{"id":"W4213454339","doi":"10.1038/s42003-022-03114-4","title":"BugSplit enables genome-resolved metagenomics through highly accurate taxonomic binning of metagenomic assemblies","year":2022,"lang":"en","type":"article","venue":"Communications Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"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; Biology; Nanopore sequencing; 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":[0.003647432,0.002127209,0.001078171,0.003540118,0.001219528,0.002781257,0.001847216,0.001123048,0.004715504],"category_scores_gemma":[0.009350919,0.001587035,0.001735786,0.00207696,0.0006373749,0.00255343,0.003703949,0.001893091,0.003312892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009601544,"about_ca_system_score_gemma":0.001311524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002326566,"about_ca_topic_score_gemma":0.004964409,"domain_scores_codex":[0.9980122,0.0003329719,0.0002156066,0.0006421846,0.0006235975,0.0001733859],"domain_scores_gemma":[0.9961888,0.001402461,0.0005544088,0.0009491001,0.0006379152,0.0002672504],"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":[0.004168829,0.0003083078,0.05898655,0.003046221,0.001938179,0.001166757,0.002977345,0.01810234,0.4494415,0.009454254,0.07887539,0.3715344],"study_design_scores_gemma":[0.0003916762,0.0008257954,0.05490203,0.0006738139,0.0004781252,0.002006045,0.001391691,0.269213,0.4840111,0.02081418,0.164572,0.0007205134],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1274683,0.001496176,0.6408427,0.0006954168,0.0005147982,0.00047871,0.04705578,0.1738626,0.007585609],"genre_scores_gemma":[0.1996565,0.0004753436,0.7203029,0.0006043867,0.0001177532,0.0007459113,0.06156504,0.01431318,0.002218891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004715504,"threshold_uncertainty_score":0.01928967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05763515421892181,"score_gpt":0.2972131714242633,"score_spread":0.2395780172053416,"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."}}