{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005536553,0.0001536634,0.0001822122,0.00003696179,0.0001379674,0.00005477824,0.0003787967,0.0002275309,0.00003730914],"category_scores_gemma":[0.001281485,0.0001420726,0.00006433827,0.0001017894,0.00002267256,0.000009707781,0.0002607854,0.00006802764,0.000164643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005508737,"about_ca_system_score_gemma":0.00008212116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000027923,"about_ca_topic_score_gemma":0.00001606082,"domain_scores_codex":[0.9986537,0.0000338769,0.0005281707,0.0002326399,0.0001457763,0.000405903],"domain_scores_gemma":[0.9985523,0.0000865414,0.0003688118,0.0006488267,0.0002714647,0.00007207255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002481658,0.0001464516,0.458538,0.0002443893,0.0003329175,2.494423e-7,0.0005491565,0.004212614,0.009440255,0.0001164769,0.177334,0.3490607],"study_design_scores_gemma":[0.000965426,0.0004740464,0.2926098,0.00002041269,0.00006770169,0.000008376878,0.0005602301,0.6775101,0.0005231877,0.0003165039,0.02650831,0.0004358996],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700937,0.00005170876,0.02749968,0.0002470144,0.000418121,0.0008024877,0.0001441501,0.0000296308,0.0007135636],"genre_scores_gemma":[0.7048787,0.00002432254,0.2906813,0.0007338744,0.0004162799,0.00009463113,0.001408613,0.00003396353,0.001728332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6732975,"threshold_uncertainty_score":0.5793552,"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."}}