{"id":"W2162671544","doi":"10.1093/bioinformatics/btt261","title":"pyGenClean: efficient tool for genetic data clean up before association testing","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Python (programming language); Computer science; Genotyping; Data mining; Software; Source code; Pipeline (software); Documentation; Data quality; Operating system; Genotype; Biology; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009667646,0.002854635,0.002326467,0.004032683,0.001906012,0.003193898,0.005539012,0.001555848,0.0510808],"category_scores_gemma":[0.02989239,0.002139749,0.002723055,0.004547769,0.001535969,0.003423293,0.005491232,0.00484938,0.032796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009493048,"about_ca_system_score_gemma":0.005544033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00252403,"about_ca_topic_score_gemma":0.002443202,"domain_scores_codex":[0.9940925,0.001396441,0.0006657686,0.001392786,0.002085845,0.0003666263],"domain_scores_gemma":[0.9852725,0.007855254,0.001552371,0.002826802,0.001772368,0.0007207427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001662169,0.000362094,0.01805609,0.002055587,0.0007095592,0.001035735,0.0008324966,0.008472307,0.01941396,0.01154584,0.595224,0.3406302],"study_design_scores_gemma":[0.001153031,0.0003205071,0.01899364,0.0006199998,0.0003859218,0.002330225,0.0002579586,0.178909,0.09447143,0.09477449,0.6069675,0.0008162745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.0032349,0.0002599282,0.5948089,0.0006413449,0.0003012252,0.0002827643,0.02352784,0.374859,0.002084176],"genre_scores_gemma":[0.03461783,0.000471459,0.8058417,0.001515056,0.0002670753,0.002061018,0.05505762,0.09339986,0.006768352],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.0510808,"threshold_uncertainty_score":0.1708823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02935654915934202,"score_gpt":0.2703399993806277,"score_spread":0.2409834502212857,"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."}}