,0.0001799819,0.0006764028,0.0399824,0.005087381,0.00184561],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00692341,"threshold_uncertainty_score":0.02316111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08674744853583267,"score_gpt":0.28577810191656,"score_spread":0.1990306533807273,"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."}}