{"id":"W2821433317","doi":"10.7717/peerj.6304","title":"Prioritizing bona fide bacterial small RNAs with machine learning classifiers","year":2019,"lang":"en","type":"article","venue":"PeerJ","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Computational biology; Genome; Context (archaeology); Precision and recall; Artificial intelligence; ORFS; Pipeline (software); Open reading frame; Machine learning; Bacterial genome size; Genetics; Gene; Computer science; Peptide sequence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009764408,0.0001351278,0.0001435972,0.0000193388,0.00007663869,0.00002771657,0.0001075927,0.00007104407,0.0000261479],"category_scores_gemma":[0.0000257193,0.0001159647,0.00005343394,0.00003324507,0.00003456824,5.155157e-7,0.0001004372,0.00009572884,0.00002444388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009100754,"about_ca_system_score_gemma":0.00003973125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005147856,"about_ca_topic_score_gemma":0.000100072,"domain_scores_codex":[0.9992834,0.00002666863,0.0001107377,0.0002814938,0.00007344423,0.0002242521],"domain_scores_gemma":[0.9996448,0.00001152017,0.00005510386,0.000188308,0.0000471822,0.0000531098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001151151,0.00001252696,0.06417924,0.00001483787,0.00007075924,0.000002737931,0.0000813294,0.00007584682,0.9334421,0.00004375304,0.0001278613,0.001833888],"study_design_scores_gemma":[0.00230782,0.001266912,0.1335634,0.00003064253,0.00005988452,0.00005191554,0.0002909786,0.0002980908,0.1223295,0.00006321474,0.7390789,0.0006588433],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943475,0.0007382719,0.00009594706,0.0001450839,0.000237634,0.0001275207,0.00001161366,0.000006559236,0.004289929],"genre_scores_gemma":[0.9942265,0.0001446939,0.001355304,0.0001041465,0.0002628093,0.000007625649,0.00006275198,0.00002520151,0.003810938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8111126,"threshold_uncertainty_score":0.4728902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009201968950497007,"score_gpt":0.1981520699552252,"score_spread":0.1889501010047282,"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."}}