{"id":"W3205342437","doi":"10.1101/2021.10.16.464647","title":"BugSplit: highly accurate taxonomic binning of metagenomic assemblies enables genome-resolved metagenomics","year":2021,"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":"BC Centre for Disease Control; Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Metagenomics; Contig; Computational biology; In silico; Nanopore sequencing; Biology; Genome; Workflow; Computer science; Genetics; Gene; Database","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":[0.003553478,0.002047481,0.00117742,0.002820296,0.001022421,0.002720199,0.001656059,0.001281684,0.00450159],"category_scores_gemma":[0.007248194,0.001576099,0.001389034,0.001710915,0.0006545709,0.002486117,0.002972775,0.00205484,0.00313799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008043733,"about_ca_system_score_gemma":0.00107696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001839232,"about_ca_topic_score_gemma":0.002991748,"domain_scores_codex":[0.9982066,0.0003204436,0.00017369,0.0005377571,0.0005902483,0.0001712776],"domain_scores_gemma":[0.9973787,0.0008673196,0.0003280486,0.0008301764,0.0004145077,0.0001813062],"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":[0.002881819,0.0002339951,0.03496097,0.002194524,0.001361701,0.0007974592,0.001504006,0.01747728,0.569884,0.007753204,0.08480322,0.2761478],"study_design_scores_gemma":[0.0003614855,0.0004674019,0.04296574,0.0004868904,0.0003224808,0.001299943,0.0007248968,0.24692,0.5521016,0.02232218,0.1314771,0.0005502628],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1552002,0.002068953,0.6213471,0.001195267,0.0008168851,0.0003483745,0.04392243,0.1697321,0.005368697],"genre_scores_gemma":[0.2475061,0.0005095411,0.6780856,0.0006609305,0.0001698436,0.0004785462,0.05375754,0.01677889,0.002053035],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00450159,"threshold_uncertainty_score":0.01879281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0191433385906685,"score_gpt":0.2207722298899595,"score_spread":0.201628891299291,"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."}}