{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.01822303,0.001831107,0.002786239,0.0166842,0.003590039,0.006542317,0.002553085,0.001668768,0.01355336],"category_scores_gemma":[0.03897826,0.001178475,0.003314947,0.01782632,0.0009727505,0.003467138,0.009165266,0.003077101,0.01008245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002322788,"about_ca_system_score_gemma":0.01130028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00635498,"about_ca_topic_score_gemma":0.01965316,"domain_scores_codex":[0.9890205,0.001870041,0.002248448,0.003529809,0.002715807,0.0006152815],"domain_scores_gemma":[0.9659796,0.007825448,0.002563193,0.01354056,0.008262176,0.001829082],"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":[0.001451438,0.0002127701,0.03218541,0.01224538,0.002320495,0.001772744,0.003295031,0.002845425,0.1306034,0.01336131,0.5089692,0.2907374],"study_design_scores_gemma":[0.0001770744,0.0001151984,0.03409573,0.001665639,0.00110046,0.001082758,0.0005985456,0.002727247,0.02255679,0.01485073,0.9208412,0.0001886055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.04222474,0.01583056,0.1795537,0.004252137,0.002202909,0.00202164,0.6925799,0.0334824,0.02785204],"genre_scores_gemma":[0.03804413,0.004359594,0.205673,0.001833212,0.0003823093,0.00275044,0.7339167,0.007721167,0.005319431],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9974469,"threshold_uncertainty_score":0.09637374,"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."}}