{"id":"W2154865814","doi":"10.1093/bioinformatics/btr649","title":"Identifying quantitative trait loci via group-sparse multitask regression and feature selection: an imaging genetics study of the ADNI cohort","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":181,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Genentech; National Institutes of Health; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Center for Research Resources; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Synarc; Foundation for the National Institutes of Health; National Science Foundation","keywords":"Feature selection; Single-nucleotide polymorphism; Imaging genetics; Artificial intelligence; Computer science; Regression; Pairwise comparison; Computational biology; Interpretability; Neuroimaging; Machine learning; Pattern recognition (psychology); Biology; Genetics; Statistics; Mathematics; Genotype; Neuroscience","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005546778,0.0008444395,0.0007318088,0.000749775,0.0007830383,0.0007022427,0.0008728718,0.0006733814,0.0007624788],"category_scores_gemma":[0.005458946,0.0002774606,0.001023479,0.0007444598,0.0005385328,0.000259494,0.0005220233,0.0009759003,0.0001810752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005465843,"about_ca_system_score_gemma":0.0009141716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01286242,"about_ca_topic_score_gemma":0.01733903,"domain_scores_codex":[0.9994252,0.0002833283,0.00002291723,0.0001714415,0.00006163988,0.00003556203],"domain_scores_gemma":[0.9977242,0.001168722,0.0002818339,0.0004385797,0.0001724838,0.000214087],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003643057,0.001351288,0.8367178,0.0002002405,0.002724665,0.00264348,0.0007389009,0.04069993,0.01069337,0.002359904,0.009651552,0.08857574],"study_design_scores_gemma":[0.0009733441,0.001034251,0.6213461,0.0000621013,0.002107916,0.00196715,0.0005369714,0.3501206,0.004696714,0.01271736,0.004249838,0.0001877367],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811243,0.0005706086,0.01601112,0.0008770739,0.00003389497,0.00006824606,0.0008241488,0.0001348451,0.0003558336],"genre_scores_gemma":[0.9794633,0.0002500107,0.01771067,0.0001567659,0.00009817786,0.00008548082,0.00150768,0.00003226232,0.0006956527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01286242,"threshold_uncertainty_score":0.02933455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03403405047364537,"score_gpt":0.2934433759623913,"score_spread":0.259409325488746,"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."}}