{"id":"W4393737653","doi":"10.5281/zenodo.3711137","title":"Metabolic pathway prediction using non-negative matrix factorization with improved precision","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","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; Factorization; Matrix (chemical analysis); Computer science; Non-negative matrix factorization; Algorithm; Mathematics; 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":[0.0003482936,0.0003255576,0.0002673998,0.0001918817,0.00106528,0.0005044617,0.0008573732,0.0002522315,0.0007982784],"category_scores_gemma":[0.001003075,0.0003042103,0.00007368719,0.0004154883,0.0001149443,0.00003391671,0.001139788,0.0005189772,0.0008986391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007771824,"about_ca_system_score_gemma":0.00002438583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002783157,"about_ca_topic_score_gemma":8.871448e-7,"domain_scores_codex":[0.9979979,0.0002942932,0.0003968477,0.0005611828,0.0004257398,0.0003240663],"domain_scores_gemma":[0.9981347,0.00001307214,0.0004270731,0.0006477616,0.0005955422,0.0001818605],"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":[0.0002414537,0.00007094107,0.000001906299,0.0001930947,0.0001557586,0.000003465609,0.0001886961,0.0007084809,0.03477909,0.000009878454,0.9597628,0.003884424],"study_design_scores_gemma":[0.000621395,0.0008482368,0.00005738531,0.00005776723,0.00007297061,0.00006499237,0.00007142739,0.003636753,0.005571599,0.000005144476,0.9886892,0.0003031198],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001256345,0.00005670423,0.05084169,0.00004206901,0.0002108418,0.001045919,0.9453543,0.0001771972,0.00101488],"genre_scores_gemma":[0.004941795,0.0002172925,0.001650182,0.00006337951,0.0004931836,1.444901e-7,0.9916235,0.0008733041,0.0001372814],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04919151,"threshold_uncertainty_score":0.999941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0162224134389584,"score_gpt":0.2528149616698332,"score_spread":0.2365925482308749,"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."}}