{"id":"W4387186903","doi":"10.1101/2023.09.27.559801","title":"skDER & CiDDER: two scalable approaches for microbial genome dereplication","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Metagenomics; Computational biology; Genome; Biology; Biochemical engineering; Evolutionary biology; Genetics; Engineering; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00467507,0.002879779,0.002032947,0.002338753,0.001593267,0.002941082,0.006318219,0.001978151,0.01265321],"category_scores_gemma":[0.01263091,0.001846106,0.002957254,0.002259579,0.001196332,0.003782227,0.008267484,0.003935574,0.01195551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001503168,"about_ca_system_score_gemma":0.002589589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002997305,"about_ca_topic_score_gemma":0.004239385,"domain_scores_codex":[0.9963045,0.0006667894,0.0003243335,0.001183933,0.001163446,0.0003569203],"domain_scores_gemma":[0.993417,0.002191171,0.0005188301,0.00251134,0.0008452914,0.0005163512],"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":[0.004058002,0.001226184,0.01061716,0.002391038,0.00108351,0.001120289,0.001446741,0.04654686,0.1320003,0.01455333,0.1936906,0.591266],"study_design_scores_gemma":[0.001545652,0.0006203425,0.005733224,0.0001972214,0.0002195025,0.0008124073,0.000409704,0.6829234,0.1395629,0.02147334,0.1458496,0.0006526852],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04155885,0.001069838,0.51071,0.0008285961,0.0005639633,0.001001857,0.007430438,0.4318864,0.004950004],"genre_scores_gemma":[0.07141759,0.0004080719,0.8715816,0.0006461498,0.00009704851,0.001427129,0.02270938,0.02789833,0.003814803],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01265321,"threshold_uncertainty_score":0.04232919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04110654492917749,"score_gpt":0.241477909901489,"score_spread":0.2003713649723115,"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."}}