{"id":"W2140048165","doi":"10.1093/bioinformatics/bth239","title":"Estimating and comparing the rates of gene discovery and expressed sequence tag (EST) frequencies in EST surveys","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Dalhousie University","funders":"Genome Atlantic; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Alfred P. Sloan Foundation","keywords":"Redundancy (engineering); Sample (material); Sequence (biology); Sample size determination; Computer science; False discovery rate; Gene; Statistics; Biology; Genetics; Mathematics","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":[0.000300111,0.00008418401,0.0001015005,0.00002894439,0.00005636673,0.00004746504,0.0000983873,0.00004992482,4.703363e-7],"category_scores_gemma":[0.00008371752,0.000060712,0.00001462559,0.00006901709,0.0001322033,0.00002294211,0.00006317534,0.00004834506,3.776618e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009898446,"about_ca_system_score_gemma":0.00006368423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009860429,"about_ca_topic_score_gemma":0.00006582488,"domain_scores_codex":[0.9994485,0.00003286058,0.0002447328,0.00009454312,0.00007703785,0.0001023645],"domain_scores_gemma":[0.9996119,0.00001546127,0.0001312641,0.0001841489,0.00003031573,0.00002696854],"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":[0.00001295126,0.00002212269,0.03085593,0.0001357076,0.00001178517,4.924455e-7,0.001561866,0.004196908,0.96026,0.0003457342,0.00003432462,0.002562122],"study_design_scores_gemma":[0.001155352,0.0001189403,0.08527324,0.0001925337,0.00001336627,0.0000224887,0.002363783,0.03298044,0.8767828,0.0006394564,0.0001816186,0.0002759756],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9788576,0.0004339292,0.02022554,0.0000726408,0.00003994555,0.000107318,0.000009834468,0.000004054201,0.0002491765],"genre_scores_gemma":[0.9876012,0.0001819218,0.01209093,0.0000446114,0.00002008602,0.00001015868,0.00003206654,0.000004810462,0.00001425853],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08347725,"threshold_uncertainty_score":0.2475764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03646441197339777,"score_gpt":0.281118808471943,"score_spread":0.2446543964985452,"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."}}