{"id":"W4395954635","doi":"10.1101/2024.04.23.590803","title":"Fairy: fast approximate coverage for multi-sample metagenomic binning","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; Sample (material); Computer science; Statistics; Data mining; Mathematics; Biology; Chromatography; Chemistry","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":[0.002849123,0.00218708,0.002059109,0.002803505,0.001587144,0.002759764,0.003410624,0.001711152,0.02288394],"category_scores_gemma":[0.01371101,0.001482423,0.002505261,0.002858671,0.001102266,0.00303109,0.003354191,0.002644981,0.007448186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001958941,"about_ca_system_score_gemma":0.002831877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01047358,"about_ca_topic_score_gemma":0.01559311,"domain_scores_codex":[0.9979367,0.0003013243,0.0001381927,0.0006529955,0.0007592944,0.0002113524],"domain_scores_gemma":[0.9976967,0.00107797,0.0001768824,0.0005172204,0.0004000427,0.0001311557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002709585,0.000327267,0.01939345,0.002493839,0.001244363,0.0006844692,0.001092004,0.1461164,0.06293738,0.02468504,0.1199364,0.6183798],"study_design_scores_gemma":[0.0003150513,0.0001215881,0.004086687,0.0001179887,0.0001022743,0.0002473887,0.0001559086,0.8833748,0.03888915,0.03819578,0.03422771,0.0001655509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0187924,0.001030438,0.8211293,0.0002369106,0.0002466273,0.0002046315,0.006248153,0.1501325,0.001979148],"genre_scores_gemma":[0.1029357,0.0002369692,0.8603927,0.0004287687,0.00008223463,0.0007023525,0.01350304,0.0190536,0.002664566],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02288394,"threshold_uncertainty_score":0.07655442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02298928258792027,"score_gpt":0.2444211366700951,"score_spread":0.2214318540821749,"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."}}