{"id":"W1968839521","doi":"10.1093/bib/bbv019","title":"Optimization of miRNA-seq data preprocessing","year":2015,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"Canadian Cancer Society Research Institute","keywords":"Computer science; Preprocessor; Count data; Data mining; Normalization (sociology); Quantile; Computational biology; Statistics; Poisson distribution; Artificial intelligence; Biology; 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":[0.0003058508,0.00008122039,0.0000965032,0.00005279965,0.00001643209,0.00002200054,0.0002781076,0.00009103063,0.000004326858],"category_scores_gemma":[0.0003804726,0.0000844509,0.00001702339,0.0001276602,0.00005302622,0.00002984512,0.0002487954,0.0000353101,0.000002730473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001700243,"about_ca_system_score_gemma":0.00015713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002474324,"about_ca_topic_score_gemma":0.000006437858,"domain_scores_codex":[0.9992452,0.00001378506,0.0003539929,0.0001301467,0.0001404643,0.0001164476],"domain_scores_gemma":[0.999101,0.00000525396,0.000207604,0.000519788,0.0001141407,0.00005215821],"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":[0.0008556922,0.0009029775,0.02823619,0.002902963,0.000254622,0.000007654692,0.006049751,0.6893771,0.08926373,0.0006783214,0.09981513,0.08165584],"study_design_scores_gemma":[0.001935507,0.0001187297,0.001994052,0.000213875,0.00003588829,0.000034603,0.0004202561,0.9141006,0.06246535,0.0002306088,0.01802333,0.0004272394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.47758,0.002378936,0.5099686,0.0004588411,0.0002364707,0.0006460704,0.0001517985,0.00005318759,0.008526077],"genre_scores_gemma":[0.7170693,0.00008856948,0.2803596,0.0004367861,0.00008844608,0.000006820234,0.001824025,0.00002718456,0.00009928233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2394893,"threshold_uncertainty_score":0.3443808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04211552848997092,"score_gpt":0.2862784146327305,"score_spread":0.2441628861427595,"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."}}