{"id":"W3037354611","doi":"10.1093/nargab/lqaa043","title":"Factorial study of the RNA-seq computational workflow identifies biases as technical gene signatures","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Modularity (biology); RNA-Seq; Pipeline (software); Computational biology; Computer science; Workflow; RNA; Modular design; Software; Gene; Biology; Genetics; Transcriptome; Gene expression; Database; Programming language","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":[0.00009318686,0.0001520417,0.0001845115,0.00002123464,0.0001510695,0.00004210164,0.0002390946,0.0001063737,0.000003461688],"category_scores_gemma":[0.0001071416,0.0001097211,0.00007977031,0.00008685623,0.0001084573,0.000001873455,0.0003776481,0.00009553749,0.000001994357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000752955,"about_ca_system_score_gemma":0.00007130846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001416424,"about_ca_topic_score_gemma":0.00001911121,"domain_scores_codex":[0.9991521,0.00002391925,0.0003619365,0.0001580695,0.0001656823,0.0001383453],"domain_scores_gemma":[0.9994617,0.00003364567,0.000167875,0.0001819525,0.00008889865,0.00006597465],"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":[0.0004011201,0.000374323,0.007692194,0.0001194602,0.0006074055,0.000002807137,0.007078776,0.02265776,0.9493709,0.0002435504,0.004218216,0.007233486],"study_design_scores_gemma":[0.01856792,0.01535394,0.1614878,0.0001646931,0.00125589,0.0001512994,0.0291735,0.04517936,0.6532864,0.007400204,0.06363356,0.004345412],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9980605,0.0006344064,0.0002924911,0.0001738189,0.0002286154,0.00034512,0.00008074287,0.000003922098,0.000180432],"genre_scores_gemma":[0.9965737,0.0002425565,0.002524171,0.0003643734,0.0002351169,0.000006016764,0.00002588211,0.00001132708,0.00001683883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2960845,"threshold_uncertainty_score":0.4474295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01929335731755154,"score_gpt":0.2429575639041722,"score_spread":0.2236642065866206,"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."}}