{"id":"W4318347652","doi":"10.48550/arxiv.2301.10772","title":"Gene-SGAN: a method for discovering disease subtypes with imaging and genetic signatures via multi-view weakly-supervised deep clustering","year":2023,"lang":"en","type":"preprint","venue":"PubMed","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Endophenotype; Interpretability; Subtyping; Imaging genetics; Neuroimaging; Disease; Computational biology; Biology; Phenotype; Genetic heterogeneity; Machine learning; Neuroscience; Gene; Genetics; Computer science; Medicine; Cognition; Pathology","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":[0.001629781,0.001390652,0.001053059,0.001459318,0.0008833808,0.001093797,0.002451842,0.001686121,0.001477071],"category_scores_gemma":[0.003516253,0.0006005802,0.001810384,0.001222509,0.001005401,0.000812307,0.001743152,0.001826226,0.001044986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001299187,"about_ca_system_score_gemma":0.001835952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01029579,"about_ca_topic_score_gemma":0.02071885,"domain_scores_codex":[0.9992467,0.0002976183,0.00004132039,0.0002177601,0.0001264948,0.00007011829],"domain_scores_gemma":[0.998931,0.0003958495,0.00009836051,0.0002587555,0.0002342899,0.0000817429],"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":[0.0008579564,0.0002986048,0.01200895,0.0003645727,0.0008075666,0.0003637378,0.0004757004,0.4675298,0.01705561,0.0197113,0.03242604,0.4481002],"study_design_scores_gemma":[0.00002473992,0.00002702574,0.0005696744,0.00001085167,0.00002007616,0.00004759499,0.00002227391,0.9831404,0.001310164,0.01348213,0.001331209,0.00001392292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02748884,0.0002904333,0.9664033,0.0003983582,0.00005231443,0.0001249062,0.001057247,0.003332403,0.0008521969],"genre_scores_gemma":[0.3341157,0.0002624711,0.6503111,0.0007865076,0.00008517058,0.0004846022,0.008387285,0.0009682853,0.004598894],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01029579,"threshold_uncertainty_score":0.02047169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01542823824575888,"score_gpt":0.2428958507901612,"score_spread":0.2274676125444024,"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."}}