{"id":"W4412173166","doi":"10.1099/mgen.0.001438","title":"skDER and CiDDER: two scalable approaches for microbial genome dereplication","year":2025,"lang":"en","type":"article","venue":"Microbial Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"Division of Microbiology and Infectious Diseases, National Institute of Allergy and Infectious Diseases; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"Scalability; Computational biology; Genome; Biology; Computer science; Genetics; Database; Gene","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001599625,0.000205376,0.0002036623,0.00005499521,0.0002516272,0.00006333064,0.0001944975,0.0001352687,0.000003190989],"category_scores_gemma":[0.00002250288,0.0002238618,0.00009692861,0.00006539487,0.0001253406,0.000001115534,0.0002474034,0.00005643588,0.000003913021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012814,"about_ca_system_score_gemma":0.0001309534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002691853,"about_ca_topic_score_gemma":0.00009295762,"domain_scores_codex":[0.9988644,0.00002208933,0.0002489852,0.0005347817,0.00002627123,0.0003034568],"domain_scores_gemma":[0.9994377,0.00001424336,0.00007153336,0.0003441354,0.00008287498,0.00004954292],"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":[0.00009681049,0.00004215017,0.0005386577,0.0000413166,0.0001298066,1.150316e-7,0.00008531405,0.0001958057,0.991086,0.0005044602,0.002122985,0.0051566],"study_design_scores_gemma":[0.002084191,0.0001262237,0.003591955,0.000008780747,0.0001135023,0.00001614637,0.0001276103,0.0002106188,0.4430258,0.0009496982,0.5492912,0.0004542653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837823,0.003884864,0.009932256,0.0005092984,0.0002137347,0.0006667816,0.0001440443,0.00000712597,0.0008595812],"genre_scores_gemma":[0.9814563,0.0005889903,0.01399645,0.0009280739,0.0003710889,0.00008430405,0.0002397253,0.00003786475,0.002297197],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5480602,"threshold_uncertainty_score":0.912882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01629361807508346,"score_gpt":0.2328643390713779,"score_spread":0.2165707209962945,"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."}}