{"id":"W2888071326","doi":"","title":"Enter the matrix: Interpreting unsupervised feature learning with matrix decomposition to discover hidden knowledge in high-throughput omics data","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; National Research Council Canada","funders":"","keywords":"Matrix decomposition; Computer science; Biological data; Non-negative matrix factorization; DECIPHER; Context (archaeology); Drug discovery; Data mining; Artificial intelligence; Theoretical computer science; Bioinformatics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004233931,0.001835709,0.0009569715,0.002805667,0.0007750725,0.0025367,0.001482332,0.001341824,0.003615752],"category_scores_gemma":[0.01857312,0.0005027413,0.001518012,0.002570855,0.002134836,0.003523353,0.002481123,0.002320365,0.00152559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006562562,"about_ca_system_score_gemma":0.001374055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003387954,"about_ca_topic_score_gemma":0.003037115,"domain_scores_codex":[0.9983398,0.000719371,0.0001004537,0.0003492204,0.0004006047,0.0000905845],"domain_scores_gemma":[0.9947367,0.003283576,0.0004570123,0.0007305188,0.0006286755,0.0001634751],"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":[0.00048362,0.0002086739,0.006391052,0.001049269,0.0005282264,0.0006888122,0.001170226,0.1361363,0.01590479,0.2241789,0.03788758,0.5753725],"study_design_scores_gemma":[0.00003999514,0.00009184056,0.001547061,0.0001132794,0.00005573664,0.0002541159,0.0001992447,0.6113708,0.003869282,0.3688706,0.01352307,0.00006498344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002087407,0.0004103717,0.9953549,0.0003796836,0.0000789797,0.0000394977,0.0003126482,0.0008982171,0.000438315],"genre_scores_gemma":[0.1109217,0.001501633,0.8821607,0.0004654166,0.0004765136,0.0003473568,0.001781688,0.0005283492,0.001816721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004233931,"threshold_uncertainty_score":0.02239144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02140417802729721,"score_gpt":0.3499980531342871,"score_spread":0.3285938751069898,"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."}}