{"id":"W2757020358","doi":"10.1177/0003702817732117","title":"Empirical Factors Affecting the Quality of Non-Negative Matrix Factorization of Mammalian Cell Raman Spectra","year":2017,"lang":"en","type":"article","venue":"Applied Spectroscopy","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada","keywords":"Raman spectroscopy; Interpretability; Principal component analysis; Biological system; Hyperspectral imaging; Non-negative matrix factorization; Macromolecule; Matrix (chemical analysis); Spectral line; Chemistry; Matrix decomposition; Computer science; Analytical Chemistry (journal); Artificial intelligence; Optics; Physics; Biology; Chromatography; Biochemistry; Eigenvalues and eigenvectors","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01251447,0.0009468853,0.0005714088,0.0007270884,0.0007028556,0.0009636672,0.0006349343,0.000981682,0.0008817713],"category_scores_gemma":[0.07381944,0.0003888566,0.0005281226,0.0004639018,0.001256318,0.00138617,0.0008090294,0.001365543,0.0002277899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006682456,"about_ca_system_score_gemma":0.001071561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00407662,"about_ca_topic_score_gemma":0.005167991,"domain_scores_codex":[0.997317,0.001451407,0.0002038162,0.0002683332,0.0006236054,0.0001358865],"domain_scores_gemma":[0.9381891,0.05251427,0.002354432,0.002345338,0.004324876,0.0002718647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008484971,0.0002373598,0.01363259,0.0005821284,0.0001708527,0.0002499635,0.0007129876,0.7088754,0.05955086,0.007572612,0.001558025,0.2060087],"study_design_scores_gemma":[0.00002839977,0.00008202875,0.003228984,0.00003233142,0.00001864267,0.0001003543,0.00006832692,0.9785553,0.01454388,0.002911398,0.0003942485,0.00003623241],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2130322,0.0004201156,0.7846078,0.0003786629,0.00004548277,0.00008663357,0.0001073041,0.0005694926,0.0007523278],"genre_scores_gemma":[0.6182697,0.0002706588,0.3804291,0.0000926038,0.00002520746,0.00008345331,0.0003636906,0.0001576658,0.0003077717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01251447,"threshold_uncertainty_score":0.06618363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02715222054972019,"score_gpt":0.3999208150506032,"score_spread":0.372768594500883,"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."}}