{"id":"W2959991108","doi":"10.3389/fgene.2019.00726","title":"Integration of Machine Learning Methods to Dissect Genetically Imputed Transcriptomic Profiles in Alzheimer’s Disease","year":2019,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Engineering and Physical Sciences Research Council; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Artificial intelligence; Autoencoder; Machine learning; Expression quantitative trait loci; Classifier (UML); Computational biology; Computer science; Deep learning; Gene regulatory network; Biology; Unsupervised learning; Feature selection; Gene; Gene expression; Genetics; Single-nucleotide polymorphism; Genotype","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003536482,0.0001780401,0.000254592,0.000152379,0.00001696363,0.00001510587,0.0002399932,0.0001499212,0.00001262875],"category_scores_gemma":[0.00003680427,0.0001755599,0.00007915156,0.0002001646,0.0000416514,0.000003636141,0.0000807398,0.0001728427,0.000003402693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002121669,"about_ca_system_score_gemma":0.00007473868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001240469,"about_ca_topic_score_gemma":0.00004320297,"domain_scores_codex":[0.9987561,0.0001338643,0.0004517116,0.0002831323,0.0001025596,0.000272628],"domain_scores_gemma":[0.9994407,0.00001084963,0.00008673506,0.000302373,0.00004307137,0.0001162983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006907372,0.0001404017,0.1793967,0.00008059911,0.0001126622,0.000002687828,0.0007937378,0.04450249,0.5608329,0.00009962369,0.001023625,0.2123238],"study_design_scores_gemma":[0.002591543,0.001180341,0.1439349,0.0001808591,0.0001258815,0.000003990618,0.0005954202,0.5959249,0.237764,0.001374806,0.01529893,0.001024438],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7127779,0.00663942,0.2792314,0.00007216739,0.0004521447,0.0006032664,0.00002281412,0.00000621169,0.0001946989],"genre_scores_gemma":[0.7510869,0.0004369548,0.2480727,0.00009564159,0.00004266315,0.00002168948,0.0001444321,0.00002378696,0.00007520959],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5514224,"threshold_uncertainty_score":0.7159125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009620796184804164,"score_gpt":0.2727425707145507,"score_spread":0.2631217745297465,"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."}}