{"id":"W3042374971","doi":"10.1093/bioinformatics/btaa488","title":"Factorized embeddings learns rich and biologically meaningful embedding spaces using factorized tensor decomposition","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Institute for Research in Immunology and Cancer","funders":"Canadian Institutes of Health Research; Institut de Valorisation des Données; Canada First Research Excellence Fund; Canadian Institute for Advanced Research","keywords":"Representation (politics); Computer science; Tensor (intrinsic definition); Dimensionality reduction; Embedding; Curse of dimensionality; Rank (graph theory); Sample (material); Artificial intelligence; Multifactor dimensionality reduction; Matrix decomposition; Theoretical computer science; Pattern recognition (psychology); Gene; Mathematics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000159928,0.0003036428,0.0004648637,0.00007564558,0.0003115992,0.0002534032,0.0002177111,0.0001848702,0.0001415246],"category_scores_gemma":[0.0003896965,0.0002544122,0.0001112859,0.0003016921,0.00008225903,0.0003746755,0.000135565,0.0002541664,0.00006638919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000051763,"about_ca_system_score_gemma":0.00002906341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003421546,"about_ca_topic_score_gemma":4.450875e-7,"domain_scores_codex":[0.9983827,0.00005347002,0.0006914491,0.0002516165,0.0002761357,0.0003446369],"domain_scores_gemma":[0.9985645,0.0003224236,0.0004339993,0.0001916218,0.0001532052,0.0003341859],"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":[0.001267219,0.001110282,0.01424884,0.00461072,0.001487691,0.00004508361,0.1521409,0.003461687,0.6657314,0.1200446,0.02397337,0.01187822],"study_design_scores_gemma":[0.002961943,0.0004228628,0.0005296991,0.0001510647,0.0002963895,0.00006474439,0.007533985,0.9658132,0.006996482,0.005151428,0.008869844,0.001208415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7819094,0.00002513142,0.2149187,0.001351594,0.00005954375,0.0004874288,0.00008489912,0.0004424908,0.0007207909],"genre_scores_gemma":[0.7182931,0.00002854623,0.2805695,0.0008687605,0.0001319519,0.00001164587,0.0000459076,0.00002945945,0.00002117424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9623514,"threshold_uncertainty_score":0.9999908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08759766551448768,"score_gpt":0.3535100233903203,"score_spread":0.2659123578758327,"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."}}