{"id":"W4317815831","doi":"10.1099/mgen.0.000908","title":"The DataHarmonizer: a tool for faster data harmonization, validation, aggregation and analysis of pathogen genomics contextual information","year":2023,"lang":"en","type":"article","venue":"Microbial Genomics","topic":"Research Data Management Practices","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. John’s Health Sciences Centre; McMaster University; University of Alberta; Saskatchewan Disease Control Laboratory; Public Health Agency of Canada; Simon Fraser University; Institut National de Santé Publique du Québec; Nova Scotia Health Authority; BC Centre for Disease Control; Hospital for Sick Children; Public Health Ontario; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael G. DeGroote Institute for Infectious Disease Research, McMaster University; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Metadata; Data sharing; Computer science; Data science; Harmonization; Interoperability; Big data; Data integration; Usability; World Wide Web; Database; Data mining; Medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02099016,0.003785553,0.002786874,0.007479324,0.001728553,0.007727626,0.004681956,0.002045783,0.02516919],"category_scores_gemma":[0.04017836,0.002946919,0.003175255,0.006022203,0.002015234,0.01033047,0.01319393,0.006078586,0.01377491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001723975,"about_ca_system_score_gemma":0.005147915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004731784,"about_ca_topic_score_gemma":0.004204763,"domain_scores_codex":[0.9877033,0.002495134,0.001880503,0.002636591,0.004717736,0.0005666803],"domain_scores_gemma":[0.9740636,0.01367206,0.001559426,0.007250343,0.002270991,0.0011834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002417706,0.0005623286,0.01089055,0.003521141,0.001040008,0.001791245,0.004738895,0.01086983,0.0195198,0.03612981,0.4243872,0.4841316],"study_design_scores_gemma":[0.00108463,0.0003677248,0.01143773,0.002077603,0.000347296,0.001264225,0.001315657,0.10907,0.05759684,0.08978228,0.7247316,0.0009244566],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.003568097,0.0004456913,0.4905234,0.0009879002,0.0003428288,0.0009031328,0.03125142,0.4663395,0.005638081],"genre_scores_gemma":[0.04684537,0.0008689334,0.7915632,0.00185622,0.0001536894,0.00229903,0.07915699,0.07032105,0.006935562],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02516919,"threshold_uncertainty_score":0.1110079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07868323319902724,"score_gpt":0.3125234092058528,"score_spread":0.2338401760068255,"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."}}