{"id":"W2015530630","doi":"10.1186/s13059-014-0462-7","title":"Toward better benchmarking: challenge-based methods assessment in cancer genomics","year":2014,"lang":"en","type":"article","venue":"Genome biology","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Genome Canada; National Cancer Institute; National Institutes of Health; Ontario Institute for Cancer Research; Movember Foundation","keywords":"Benchmarking; Genomics; Data science; Biology; Human genetics; Crowd sourcing; Genome Biology; Computational biology; Computer science; Genome; Genetics; Business; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.162964,0.002742909,0.003020424,0.006872687,0.00282533,0.01045536,0.004477566,0.005374424,0.002757995],"category_scores_gemma":[0.309046,0.0007114679,0.001875332,0.004843587,0.003510656,0.007911706,0.01184318,0.004729505,0.001103794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003497336,"about_ca_system_score_gemma":0.005912977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004228047,"about_ca_topic_score_gemma":0.004542513,"domain_scores_codex":[0.8455886,0.118527,0.00456344,0.007583537,0.02167761,0.002059818],"domain_scores_gemma":[0.7527823,0.1653002,0.008807414,0.0303583,0.03739422,0.005357655],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001267393,0.001102004,0.07438613,0.002194577,0.001890293,0.0003999469,0.003735091,0.3941828,0.006414854,0.101526,0.0369308,0.3759702],"study_design_scores_gemma":[0.0001575316,0.0005633153,0.01003279,0.0006450302,0.0001519087,0.0002292404,0.001250204,0.7577304,0.007608026,0.2002132,0.02123681,0.0001815536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0718556,0.005749167,0.8899565,0.01137525,0.001095653,0.000997416,0.001153994,0.002437239,0.0153792],"genre_scores_gemma":[0.4533291,0.001037922,0.5358209,0.002546415,0.0004319988,0.001130059,0.002707643,0.001318568,0.001677357],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.837036,"threshold_uncertainty_score":0.8618466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03123681804151992,"score_gpt":0.346673427813033,"score_spread":0.3154366097715131,"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."}}