{"id":"W4391377424","doi":"10.1101/2024.01.28.577669","title":"Floria: Fast and accurate strain haplotyping in metagenomes","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metagenomics; Strain (injury); Computational biology; Genome; Shotgun sequencing; Haplotype; Computer science; Biology; Set (abstract data type); Scalability; Data mining; Genetics; Gene; Allele; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002674452,0.001626994,0.001302337,0.001811951,0.0007310417,0.001564877,0.002780417,0.001167705,0.005835555],"category_scores_gemma":[0.005341356,0.001413708,0.001935109,0.0008615773,0.0006497834,0.00177236,0.002756045,0.002052716,0.005724634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008491692,"about_ca_system_score_gemma":0.001048881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002817105,"about_ca_topic_score_gemma":0.003858938,"domain_scores_codex":[0.9984263,0.0002140334,0.00009768455,0.0006666415,0.0004448355,0.0001504885],"domain_scores_gemma":[0.998047,0.0005688096,0.0002443577,0.000674858,0.000254424,0.0002105832],"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":[0.003718232,0.000315428,0.02739058,0.002111863,0.001230127,0.001047256,0.001065498,0.02836143,0.5213794,0.006032766,0.1090863,0.298261],"study_design_scores_gemma":[0.0009236368,0.0008189655,0.02800706,0.0004691668,0.0002759247,0.001727553,0.0003639776,0.4217733,0.4050721,0.01314656,0.1266665,0.0007552461],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1237199,0.001839707,0.4394322,0.000822328,0.0003486265,0.0005474741,0.03777768,0.3908929,0.004619183],"genre_scores_gemma":[0.223273,0.0003726116,0.7209327,0.0005293076,0.00008736813,0.000783152,0.03758911,0.01414527,0.002287542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005835555,"threshold_uncertainty_score":0.01952189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01364108540466983,"score_gpt":0.2248797565968794,"score_spread":0.2112386711922096,"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."}}