{"id":"W2153767201","doi":"10.1093/nar/gkl404","title":"Sequence biases in large scale gene expression profiling data","year":2006,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Biology; Gene expression profiling; Gene; Serial analysis of gene expression; RefSeq; Genetics; Gene expression; Computational biology; DNA microarray; Sampling bias; Genome; Statistics; Sample size determination; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008340368,0.0007475918,0.0008776526,0.001967313,0.0006776965,0.001188157,0.0005606688,0.0006414491,0.0009986388],"category_scores_gemma":[0.03096495,0.0003629286,0.0005933255,0.003493365,0.001017977,0.0007125016,0.0009501813,0.0009920993,0.0007354323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007108523,"about_ca_system_score_gemma":0.0006663272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004416255,"about_ca_topic_score_gemma":0.000887525,"domain_scores_codex":[0.9845319,0.005521791,0.00138567,0.002774784,0.00541563,0.0003703259],"domain_scores_gemma":[0.9617816,0.02514653,0.004877088,0.004803272,0.003101471,0.0002899834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001467685,0.0001702573,0.08690143,0.001183858,0.0007885543,0.0004002978,0.0008254175,0.01225383,0.7829967,0.00442039,0.0009346894,0.1076569],"study_design_scores_gemma":[0.0000740929,0.0005879008,0.2010199,0.000135881,0.0004919457,0.001830131,0.0002798155,0.03934894,0.722684,0.01961156,0.01375016,0.0001856869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6047251,0.00268952,0.3810447,0.0004594378,0.0002136993,0.0004715308,0.004816572,0.002105228,0.003474154],"genre_scores_gemma":[0.8118319,0.0008365801,0.177555,0.0007332834,0.0001387009,0.000659023,0.006621372,0.0005924092,0.001031796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008340368,"threshold_uncertainty_score":0.04410863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1263237161734327,"score_gpt":0.4009265080186994,"score_spread":0.2746027918452668,"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."}}