{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000235986,0.0001761038,0.0002162119,0.00004633906,0.0001003344,0.00005495888,0.0004136561,0.00009192189,0.0000215192],"category_scores_gemma":[0.0001099709,0.000174505,0.00005943917,0.000107313,0.00007303165,0.00000310343,0.0008919673,0.00007242661,0.00002260256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001808496,"about_ca_system_score_gemma":0.0001895438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001680813,"about_ca_topic_score_gemma":0.0005900033,"domain_scores_codex":[0.9988865,0.00003746078,0.000413555,0.0002595815,0.0001099287,0.0002929371],"domain_scores_gemma":[0.9988896,0.00002605148,0.0001064574,0.0008682642,0.00005324275,0.00005642236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002543224,0.0006260935,0.3237102,0.001294747,0.001261329,0.00007787766,0.003590593,0.01313074,0.6063212,0.004253996,0.02142419,0.02405467],"study_design_scores_gemma":[0.005478994,0.000379446,0.3045603,0.0001013217,0.0002868911,0.0003960891,0.007158889,0.1768583,0.2169031,0.001778776,0.2832711,0.002826752],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9698325,0.004682523,0.01920898,0.00007544074,0.0003287432,0.0001901044,0.0005444024,0.000007748411,0.005129504],"genre_scores_gemma":[0.8029959,0.000722028,0.1931449,0.0003439519,0.0002678023,0.00001350796,0.001894404,0.000030478,0.0005871016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3894181,"threshold_uncertainty_score":0.7116106,"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."}}