{"id":"W2045510682","doi":"10.1101/gr.147901","title":"Evaluation of Gene-Finding Programs on Mammalian Sequences","year":2001,"lang":"en","type":"article","venue":"Genome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pacific Centre for Reproductive Medicine; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Exon; Sequence (biology); Gene prediction; Computational biology; Gene; Sequence analysis; Genetics; Strengths and weaknesses; Function (biology); Genome","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":[0.005328821,0.00008245864,0.0000849937,0.0001363228,0.0001135115,0.00003165482,0.0002808163,0.0001007268,0.00009611266],"category_scores_gemma":[0.0004049683,0.00007371401,0.00004366875,0.000268142,0.0001223208,0.000003340426,0.00008414347,0.000183654,0.00006292223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000056573,"about_ca_system_score_gemma":0.0001922649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003413591,"about_ca_topic_score_gemma":0.00001952273,"domain_scores_codex":[0.9977363,0.000377131,0.000196618,0.0001948376,0.001160233,0.0003348617],"domain_scores_gemma":[0.9989237,0.00001767727,0.00006500537,0.0003570461,0.0005693318,0.00006723317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001304936,0.0001767254,0.02427672,0.00009516697,0.000107664,0.000006192744,0.0006289343,0.004482752,0.7806674,0.0003939153,0.0002596639,0.1887743],"study_design_scores_gemma":[0.004263208,0.01045772,0.09763709,0.0002094395,0.0001440269,0.0002168248,0.003040274,0.02881101,0.5914286,0.002607363,0.2597926,0.001391881],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9685731,0.0003420147,0.0002086265,0.0001310183,0.00003862043,0.0003900354,0.000003629087,0.000007312134,0.03030564],"genre_scores_gemma":[0.9972047,0.0001095272,0.001550645,0.00001667167,0.0001497411,0.00004330899,0.0001188542,0.00001293209,0.000793632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2595329,"threshold_uncertainty_score":0.300597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1565077522533462,"score_gpt":0.4316221012825429,"score_spread":0.2751143490291966,"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."}}