{"id":"W4401587896","doi":"10.1186/s40168-024-01861-6","title":"Fairy: fast approximate coverage for multi-sample metagenomic binning","year":2024,"lang":"en","type":"article","venue":"Microbiome","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Algorithm; Computer science; Metagenomics; Artificial intelligence; Biology; Genetics; Gene","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":[0.0001466443,0.000184942,0.000163536,0.00006631829,0.0001151613,0.0000841391,0.0001586585,0.00008891839,0.00001311428],"category_scores_gemma":[0.00001993556,0.0001730516,0.0001618153,0.00008321802,0.0000535473,9.491368e-7,0.0001459579,0.00004633111,0.00002389376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001885823,"about_ca_system_score_gemma":0.00004272766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002245426,"about_ca_topic_score_gemma":0.00001449154,"domain_scores_codex":[0.9990417,0.00001518478,0.0001794904,0.0004310683,0.00003132564,0.0003012272],"domain_scores_gemma":[0.9996424,0.00002018949,0.00003205998,0.0002258811,0.00003621337,0.00004330558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002121457,0.00002331938,0.00008966639,0.00008814388,0.0002005109,0.00000156463,0.0001217487,0.00005280789,0.9945333,0.0001261946,0.001914623,0.002826908],"study_design_scores_gemma":[0.0006016484,0.0001406414,0.0002913855,0.00001811225,0.00006141207,0.00001432021,0.00006654973,0.001030973,0.4491087,0.0001323341,0.5482003,0.0003335611],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8453016,0.01229268,0.1392735,0.000160213,0.0007593902,0.0005424352,0.001485284,0.00002806512,0.0001568385],"genre_scores_gemma":[0.9739352,0.0003109321,0.02309122,0.0001978709,0.0002671278,0.00008356786,0.0004026925,0.00005986845,0.001651556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5462857,"threshold_uncertainty_score":0.7056839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02454039499607893,"score_gpt":0.2697265679046888,"score_spread":0.2451861729086099,"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."}}