{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009654994,0.0012733,0.001346549,0.002095137,0.0006262667,0.001596853,0.001081599,0.001450167,0.001194837],"category_scores_gemma":[0.01923692,0.000324353,0.001373281,0.001188718,0.0009651244,0.001646789,0.001043497,0.001592574,0.0005517656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000709519,"about_ca_system_score_gemma":0.002182653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002882403,"about_ca_topic_score_gemma":0.002003348,"domain_scores_codex":[0.9963334,0.001739074,0.000275061,0.0006040309,0.0007912349,0.0002572275],"domain_scores_gemma":[0.9905363,0.006232077,0.0007558594,0.0004242778,0.001705498,0.0003460345],"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":[0.0007855043,0.0003971901,0.006279075,0.0008263875,0.0002738328,0.0002407446,0.0003396538,0.3897449,0.02336768,0.01597921,0.00357704,0.5581887],"study_design_scores_gemma":[0.0000206036,0.000132198,0.0008781083,0.00003173291,0.00002121787,0.00006848357,0.00005087185,0.9922636,0.003686883,0.002234958,0.000580859,0.0000305162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01570598,0.0004957615,0.9828768,0.0001048398,0.00002649386,0.00007648842,0.00004787993,0.000273738,0.000391942],"genre_scores_gemma":[0.2614605,0.0005500623,0.7362273,0.0001039973,0.00008607532,0.0002848865,0.0004328428,0.0001394776,0.0007147371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009654994,"threshold_uncertainty_score":0.05106115,"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."}}