{"id":"W7117874921","doi":"10.1093/bib/bbaf698","title":"MOGEDN: small-sample cancer subtype classification with encoder–decoder networks for missing-omics recovery and biomarker discovery","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Cybermedia Center, Osaka University; Japan Society for the Promotion of Science; National Institute of Advanced Industrial Science and Technology","keywords":"Biomarker discovery; Biomarker; Cancer; Omics; Imputation (statistics); Cancer biomarkers; Missing data; Feature (linguistics)","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":[0.0003493376,0.0002594612,0.0002645321,0.0001160687,0.0001614891,0.0002152701,0.0001981716,0.0003136845,0.000002226923],"category_scores_gemma":[0.0001031866,0.0002308555,0.00007047835,0.0002133506,0.0001401125,0.00004332268,0.0001239206,0.000146774,4.884931e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005598392,"about_ca_system_score_gemma":0.0002291751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001330811,"about_ca_topic_score_gemma":0.0004404369,"domain_scores_codex":[0.9986593,0.00001652374,0.0005833025,0.0002565829,0.00008397343,0.0004003676],"domain_scores_gemma":[0.9990925,0.0001115758,0.0002730996,0.0003518068,0.0001028288,0.00006815678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004084899,0.0003817463,0.03777319,0.002464353,0.001134901,0.000002848577,0.001360882,0.03179484,0.007234556,0.01091589,0.05742821,0.8454237],"study_design_scores_gemma":[0.003107346,0.0003009377,0.01110393,0.0004367982,0.0001292999,0.00001838438,0.0004593714,0.9127734,0.001797491,0.00285927,0.06611908,0.0008946715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07004832,0.001501616,0.9249392,0.001240523,0.0002854897,0.0007487452,0.0001288831,0.000022302,0.001084936],"genre_scores_gemma":[0.6599932,0.01020788,0.3041883,0.01888848,0.0004691197,0.0006028447,0.002721756,0.0001646422,0.002763698],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8809786,"threshold_uncertainty_score":0.9414014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0161614529337112,"score_gpt":0.2501743481142379,"score_spread":0.2340128951805268,"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."}}