{"id":"W4367336835","doi":"10.2196/43665","title":"Decision of the Optimal Rank of a Nonnegative Matrix Factorization Model for Gene Expression Data Sets Utilizing the Unit Invariant Knee Method: Development and Evaluation of the Elbow Method for Rank Selection","year":2023,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Non-negative matrix factorization; Mathematics; Matrix decomposition; Rank (graph theory); Computer science; Pattern recognition (psychology); Data mining; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001491689,0.0001133707,0.0001601597,0.00009796876,0.0001858192,0.00001065802,0.0003140531,0.0002729234,7.582017e-7],"category_scores_gemma":[0.0003451405,0.00006099704,0.00004591894,0.0003203907,0.00009255392,0.00001572259,0.0003905937,0.00007271167,4.851009e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001224677,"about_ca_system_score_gemma":0.0001824216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003089546,"about_ca_topic_score_gemma":0.00001258143,"domain_scores_codex":[0.9989421,0.0000957365,0.0004412466,0.000192315,0.0002104307,0.0001181877],"domain_scores_gemma":[0.9986512,0.0001038261,0.0004968526,0.0004542655,0.0002778679,0.00001596255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001628865,0.00001996413,0.0000545079,0.000116529,0.00004054398,2.678086e-9,0.0007191482,0.003880513,0.9082001,0.0004370615,0.0002496854,0.08611906],"study_design_scores_gemma":[0.0005451434,0.0000503077,0.0003689031,0.00003498143,0.00003482433,0.000001478747,0.0006194095,0.4903657,0.5070427,0.0003515352,0.000542117,0.00004288194],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2742923,0.00009084815,0.723806,0.0003335018,0.00006575041,0.00128258,0.0001156521,0.000007088321,0.000006358584],"genre_scores_gemma":[0.7129672,0.0001307529,0.2865226,0.00002239898,0.00001111596,0.0001640399,0.0001498785,0.00000963658,0.00002241979],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4864852,"threshold_uncertainty_score":0.2487387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0809211860378672,"score_gpt":0.3836042088129658,"score_spread":0.3026830227750986,"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."}}