{"id":"W3133283981","doi":"10.1038/s41467-021-21254-9","title":"Uniform genomic data analysis in the NCI Genomic Data Commons","year":2021,"lang":"en","type":"article","venue":"Nature Communications","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":148,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health; University of Texas MD Anderson Cancer Center; Canada's Michael Smith Genome Sciences Centre; U.S. Department of Health and Human Services","keywords":"Workflow; Epigenomics; Data sharing; Raw data; Computational biology; Genomics; Precision medicine; Computer science; DNA methylation; Genome; Biology; Bioinformatics; Database; Genetics; Gene; Medicine; Gene expression","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005187454,0.0001202243,0.0001591754,0.00006866542,0.000212549,0.00008731513,0.00654804,0.0002133028,0.00001620784],"category_scores_gemma":[0.0003629065,0.0001083788,0.00006402735,0.0005730286,0.0001074165,0.000008315046,0.006122807,0.0005462127,0.00001055442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003469273,"about_ca_system_score_gemma":0.0003281978,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001830903,"about_ca_topic_score_gemma":0.06935988,"domain_scores_codex":[0.9988832,0.0001692536,0.0002475315,0.0004217358,0.00009823971,0.0001800112],"domain_scores_gemma":[0.9854581,0.0001984738,0.00008636295,0.01412714,0.00008675352,0.00004310884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001310932,0.00267564,0.2877031,0.0000540643,0.004944896,0.00005980534,0.001379851,0.003352745,0.1809032,0.04639237,0.4546933,0.01770992],"study_design_scores_gemma":[0.0002908514,0.00001441986,0.08192514,0.000004040651,0.0003978676,0.00001582359,0.0003407073,0.003909875,0.0002932881,0.0001551279,0.9124584,0.0001944948],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6679829,0.2346549,0.00303147,0.04874959,0.000605215,0.001045529,0.01946798,0.00004593007,0.02441648],"genre_scores_gemma":[0.9373509,0.01040324,0.005421254,0.002107736,0.0001091798,0.00001306995,0.04450785,0.00001512873,0.00007167976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4577651,"threshold_uncertainty_score":0.998827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04565861463920134,"score_gpt":0.3347831478506129,"score_spread":0.2891245332114116,"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."}}