{"id":"W3217633165","doi":"10.1038/s41467-021-27219-2","title":"Computational tools for genomic data de-identification: facilitating data protection law compliance","year":2021,"lang":"en","type":"article","venue":"Nature Communications","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; Government of Canada; Canada Foundation for Innovation; Ontario Institute for Cancer Research","keywords":"Identifiability; Identification (biology); Data anonymization; Data Protection Act 1998; Computer science; Big data; Data science; Privacy law; Limit (mathematics); Information privacy; Data mining; Computational biology; Internet privacy; Biology; Computer security; Privacy policy; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.07395148,0.0009052154,0.001270335,0.003574394,0.003447542,0.01448114,0.006478729,0.01082661,0.009289984],"category_scores_gemma":[0.1718145,0.0009037395,0.002309761,0.002321353,0.01743945,0.0204086,0.01147038,0.01540089,0.003484455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003182041,"about_ca_system_score_gemma":0.007330269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0017495,"about_ca_topic_score_gemma":0.0017047,"domain_scores_codex":[0.9455717,0.03336095,0.00275836,0.004397803,0.0123388,0.001572359],"domain_scores_gemma":[0.8303427,0.1301371,0.003661278,0.02417998,0.01052397,0.001155086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001384227,0.00002335576,0.0003031364,0.0001643594,0.00002358233,0.0001395859,0.00099043,0.00166372,0.000611548,0.9468898,0.01938598,0.02979061],"study_design_scores_gemma":[0.00002485613,0.00002109152,0.0002104423,0.0005681594,0.0000259595,0.0002324797,0.0005467559,0.01002841,0.002619511,0.7961954,0.1894681,0.000058953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003521336,0.002561526,0.7015276,0.2479135,0.003062634,0.0002123587,0.0003000697,0.0009432376,0.03995777],"genre_scores_gemma":[0.1963476,0.007734778,0.7300559,0.04768353,0.004133868,0.0009838436,0.001000372,0.0007645379,0.01129554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07395148,"threshold_uncertainty_score":0.3910975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2775683543315902,"score_gpt":0.4018329874746633,"score_spread":0.1242646331430731,"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."}}