{"id":"W4200301447","doi":"10.1093/bioinformatics/btab852","title":"geoCancerPrognosticDatasetsRetriever: a bioinformatics tool to easily identify cancer prognostic datasets on Gene Expression Omnibus (GEO)","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Perl; Computer science; Data mining; DNA microarray; MIT License; Download; Bioinformatics; Computational biology; Information retrieval; Software; Gene; Gene expression; World Wide Web; Biology; Programming language","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":[0.0002430933,0.0003779367,0.000289778,0.0001451396,0.0002360496,0.0001972151,0.0004546155,0.000251251,0.0001477144],"category_scores_gemma":[0.0006481607,0.0003455043,0.0001204828,0.0005283462,0.00005978022,0.00005200209,0.0004311542,0.0001863481,0.0003143467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008219227,"about_ca_system_score_gemma":0.0005279357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001005851,"about_ca_topic_score_gemma":0.00001663501,"domain_scores_codex":[0.9975743,0.00005527144,0.0007873587,0.0004476724,0.0005981383,0.0005372341],"domain_scores_gemma":[0.9978085,0.00003563277,0.0003167697,0.001261481,0.0002603743,0.0003172799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000392209,0.0003615306,0.003259419,0.0004296592,0.0001321825,0.00002316938,0.0004404694,0.001239357,0.4271334,0.0001112762,0.511495,0.05498239],"study_design_scores_gemma":[0.0010292,0.0002910285,0.006995665,0.0003230074,0.00006744191,0.00003579731,0.0002766288,0.00198848,0.6438726,0.00002534561,0.3444181,0.0006766425],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8520669,0.003645041,0.1018604,0.002177463,0.00443854,0.00409281,0.02734015,0.0003344039,0.004044241],"genre_scores_gemma":[0.751862,0.004733094,0.1489999,0.01852714,0.001656202,0.00143333,0.07070804,0.0002272876,0.001853049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2167393,"threshold_uncertainty_score":0.9998997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01894596870205884,"score_gpt":0.2948328055811739,"score_spread":0.2758868368791151,"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."}}