{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001272204,0.00007020784,0.0001388692,0.00003682089,0.0001134491,0.00000720597,0.0001497323,0.00003194534,0.0001160884],"category_scores_gemma":[0.00007244328,0.00007217101,0.0000879162,0.00009471601,0.00003319108,0.000003337046,0.0001223256,0.00006298172,0.000001582671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001116824,"about_ca_system_score_gemma":0.00001781607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002674301,"about_ca_topic_score_gemma":0.00002518033,"domain_scores_codex":[0.9993452,0.00003833025,0.0001456506,0.0001848464,0.0001480628,0.0001378964],"domain_scores_gemma":[0.9996914,0.00001384886,0.00007072186,0.0001324967,0.00006047483,0.00003105566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006261622,0.0001475824,0.00177394,0.0000533759,0.0001699595,0.000001006102,0.00009751387,0.003190121,0.9924437,0.000008261552,0.000006895911,0.002045072],"study_design_scores_gemma":[0.0004064781,0.0008491845,0.0002328924,0.00002111591,0.000166437,0.000002393113,0.0008895225,0.02380348,0.972155,0.0001351111,0.001146614,0.000191767],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970309,0.0007011003,0.001736348,0.00009242177,0.00001353649,0.0001097347,0.00001381289,0.000009237441,0.0002929342],"genre_scores_gemma":[0.9967834,0.000115508,0.002210513,0.00009249742,0.0000611871,0.00007659396,0.000130918,0.00001146442,0.0005179661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02061336,"threshold_uncertainty_score":0.2943048,"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."}}