{"id":"W4385302529","doi":"10.1038/s41592-023-01940-w","title":"CheckM2: a rapid, scalable and accurate tool for assessing microbial genome quality using machine learning","year":2023,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1386,"is_retracted":false,"has_abstract":false,"ca_institutions":"Parks Canada","funders":"Australian Government; McMaster University; Queensland University of Technology; National Science Foundation","keywords":"Genome; Metagenomics; Computational biology; Scalability; Bacterial genome size; Biology; Computer science; Genome size; Gene; Genetics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005771539,0.002359427,0.002227337,0.004045721,0.001061238,0.003029171,0.003115747,0.002128297,0.007512391],"category_scores_gemma":[0.01841317,0.001110811,0.001514014,0.002105247,0.0006811795,0.00239393,0.003269554,0.002248554,0.004101945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007662607,"about_ca_system_score_gemma":0.001926036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002063324,"about_ca_topic_score_gemma":0.004869646,"domain_scores_codex":[0.9954506,0.0006639504,0.0003084451,0.0008503766,0.002444405,0.0002822376],"domain_scores_gemma":[0.992289,0.003734723,0.001273262,0.001073658,0.001239582,0.000389754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003592371,0.000764938,0.06450322,0.004577009,0.00188359,0.0006584695,0.000643445,0.01472263,0.2206598,0.006090426,0.2093588,0.4725454],"study_design_scores_gemma":[0.0007469032,0.0008783733,0.04410445,0.0005076247,0.00046146,0.001155345,0.0003112046,0.4432324,0.3765132,0.01575555,0.1154885,0.0008449602],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1168775,0.002569898,0.5631688,0.0008864595,0.0006672838,0.0008456974,0.06244676,0.2465984,0.005939079],"genre_scores_gemma":[0.1974646,0.0006410543,0.6941251,0.001079047,0.0001554805,0.001723743,0.08577404,0.01423818,0.004798856],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007512391,"threshold_uncertainty_score":0.03052312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05349198636756088,"score_gpt":0.4172533937874246,"score_spread":0.3637614074198637,"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."}}