{"id":"W3215029602","doi":"10.1093/genetics/iyab216","title":"Disentangling genetic feature selection and aggregation in transcriptome-wide association studies","year":2021,"lang":"en","type":"article","venue":"Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Feature (linguistics); Computational biology; Kernel (algebra); Genetic association; Association (psychology); Biology; Computer science; Artificial intelligence; Adaptability; Genotype; Machine learning; Data mining; Single-nucleotide polymorphism; Genetics; Gene; Mathematics","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":[0.04352478,0.0008712059,0.001397195,0.001429303,0.00114426,0.002514125,0.001456435,0.001100595,0.0008586331],"category_scores_gemma":[0.09565019,0.0008148091,0.001357452,0.002401894,0.002548047,0.003320624,0.004108844,0.002750187,0.0002231073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009129068,"about_ca_system_score_gemma":0.002060274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00148617,"about_ca_topic_score_gemma":0.002376398,"domain_scores_codex":[0.9676487,0.02633485,0.001287528,0.002187127,0.002137372,0.0004043613],"domain_scores_gemma":[0.924477,0.05579565,0.003938984,0.01341658,0.001753643,0.0006182299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001380456,0.0004519917,0.1015177,0.0007639583,0.002481467,0.001023104,0.00202208,0.261831,0.07112601,0.1646915,0.00165795,0.3910529],"study_design_scores_gemma":[0.00009282575,0.0003575686,0.02673654,0.00006575241,0.0003041167,0.0002865644,0.0001783614,0.7328264,0.02177281,0.2143915,0.002869731,0.0001179133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05320438,0.0002151454,0.9454135,0.0003126487,0.0000299375,0.000121362,0.00007147715,0.0002941929,0.0003374312],"genre_scores_gemma":[0.5310571,0.0002677859,0.4670551,0.0002305199,0.00006064381,0.000487848,0.0002309703,0.0001121523,0.0004978975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04352478,"threshold_uncertainty_score":0.2301837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01322570000039891,"score_gpt":0.2731449243175376,"score_spread":0.2599192243171387,"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."}}