{"id":"W3081097618","doi":"10.1101/2020.08.21.260109","title":"Relabeling metabolic pathway data with groups to improve prediction outcomes","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":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Computer science; Scalability; Inference; Metabolic pathway; Set (abstract data type); Artificial intelligence; Machine learning; Biology; Genetics; Gene","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":[0.0006446603,0.0006849042,0.0006316006,0.0001452615,0.0001598486,0.0002260275,0.001499872,0.000603056,0.00001053286],"category_scores_gemma":[0.000880568,0.0006281078,0.0001117837,0.000312349,0.00007478128,0.00002594806,0.002844055,0.0009343964,0.00006532379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005257034,"about_ca_system_score_gemma":0.0005521867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003164494,"about_ca_topic_score_gemma":0.000005969824,"domain_scores_codex":[0.9967551,0.0001206822,0.0006668299,0.001433597,0.0004769166,0.0005469124],"domain_scores_gemma":[0.99537,0.00002406587,0.0004915553,0.003374075,0.0003319058,0.0004083797],"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":[0.0001278792,0.0001008133,0.03195398,0.0004658794,0.0007138203,0.00001929333,0.00002431404,0.000837502,0.9641048,0.0003216668,0.001312605,0.00001741795],"study_design_scores_gemma":[0.002577153,0.001054472,0.1747395,0.0005644664,0.0008421707,1.974203e-7,0.00001705434,0.01306029,0.6302297,0.000003880151,0.1735484,0.003362752],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.937604,0.001171639,0.05200382,0.001235369,0.001951392,0.001928727,0.003493534,0.0005546739,0.00005684496],"genre_scores_gemma":[0.946691,0.0001822767,0.05069019,0.001102019,0.0009169084,0.0001621078,0.00003790042,0.0002034542,0.00001408546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3338751,"threshold_uncertainty_score":0.999617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01351536564881809,"score_gpt":0.2320493929952831,"score_spread":0.218534027346465,"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."}}