{"id":"W3042189475","doi":"10.1101/2020.07.13.201442","title":"Curation of over 10,000 transcriptomic studies to enable data reuse","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metadata; Computer science; Reuse; Gemma; Software; Database; Data curation; World Wide Web; Information retrieval; Data mining; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01761437,0.001567711,0.002273001,0.01428215,0.003207445,0.006297462,0.0026301,0.001553268,0.01015501],"category_scores_gemma":[0.03807241,0.001059273,0.002843522,0.01471854,0.001066218,0.00341226,0.009304113,0.003044047,0.007702507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002083738,"about_ca_system_score_gemma":0.009413915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006117326,"about_ca_topic_score_gemma":0.01786286,"domain_scores_codex":[0.9908378,0.001690625,0.001645601,0.002944235,0.002352061,0.0005297331],"domain_scores_gemma":[0.9688132,0.007174316,0.002391346,0.01297102,0.006929248,0.001720803],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001297414,0.0001676836,0.03630516,0.01015504,0.002453832,0.001581566,0.003483085,0.003645483,0.1361249,0.01437243,0.5252936,0.2651197],"study_design_scores_gemma":[0.0001949891,0.0001016173,0.03662109,0.001634914,0.001220198,0.0009696457,0.0005979608,0.004330205,0.02773134,0.01846319,0.9079415,0.000193363],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05809844,0.01508161,0.2133399,0.005036294,0.002103966,0.001836446,0.6313162,0.04757964,0.02560738],"genre_scores_gemma":[0.06268711,0.004078717,0.2409431,0.002140776,0.0004368115,0.002935996,0.6703867,0.01127658,0.00511422],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9823856,"threshold_uncertainty_score":0.09315485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05566424018684152,"score_gpt":0.2753523796656945,"score_spread":0.219688139478853,"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."}}