{"id":"W3207684739","doi":"10.1101/2020.09.14.297424","title":"leADS: improved metabolic pathway inference based on active dataset subsampling","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":"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; Machine learning; Artificial intelligence; Class (philosophy); License; Feature (linguistics); MIT License; Set (abstract data type); Training set; Data mining; Programming language","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":[0.0004547589,0.0007982195,0.000644594,0.0001767854,0.0001726537,0.0002261061,0.001074739,0.0007850555,0.00003795905],"category_scores_gemma":[0.001466501,0.0008364902,0.0002057601,0.0002865423,0.0001356407,0.00001561546,0.0009776683,0.001340613,0.000091254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007201752,"about_ca_system_score_gemma":0.000974093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003720515,"about_ca_topic_score_gemma":0.000003292842,"domain_scores_codex":[0.9969403,0.0002001191,0.0006246043,0.001216342,0.0003946978,0.0006240058],"domain_scores_gemma":[0.9964587,0.00007623821,0.0006670283,0.002127524,0.0003120207,0.0003584663],"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":[0.0001743256,0.0001200537,0.001628542,0.0003627296,0.0001806223,0.0000122203,0.000008475518,0.001611418,0.9949706,0.0002229836,0.0006947583,0.00001323008],"study_design_scores_gemma":[0.0008994406,0.0002921673,0.0124901,0.0002123472,0.0001341708,1.535478e-8,0.000003343453,0.03113164,0.8807876,0.00000173038,0.07268119,0.001366282],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8807421,0.0009915545,0.0887908,0.001016229,0.002187458,0.002658886,0.02284205,0.000662696,0.0001082641],"genre_scores_gemma":[0.9820623,0.0001061758,0.01491921,0.001771121,0.0006324425,0.0001724161,0.000174567,0.0001592514,0.00000255972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1141831,"threshold_uncertainty_score":0.9994086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01607321600606083,"score_gpt":0.2517440644266227,"score_spread":0.2356708484205619,"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."}}