{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002382251,0.0001155142,0.0001709644,0.00038058,0.0003499173,0.002347145,0.00227501,0.00004462004,0.000002510974],"category_scores_gemma":[0.0006458579,0.0001017085,0.00004199922,0.001276625,0.0000739988,0.0139739,0.002028725,0.00006601492,0.00002343633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005906128,"about_ca_system_score_gemma":0.0001287525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002143806,"about_ca_topic_score_gemma":0.00002307861,"domain_scores_codex":[0.9985458,0.0001081844,0.0005322392,0.0003598483,0.0002047891,0.0002491749],"domain_scores_gemma":[0.9972798,0.000434003,0.0004122928,0.001529754,0.000303346,0.00004079376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004586197,0.0001437983,0.00625411,0.0004353724,0.00483417,0.000005002613,0.008820367,0.01096,0.1446765,0.1014971,0.07809683,0.6438182],"study_design_scores_gemma":[0.0007306352,0.00004182776,0.00452995,0.000006295818,0.0003483382,0.000002073817,0.0002851944,0.494466,0.003857112,0.0002535591,0.4952481,0.0002308794],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09980295,0.00006633699,0.8948047,0.001521195,0.0001531416,0.0008101962,0.002766994,0.00005052518,0.00002398447],"genre_scores_gemma":[0.455616,0.02712117,0.3343878,0.002695128,0.0006476166,0.000407084,0.1760856,0.0001492162,0.002890337],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6435873,"threshold_uncertainty_score":0.9998171,"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."}}