{"id":"W4256736905","doi":"10.7287/peerj.preprints.934","title":"A standardized, extensible framework for optimizing classification improves marker-gene taxonomic assignments","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Amplicon; Computer science; Taxonomy (biology); Identification (biology); Computational biology; Complement (music); Extensibility; Artificial intelligence; Machine learning; Gene; Biology; Programming language; Genetics; Phenotype","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01482306,0.004708158,0.00177378,0.003684995,0.001395714,0.005397756,0.006515924,0.002005894,0.003839085],"category_scores_gemma":[0.02785203,0.002009778,0.003882992,0.003074637,0.001292704,0.004579712,0.003805527,0.004389708,0.003214707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002781625,"about_ca_system_score_gemma":0.005315369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01262885,"about_ca_topic_score_gemma":0.01565005,"domain_scores_codex":[0.9894384,0.002377505,0.00176219,0.002138135,0.003564941,0.0007188214],"domain_scores_gemma":[0.9845844,0.004329286,0.001281527,0.003568801,0.005603014,0.0006329707],"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":[0.00127036,0.001228037,0.01524767,0.0009594301,0.0007348331,0.0003876369,0.0007781404,0.1766308,0.03939736,0.02590264,0.05770294,0.6797601],"study_design_scores_gemma":[0.0002166652,0.0001802024,0.002021147,0.0001128292,0.0001428944,0.0001444481,0.00009515724,0.9215968,0.03355495,0.01898176,0.02281118,0.0001419024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005068265,0.000117996,0.9383146,0.0001607558,0.00005639223,0.0002682524,0.0008841442,0.05441248,0.0007171414],"genre_scores_gemma":[0.02642134,0.00008488422,0.9633148,0.0001217317,0.00003445309,0.0004108777,0.003761057,0.005131976,0.0007187468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01482306,"threshold_uncertainty_score":0.0783928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05081571394978905,"score_gpt":0.3004549116711124,"score_spread":0.2496391977213234,"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."}}