{"id":"W2766638840","doi":"10.1016/j.dib.2017.10.060","title":"Application of bi-clustering of gene expression data and gene set enrichment analysis methods to identify potentially disease causing nanomaterials","year":2017,"lang":"en","type":"article","venue":"Data in Brief","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada","funders":"","keywords":"Cluster analysis; Gene expression; Computational biology; Gene; Data set; Set (abstract data type); Gene expression profiling; Expression (computer science); Data mining; Computer science; Bioinformatics; Data science; Biology; Genetics; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0006669562,0.0000937458,0.0001926572,0.00009761294,0.00007411082,0.00005431045,0.0008111451,0.00005825685,0.000007316757],"category_scores_gemma":[0.0001528269,0.00009183581,0.0000220793,0.00009130431,0.0000455285,0.00002775402,0.001844414,0.0000197875,2.818764e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007107768,"about_ca_system_score_gemma":0.0000382642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001820562,"about_ca_topic_score_gemma":0.00003811865,"domain_scores_codex":[0.9987602,0.0001043978,0.0003344023,0.0005702018,0.0001288067,0.0001019473],"domain_scores_gemma":[0.996231,0.000007395883,0.0003411153,0.003291194,0.00005026502,0.00007909312],"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":[0.0000894085,0.00003272711,0.005286303,0.00004624345,0.00004830665,7.456026e-7,0.00002650305,0.0001523563,0.9863986,0.000001521287,0.0001920264,0.007725212],"study_design_scores_gemma":[0.0002613859,0.00001322306,0.1181628,0.00002817232,0.0001288515,9.162386e-7,0.0000250935,0.003932922,0.8734197,0.000007087809,0.003917763,0.0001020476],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4684772,0.0003713913,0.5291568,0.00005327444,0.0000786205,0.0001848673,0.001667218,0.000002572546,0.000008023852],"genre_scores_gemma":[0.9273772,0.0002480655,0.06492649,0.00002925718,0.00005803413,0.00001811698,0.0073207,0.000009040554,0.00001313258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4642303,"threshold_uncertainty_score":0.3744955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06234865943078773,"score_gpt":0.410856255770897,"score_spread":0.3485075963401092,"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."}}