{"id":"W3003386370","doi":"10.1101/2020.02.02.919944","title":"Metabolic pathway inference using multi-label classification with rich pathway features","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Inference; Computer science; Computational biology; Genome; Artificial intelligence; Population; Machine learning; Metabolic pathway; Biology; Gene; Genetics","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":[0.002432494,0.001402854,0.0009127002,0.003584732,0.0008576542,0.001939386,0.002238222,0.001928514,0.004009265],"category_scores_gemma":[0.006920751,0.0004340813,0.002177943,0.001704851,0.000686471,0.002121486,0.001916363,0.002051435,0.00182914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054175,"about_ca_system_score_gemma":0.001241991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004992724,"about_ca_topic_score_gemma":0.005778159,"domain_scores_codex":[0.9981639,0.0004880891,0.00009973226,0.0007055174,0.0004190883,0.0001237843],"domain_scores_gemma":[0.9948651,0.00260043,0.0005842765,0.0009201598,0.0008350988,0.0001949222],"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":[0.001520043,0.001252727,0.03797285,0.001018427,0.0005301352,0.0006676645,0.0003946301,0.2890722,0.04043215,0.007832129,0.01930626,0.6000008],"study_design_scores_gemma":[0.00002637503,0.00004784171,0.001166197,0.00001790637,0.0000225983,0.00004285784,0.00003495694,0.9843594,0.005607044,0.007178091,0.001480999,0.00001570015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1191406,0.000551754,0.8452975,0.0005035464,0.000113552,0.0003051822,0.006633123,0.02431393,0.003140896],"genre_scores_gemma":[0.389994,0.000118674,0.591035,0.0002500914,0.00006777166,0.0002433775,0.01562061,0.0005930277,0.002077349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004992724,"threshold_uncertainty_score":0.01341236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02957416697379363,"score_gpt":0.262496035896684,"score_spread":0.2329218689228904,"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."}}