{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005351336,0.003471545,0.002558109,0.00368427,0.001670298,0.004070847,0.004809577,0.001930939,0.01086273],"category_scores_gemma":[0.01602346,0.002174231,0.003855959,0.003381539,0.001113578,0.004734589,0.01006167,0.004187569,0.01140081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063482,"about_ca_system_score_gemma":0.002617256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002442002,"about_ca_topic_score_gemma":0.004115699,"domain_scores_codex":[0.9955837,0.0006706856,0.000498755,0.001529486,0.001325398,0.0003920098],"domain_scores_gemma":[0.9937249,0.001920932,0.0006129273,0.002449467,0.0008257732,0.000466046],"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":[0.005739598,0.001047288,0.01582628,0.00576109,0.002298049,0.001668168,0.003732442,0.0215506,0.1850426,0.01355715,0.1869895,0.5567872],"study_design_scores_gemma":[0.00264454,0.001455737,0.01708714,0.000642421,0.0009274474,0.002434413,0.001350671,0.3612552,0.2371274,0.03968444,0.3339101,0.001480472],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03360632,0.002712035,0.4893968,0.000831303,0.0009917091,0.001395613,0.02674193,0.4385222,0.005802135],"genre_scores_gemma":[0.05572605,0.001245135,0.8312742,0.0008761539,0.0001617619,0.002044294,0.07372902,0.03132111,0.003622228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01086273,"threshold_uncertainty_score":0.03633946,"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."}}