{"id":"W3200919677","doi":"10.1007/978-3-030-79290-9_4","title":"Metabolic Pathway Prediction using Non-negative Matrix Factorization with Improved Precision","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Non-negative matrix factorization; Inference; Computer science; Probabilistic logic; Matrix decomposition; Cluster analysis; Metabolic pathway; Graph; Artificial intelligence; Genome; Computational biology; Machine learning; Data mining; Theoretical computer science; Biology; Gene; Genetics; Eigenvalues and eigenvectors","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"],"consensus_categories":[],"category_scores_codex":[0.0002832733,0.0003347487,0.0002844796,0.0002056912,0.000150882,0.0001441057,0.000395331,0.000293011,0.00001235041],"category_scores_gemma":[0.0001591348,0.000274269,0.00006654007,0.0002178191,0.000224642,0.0000240585,0.0003542525,0.0004049378,0.000002059664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007251215,"about_ca_system_score_gemma":0.0004744709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001431488,"about_ca_topic_score_gemma":0.0000327158,"domain_scores_codex":[0.99831,0.00002670116,0.0003319008,0.0006478905,0.0004113726,0.0002721006],"domain_scores_gemma":[0.998713,0.00005197526,0.0003102335,0.0005444161,0.0003073399,0.00007304264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001226594,0.00005478265,0.001495795,0.0001706173,0.0001171814,0.0000167023,0.001119064,0.4479606,0.3321466,0.0003525761,0.000008273769,0.2164351],"study_design_scores_gemma":[0.0005561956,0.0005769227,0.0005187796,0.000376883,0.00003746218,0.00007678533,0.000001183929,0.7642394,0.2301983,0.0009241045,0.001891336,0.0006027014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007832774,0.0002172495,0.9904232,0.00001567758,0.0005861651,0.0003557315,0.00002710992,0.0000172175,0.0005248841],"genre_scores_gemma":[0.5335792,0.0001061398,0.4641468,0.0001956643,0.0009576234,0.000008061831,0.0002738439,0.00007054901,0.0006621769],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5262764,"threshold_uncertainty_score":0.999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007803126388566362,"score_gpt":0.2446816284988274,"score_spread":0.236878502110261,"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."}}