{"id":"W4285008006","doi":"10.1101/2022.07.11.499243","title":"CheckM2: a rapid, scalable and accurate tool for assessing microbial genome quality using machine learning","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"Parks Canada","funders":"Australian Government; McMaster University; National Science Foundation","keywords":"Genome; Metagenomics; Scalability; Computer science; Tree (set theory); Computational biology; Quality (philosophy); Data mining; Artificial intelligence; Machine learning; Biology; Gene; Genetics; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001120383,0.0005354117,0.0005897015,0.0001037591,0.0006377962,0.0002870324,0.0003654262,0.0003799698,0.00002184984],"category_scores_gemma":[0.0002586253,0.000620317,0.000210607,0.0001404915,0.0001244973,0.000004846448,0.001497291,0.0004905048,9.14938e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140728,"about_ca_system_score_gemma":0.0004321578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007464863,"about_ca_topic_score_gemma":0.000003723176,"domain_scores_codex":[0.9972901,0.0002416051,0.0005644925,0.001164024,0.0001684182,0.0005713223],"domain_scores_gemma":[0.9984201,0.000045712,0.0005136175,0.0006954405,0.0001939247,0.0001311717],"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":[0.00007050542,0.00005285681,0.01203523,0.0003238856,0.0002700897,0.000003341069,0.0000105167,0.0009538079,0.9862331,0.00002206586,0.00001955534,0.000005096777],"study_design_scores_gemma":[0.002521599,0.0003004992,0.1746912,0.0001350501,0.0004582174,2.404764e-7,0.00003393515,0.002994663,0.725086,0.000005388184,0.09107917,0.002694116],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866654,0.008838622,0.002339751,0.00007330153,0.0005717893,0.0007784693,0.0006983022,0.00003011887,0.000004297284],"genre_scores_gemma":[0.9828886,0.001112353,0.01493771,0.0001787148,0.00055325,0.0001708583,0.000007791411,0.0001388303,0.00001192065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2611471,"threshold_uncertainty_score":0.9996248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02819325749494164,"score_gpt":0.2692766303489962,"score_spread":0.2410833728540545,"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."}}