{"id":"W4226107243","doi":"10.1371/journal.pone.0261531","title":"DeLUCS: Deep learning for unsupervised clustering of DNA sequences","year":2022,"lang":"en","type":"article","venue":"PubMed Central","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"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; Computational biology; Genome; Sequence alignment; Homology (biology); Sequence analysis; Genetics; Pattern recognition (psychology); Artificial intelligence; DNA; Gene; Computer science; Peptide sequence","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":[0.0002022075,0.0000823951,0.0001072788,0.00001961476,0.0001327192,0.000007395742,0.0001484199,0.00002620553,0.00001474072],"category_scores_gemma":[0.00004812609,0.00008649608,0.00008619474,0.00004306731,0.00003561855,4.516489e-7,0.0001682611,0.00004851041,1.291342e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000238542,"about_ca_system_score_gemma":0.00002791484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001021838,"about_ca_topic_score_gemma":0.00002752163,"domain_scores_codex":[0.9990671,0.00003712629,0.000141842,0.000187747,0.00007774928,0.0004884691],"domain_scores_gemma":[0.9997331,0.00001171852,0.0000596271,0.0001017114,0.00002402602,0.0000698416],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003127945,0.00008500812,0.07016613,0.00008316859,0.0002809775,0.000002048118,0.001393962,0.07742593,0.7726381,0.0001286791,0.0001670255,0.07731616],"study_design_scores_gemma":[0.003896025,0.001443081,0.3908052,0.00001004339,0.0001739865,0.00004270906,0.005607427,0.01340169,0.3272164,0.0005266361,0.2558489,0.001027804],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955454,0.001756253,0.001797555,0.00005948345,0.0003297935,0.0002596591,0.00003177812,0.000003047464,0.000217043],"genre_scores_gemma":[0.99843,0.000170159,0.0007295875,0.00005782963,0.0001725795,0.0002486965,0.00004192588,0.00001306956,0.0001361119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4454217,"threshold_uncertainty_score":0.3527208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01516599989170456,"score_gpt":0.2139658975498194,"score_spread":0.1987998976581149,"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."}}