{"id":"W4392972987","doi":"10.1101/2024.03.18.585541","title":"Machine learning methods applied to classify complex diseases using genomic data","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Alzheimer's Association","keywords":"Artificial intelligence; Computer science; Machine learning; Computational biology; Data science; Biology","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":[0.005085588,0.0008067479,0.0006059342,0.002588952,0.0002346049,0.001038605,0.0005498527,0.0006852464,0.0008810271],"category_scores_gemma":[0.01090803,0.0001889075,0.0007659114,0.001722471,0.0004173693,0.0007032808,0.0007086844,0.001048348,0.0004177624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005430293,"about_ca_system_score_gemma":0.0005854571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003560341,"about_ca_topic_score_gemma":0.002406305,"domain_scores_codex":[0.9983418,0.0008602095,0.0001378503,0.0003514804,0.0002206703,0.00008802842],"domain_scores_gemma":[0.993064,0.005255136,0.0006574611,0.0004296273,0.0004860313,0.0001076841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003429907,0.0004350909,0.2352297,0.0003354568,0.001081029,0.0003211835,0.000206662,0.4968832,0.006549656,0.002889666,0.002551133,0.2531743],"study_design_scores_gemma":[0.00001361293,0.00008270792,0.01998935,0.00004579507,0.00003677106,0.00005526084,0.00004657719,0.9722095,0.001414458,0.005536635,0.0005544851,0.00001490589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5878772,0.003310387,0.4003112,0.001661641,0.0001331757,0.0001652803,0.003276511,0.00133189,0.001932719],"genre_scores_gemma":[0.9473143,0.0002575172,0.05058719,0.0001254262,0.00004816258,0.00005716983,0.001268286,0.00002433099,0.0003176921],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005085588,"threshold_uncertainty_score":0.02689546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06061037757877705,"score_gpt":0.3344229349369701,"score_spread":0.273812557358193,"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."}}