{"id":"W4393575358","doi":"10.5281/zenodo.5034912","title":"Metabolic pathway prediction using non-negative matrix factorization with improved precision","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Matrix decomposition; Computer science; Matrix (chemical analysis); Factorization; Non-negative matrix factorization; Algorithm; Artificial intelligence; Chemistry; Physics; Chromatography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004188004,0.000363766,0.0002847355,0.0000749149,0.000109554,0.00008979753,0.0003257612,0.0004235198,0.003292629],"category_scores_gemma":[0.001186163,0.0003068911,0.00008931714,0.0001766524,0.000009580724,0.00001361854,0.0002766309,0.0003987269,0.0003042552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002819405,"about_ca_system_score_gemma":0.0002529649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001795506,"about_ca_topic_score_gemma":0.00001385677,"domain_scores_codex":[0.9987196,0.00006082129,0.0003232166,0.0004083906,0.0002661717,0.0002217941],"domain_scores_gemma":[0.9986719,0.00002617797,0.0005072117,0.0004804735,0.0002068459,0.0001073606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006164886,0.00001662182,0.000006439541,0.0003412327,0.00008596822,0.000002059014,0.00002670172,0.0005312948,0.004156508,5.68569e-8,0.9945629,0.0002086123],"study_design_scores_gemma":[0.0003920336,0.0003830654,0.0001006497,0.0005397837,0.00006160959,0.00001256857,0.00001250216,0.00583211,0.01555217,8.56261e-7,0.9767785,0.0003341658],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00005509838,0.00008189966,0.0005753635,0.000004136596,0.0001208441,0.0006025138,0.9984984,0.00002332675,0.00003836341],"genre_scores_gemma":[0.0003724602,0.00002797055,0.001282218,0.00006702582,0.0006463602,0.00008226593,0.9974158,0.00004514429,0.0000607279],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01778437,"threshold_uncertainty_score":0.9999383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01430083162789128,"score_gpt":0.2654121728666503,"score_spread":0.2511113412387591,"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."}}