{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00116672,0.001785313,0.00109476,0.002109466,0.0009239647,0.001384948,0.002948154,0.001459275,0.004697565],"category_scores_gemma":[0.002850563,0.0008832532,0.001345778,0.00195188,0.001024986,0.001561709,0.002244688,0.002345299,0.002690569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002207422,"about_ca_system_score_gemma":0.00250819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01304363,"about_ca_topic_score_gemma":0.02055171,"domain_scores_codex":[0.9991686,0.0001774506,0.00005246856,0.0002769519,0.0002284525,0.00009601562],"domain_scores_gemma":[0.9991413,0.0002567773,0.00008916894,0.0002158913,0.0002234277,0.0000733104],"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":[0.0003321028,0.0002238732,0.003115378,0.000609201,0.0003283273,0.0001467011,0.0002059269,0.2294008,0.01522281,0.02013527,0.04576801,0.6845115],"study_design_scores_gemma":[0.00002532382,0.00004014397,0.0003172382,0.00002918754,0.00001433328,0.0000439453,0.00002174199,0.9720994,0.007099937,0.01262026,0.007668363,0.00002010878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01091156,0.0007061829,0.9657082,0.0002977329,0.0001255935,0.0001469182,0.0021044,0.01803125,0.001968111],"genre_scores_gemma":[0.1081835,0.0005039949,0.8715319,0.0005546043,0.00007738003,0.0005451603,0.01190223,0.001163368,0.005537825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01304363,"threshold_uncertainty_score":0.02593535,"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."}}