{"id":"W4400140691","doi":"10.1093/bioinformatics/btae252","title":"Floria: fast and accurate strain haplotyping in metagenomes","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metagenomics; Strain (injury); Computer science; Pipeline (software); Workflow; Computational biology; Set (abstract data type); Haplotype; Genome; Data mining; Biology; Genetics; Database; Gene; Allele; Operating system; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001442582,0.0001110701,0.0001065277,0.00005714188,0.00003805701,0.00006812806,0.00007262101,0.00006391281,0.000004107432],"category_scores_gemma":[0.00002148606,0.00009625231,0.00003399819,0.00007410152,0.00004227499,0.000002296514,0.000107521,0.00005463283,0.00001144025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007245863,"about_ca_system_score_gemma":0.00003645933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004714474,"about_ca_topic_score_gemma":0.00002635703,"domain_scores_codex":[0.9994492,0.000008923132,0.0002075899,0.0001196891,0.00004995242,0.0001646506],"domain_scores_gemma":[0.9997915,0.00001193666,0.00002446154,0.0001205062,0.00001460951,0.00003698234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000774197,0.00005396381,0.00609968,0.001294737,0.0008001557,0.00003446083,0.009452637,0.001231881,0.4692394,0.008347091,0.00334394,0.5000246],"study_design_scores_gemma":[0.002297494,0.0009309712,0.07726159,0.0003339883,0.0002085579,0.0001341502,0.009272424,0.09485631,0.04176325,0.003075297,0.7676796,0.002186362],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9779714,0.01375111,0.002955126,0.0002939982,0.000512291,0.0002373007,0.0001203928,0.00001459461,0.004143727],"genre_scores_gemma":[0.992964,0.001881827,0.004595194,0.0001107647,0.0001744058,0.00001085216,0.00002950504,0.00001349213,0.0002199288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7643357,"threshold_uncertainty_score":0.3925055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0157962292123607,"score_gpt":0.2470699199430443,"score_spread":0.2312736907306836,"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."}}