{"id":"W4394759342","doi":"10.1093/bioinformatics/btae161","title":"phylaGAN: data augmentation through conditional GANs and autoencoders for improving disease prediction accuracy using microbiome data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto; University Health Network","funders":"","keywords":"Autoencoder; Machine learning; Artificial intelligence; Computer science; Microbiome; Deep learning; Generative grammar; Subspace topology; Pattern recognition (psychology); Bioinformatics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001935545,0.0001235462,0.00008127728,0.00004029735,0.000166955,0.0001428332,0.0002649852,0.00007734649,0.000006974853],"category_scores_gemma":[0.00007589889,0.0001186843,0.00002303145,0.00005992589,0.00006760623,0.0001369838,0.0003401503,0.00005457605,0.00000418914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002720124,"about_ca_system_score_gemma":0.0003983737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001611087,"about_ca_topic_score_gemma":0.00001078538,"domain_scores_codex":[0.9991527,0.00001120538,0.0002836949,0.0002904842,0.0000736863,0.0001882654],"domain_scores_gemma":[0.999209,0.00002336944,0.00008472535,0.0005719852,0.00003899876,0.00007194417],"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":[0.0001863274,0.0001087121,0.0003799045,0.005597937,0.0002371055,0.000003828824,0.001067072,0.0003473775,0.8934414,0.0007228697,0.08539326,0.01251423],"study_design_scores_gemma":[0.0008585534,0.0001216679,0.0008332155,0.000114676,0.0002029354,0.00005448572,0.0005477756,0.9184542,0.003630166,0.0002270257,0.0746564,0.0002989013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1082338,0.00232988,0.8493488,0.0006898196,0.0008176907,0.0010646,0.03737615,0.00008185922,0.00005743294],"genre_scores_gemma":[0.5181706,0.0008371847,0.2578372,0.001364061,0.0009857642,0.00002388064,0.2205491,0.00006682348,0.0001653845],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9181069,"threshold_uncertainty_score":0.4839807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0742748241898758,"score_gpt":0.354702210346682,"score_spread":0.2804273861568062,"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."}}