{"id":"W4364381299","doi":"10.1016/j.cmpb.2023.107543","title":"Learning vector quantized representation for cancer subtypes identification","year":2023,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Bioscience Database Center; JST-Mirai Program; Japan Science and Technology Agency; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Cluster analysis; Computer science; Overfitting; Subtyping; Artificial intelligence; Machine learning; Data mining; Autoencoder; Spurious relationship; Identification (biology); Biological data; Leverage (statistics); Bioinformatics; Deep learning; Artificial neural network; Biology","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":[0.0007780092,0.00007961834,0.0001189942,0.0001198515,0.00005982604,0.00002702372,0.00007245308,0.00007555527,0.000002747063],"category_scores_gemma":[0.00006337228,0.00006834228,0.00003097518,0.000386909,0.00005333219,0.000003965489,0.0000436347,0.00004864149,8.641499e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007323587,"about_ca_system_score_gemma":0.00001800387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002115901,"about_ca_topic_score_gemma":0.000007331172,"domain_scores_codex":[0.9991225,0.0001485012,0.0002040653,0.0003215233,0.00006722126,0.0001361651],"domain_scores_gemma":[0.9996266,0.0000393664,0.0000865734,0.0001417137,0.00006439679,0.00004138336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004702256,0.0000127749,0.004480572,0.00003257008,0.00001028576,1.878501e-7,0.000177481,0.00001940774,0.3829217,0.00005151571,0.0005314863,0.611715],"study_design_scores_gemma":[0.004092103,0.001358446,0.2210766,0.0002262942,0.00005917168,0.000007447048,0.0009313155,0.08365535,0.1848662,0.001320603,0.5018874,0.0005189836],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4357738,0.001398621,0.5598392,0.001413024,0.0008984567,0.0005943167,0.000002737211,0.00006136669,0.0000184747],"genre_scores_gemma":[0.879839,0.002761148,0.1134764,0.0001696984,0.000978469,0.0007433105,0.0009114089,0.00003213752,0.001088372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.611196,"threshold_uncertainty_score":0.2786917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0913135702259476,"score_gpt":0.4427595737831088,"score_spread":0.3514460035571612,"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."}}