{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003966042,0.0007625916,0.0006015114,0.0001636147,0.0002181954,0.0002741223,0.0008172261,0.0008516797,0.00001037991],"category_scores_gemma":[0.0005875747,0.0007156634,0.000121856,0.0004152487,0.0001709541,0.00002114945,0.0007654506,0.001135132,0.00003092798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000797242,"about_ca_system_score_gemma":0.001126185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003916847,"about_ca_topic_score_gemma":0.000007428007,"domain_scores_codex":[0.9970918,0.0002107147,0.0005976416,0.001087852,0.0004452523,0.0005667114],"domain_scores_gemma":[0.9967424,0.00002773436,0.0008021992,0.001518421,0.0006001426,0.0003090769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005968417,0.0001300633,0.01004985,0.0003275199,0.0002349166,0.00001239262,0.00002481775,0.0003976481,0.9881461,0.000530165,0.00006889761,0.00001798039],"study_design_scores_gemma":[0.001410068,0.0002286639,0.1046399,0.00032228,0.00021589,1.906784e-7,0.00001332273,0.02988225,0.8512189,0.000001307064,0.01035033,0.001716841],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9385266,0.001886325,0.05724809,0.0001924149,0.0005420662,0.000950543,0.0003447803,0.000272692,0.00003646387],"genre_scores_gemma":[0.8848136,0.0002290803,0.1138541,0.0003613674,0.0004569588,0.0001069051,0.00000971192,0.0001561693,0.00001213607],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1369271,"threshold_uncertainty_score":0.9995294,"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."}}