{"id":"W4385347606","doi":"10.1101/2023.07.25.550582","title":"Systematic assessment of long-read RNA-seq methods for transcript identification and quantification","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Saint Petersburg State University; Ohio State University; National Institutes of Health; National Institute of General Medical Sciences; Ministerio de Ciencia e Innovación; Bundesministerium für Bildung und Forschung; Generalitat de Catalunya; Wellcome Trust; National Human Genome Research Institute; European Molecular Biology Laboratory; Oxford Nanopore Technologies; Centres de Recerca de Catalunya","keywords":"Computational biology; RNA-Seq; Identification (biology); Transcriptome; Annotation; Biology; Benchmark (surveying); cDNA library; Genome; Replicate; Computer science; Complementary DNA; Bioinformatics; Genetics; Gene; Gene expression; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001556785,0.000319681,0.0005612107,0.0001272499,0.0001068566,0.00007938966,0.0003101107,0.0003425891,0.000001074631],"category_scores_gemma":[0.000278788,0.0003344591,0.0001740053,0.0001289373,0.00009796884,0.000001960195,0.0001877742,0.0001265373,0.000001303598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003844813,"about_ca_system_score_gemma":0.0002029313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002094313,"about_ca_topic_score_gemma":0.000004447239,"domain_scores_codex":[0.9978809,0.0002088531,0.0007563879,0.0007746838,0.000138534,0.0002406258],"domain_scores_gemma":[0.9977294,0.00008063963,0.0006315692,0.000951863,0.0005250184,0.00008151022],"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":[0.00001233183,0.0000487771,0.001026105,0.009656347,0.0004144679,4.091686e-7,0.000009331926,0.000079014,0.9883635,0.0003475184,0.00003482687,0.000007353398],"study_design_scores_gemma":[0.0003581967,0.00009851515,0.1010566,0.001164627,0.0004734623,1.624051e-8,0.00001112841,0.001528735,0.8946429,0.00001824139,0.0001967203,0.0004508178],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.616635,0.008124683,0.371397,0.0001435248,0.001146645,0.00214277,0.0003781461,0.00003035861,0.000001964471],"genre_scores_gemma":[0.9629846,0.00210844,0.03375119,0.00001944667,0.0001373125,0.0008898803,0.000004348421,0.00008459672,0.00002014944],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3463497,"threshold_uncertainty_score":0.9999108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03629967745661278,"score_gpt":0.3194767444018824,"score_spread":0.2831770669452696,"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."}}