{"id":"W2318488401","doi":"10.1093/bioinformatics/btw155","title":"MOLGENIS/connect: a system for semi-automatic integration of heterogeneous phenotype data with applications in biobanks","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Terveyden ja hyvinvoinnin laitos; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; European Commission","keywords":"Computer science; Biobank; Documentation; Source code; Data integration; Data mining; Terminology; Open source; Information retrieval; Ontology; Categorical variable; Task (project management); Data source; Matching (statistics); Software; Programming language; Machine learning; Bioinformatics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001651021,0.0001086372,0.0001596235,0.00005147535,0.00003041102,0.000009565361,0.0003113419,0.0001285665,0.000001934992],"category_scores_gemma":[0.0001149349,0.0000623649,0.00002828828,0.00009546205,0.0001002204,0.000007432846,0.00008754717,0.0000255193,0.000003676412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001788752,"about_ca_system_score_gemma":0.00006888766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007353696,"about_ca_topic_score_gemma":0.00005393237,"domain_scores_codex":[0.9992594,0.00001322614,0.000339259,0.0001459716,0.00009069026,0.0001514278],"domain_scores_gemma":[0.9991127,0.00005481177,0.0001640615,0.0005637531,0.00006538703,0.00003925724],"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":[0.0002389494,0.0002406057,0.001455261,0.001598473,0.000210607,0.000001464185,0.0006561019,0.00002916106,0.1116896,0.001484746,0.00144518,0.8809499],"study_design_scores_gemma":[0.0116347,0.006677649,0.002463231,0.002900973,0.0004543382,0.0001790973,0.008241173,0.171945,0.7024714,0.0007143833,0.08998843,0.002329633],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2698311,0.0003716609,0.7278995,0.0001222805,0.00007220838,0.0008175446,0.0004921803,0.00005636889,0.0003371864],"genre_scores_gemma":[0.9488944,0.00002580201,0.05057764,0.00002261819,0.0000355315,0.00008257588,0.000319803,0.00001012416,0.00003145228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8786202,"threshold_uncertainty_score":0.2543167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02425168455166588,"score_gpt":0.2718240070330186,"score_spread":0.2475723224813527,"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."}}