{"id":"W3130317325","doi":"10.1093/database/baab006","title":"Curation of over 10 000 transcriptomic studies to enable data reuse","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; University of British Columbia","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada","keywords":"Metadata; Computer science; Reuse; Software; Data curation; Gemma; World Wide Web; Database; Information retrieval; Data science; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001140649,0.0000663417,0.00008453682,0.00002386572,0.00003092311,0.000008962059,0.0003796448,0.00003307928,0.0001824689],"category_scores_gemma":[0.000392777,0.00006288498,0.00001956812,0.0001031803,0.00001990054,0.00001382181,0.0004429398,0.00002740508,0.00001272355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006845168,"about_ca_system_score_gemma":0.00007598367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001496011,"about_ca_topic_score_gemma":0.00008402701,"domain_scores_codex":[0.9993147,0.00004085686,0.0001445322,0.0003195024,0.00009333382,0.00008705322],"domain_scores_gemma":[0.9977704,0.000005570218,0.00004173083,0.00203069,0.0001064096,0.00004523718],"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":[0.00003979097,0.00003198958,0.00008114253,0.00002146625,0.0000195308,0.000001020177,0.00004094569,0.000005071131,0.7144995,0.00004391541,0.2847947,0.0004209184],"study_design_scores_gemma":[0.000197736,0.00002184531,0.0002366851,0.00001769049,0.00001294342,0.000001166641,0.0001666822,0.00002525478,0.6092438,0.00002040737,0.3899991,0.00005664242],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9750338,0.008697136,0.007736288,0.002196505,0.0005575391,0.0002762487,0.004509044,0.00001923291,0.0009741718],"genre_scores_gemma":[0.9653775,0.002485586,0.007145513,0.0009998312,0.0002785509,0.00003651248,0.01885782,0.00002298452,0.004795699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1052557,"threshold_uncertainty_score":0.2564375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09921660307901177,"score_gpt":0.3764284461266624,"score_spread":0.2772118430476506,"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."}}