{"id":"W4248218360","doi":"10.7287/peerj.preprints.26974","title":"Prioritizing bona fide bacterial small RNAs with machine learning classifiers","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Biology; Computational biology; ORFS; Open reading frame; Genome; Transfer RNA; Bacterial genome size; Terminator (solar); Genetics; Gene; Machine learning; Artificial intelligence; RNA; Computer science; Peptide sequence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002342993,0.001694343,0.001117864,0.001836974,0.0004819703,0.001361289,0.001102248,0.00149437,0.001124524],"category_scores_gemma":[0.004609489,0.0004137395,0.0009857175,0.0006826151,0.0004025906,0.001441275,0.0007798162,0.00160585,0.0007290919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008967022,"about_ca_system_score_gemma":0.001166455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002378826,"about_ca_topic_score_gemma":0.002093634,"domain_scores_codex":[0.998991,0.0003256493,0.0000753132,0.0002737427,0.0001979387,0.000136421],"domain_scores_gemma":[0.9971184,0.001950745,0.000237804,0.0001356108,0.0004325999,0.0001248929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008864096,0.0006696152,0.02921852,0.000323418,0.0003122273,0.0003091722,0.0001661841,0.5410333,0.04375217,0.002648671,0.003553011,0.3771273],"study_design_scores_gemma":[0.000008165754,0.00006162481,0.0005899471,0.00000725542,0.00001650349,0.00001773436,0.00001580182,0.9927987,0.00491665,0.00129849,0.0002614975,0.000007682152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4360659,0.001550321,0.5539761,0.0006574655,0.0001710289,0.0002079081,0.0006973073,0.003682991,0.002990886],"genre_scores_gemma":[0.7877349,0.0002789674,0.2086927,0.0002860021,0.0000982436,0.0001511778,0.001278902,0.0001188912,0.001360266],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002378826,"threshold_uncertainty_score":0.01239109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01878352746188341,"score_gpt":0.2263962431520289,"score_spread":0.2076127156901454,"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."}}