{"id":"W3192059217","doi":"10.1371/journal.pone.0261531","title":"DeLUCS: Deep learning for unsupervised clustering of DNA sequences","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Cluster analysis; Biology; DNA sequencing; Genome; Unsupervised learning; Computational biology; Sequence (biology); Homology (biology); Taxonomic rank; Pattern recognition (psychology); Artificial intelligence; Genetics; Computer science; DNA; Gene","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":[0.0009877472,0.001492825,0.00100052,0.001478917,0.000776905,0.001149491,0.002836464,0.001412911,0.003227944],"category_scores_gemma":[0.00243018,0.0007717513,0.001109039,0.001271547,0.001135293,0.001355061,0.002132686,0.002229028,0.001778076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002059529,"about_ca_system_score_gemma":0.002040852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01041311,"about_ca_topic_score_gemma":0.01466454,"domain_scores_codex":[0.9993299,0.0001371062,0.00003646822,0.0002221055,0.0001865089,0.00008782695],"domain_scores_gemma":[0.9992093,0.0002300416,0.00008638935,0.00020562,0.00019115,0.00007752973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002721283,0.0002116526,0.003392662,0.00033372,0.0002614654,0.0001439837,0.0001873802,0.3945707,0.02061586,0.02707069,0.02508673,0.5278531],"study_design_scores_gemma":[0.00001012345,0.00002093923,0.0001683138,0.00001039597,0.000005274397,0.00002368523,0.00001021736,0.9858136,0.004111838,0.007232733,0.002582538,0.00001037424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01200684,0.0003263052,0.9758863,0.0002053487,0.00007409352,0.00007921287,0.0006702163,0.009366216,0.00138552],"genre_scores_gemma":[0.1634275,0.0002900674,0.8234033,0.0005578001,0.00006492253,0.0004118826,0.005459187,0.0009731351,0.00541219],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01041311,"threshold_uncertainty_score":0.02070498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0290963853029281,"score_gpt":0.2302012257113439,"score_spread":0.2011048404084158,"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."}}