{"id":"W2009070690","doi":"10.5731/pdajpst.2014.01023","title":"Cataloguing the Taxonomic Origins of Sequences from a Heterogeneous Sample Using Phylogenomics: Applications in Adventitious Agent Detection","year":2014,"lang":"en","type":"article","venue":"PDA Journal of Pharmaceutical Science and Technology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sanofi (Canada)","funders":"","keywords":"Contig; Phylogenomics; Computer science; Metagenomics; Taxonomic rank; Sequence (biology); Software; Classifier (UML); Artificial intelligence; Data mining; Biology; Phylogenetic tree; Genome; Genetics; Taxon","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044535,0.00007596879,0.0001366894,0.0001281691,0.0001332673,0.00001409113,0.0003016224,0.0000566285,0.000001718104],"category_scores_gemma":[0.0001349273,0.00005548788,0.00003340234,0.0002486097,0.0007367331,0.000002861486,0.0001338751,0.0001026216,2.664299e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005602938,"about_ca_system_score_gemma":0.00008720285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001314844,"about_ca_topic_score_gemma":0.0001184114,"domain_scores_codex":[0.9992849,0.00002676149,0.0002570605,0.0001660638,0.00009531331,0.0001698501],"domain_scores_gemma":[0.9994776,0.00004430928,0.0001732619,0.0001271358,0.0001313864,0.00004631009],"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":[0.0000108353,0.00002258941,0.006797037,0.000003427783,0.00002001935,5.238995e-7,0.00002530984,0.0002662098,0.9718257,0.0003531491,4.894902e-7,0.02067472],"study_design_scores_gemma":[0.000371154,0.0002063756,0.001568547,0.000009527565,0.00004500171,0.00007810363,0.0002270244,0.001635652,0.9699481,0.004507644,0.02130127,0.0001016274],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879273,0.001937578,0.009782334,0.0001363105,0.00008729755,0.0001050629,0.00001298657,0.000001154573,0.00000994157],"genre_scores_gemma":[0.997267,0.0005339068,0.002066463,0.000051977,0.00006993728,0.000005873128,7.882583e-7,0.000003783337,2.434284e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02130078,"threshold_uncertainty_score":0.2714524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02237278395954507,"score_gpt":0.2949805395617308,"score_spread":0.2726077556021858,"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."}}