{"id":"W4385897776","doi":"10.1093/bioinformatics/btad508","title":"<i>i</i>DeLUCS: a deep learning interactive tool for alignment-free clustering of DNA sequences","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Cluster analysis; Computer science; Metagenomics; DNA sequencing; Data mining; Artificial intelligence; Scalability; Genomics; Software; Set (abstract data type); Genome; Unsupervised learning; Identifier; Computational biology; Pattern recognition (psychology); Machine learning; DNA; Biology; Database; Genetics; 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":[0.00127146,0.001853821,0.0008437225,0.001582319,0.0005203647,0.001373973,0.004939169,0.001332757,0.05457161],"category_scores_gemma":[0.004327453,0.001293576,0.001330441,0.001214366,0.0007362384,0.001821384,0.003257443,0.002438019,0.01792791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133624,"about_ca_system_score_gemma":0.001279894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005056207,"about_ca_topic_score_gemma":0.006380807,"domain_scores_codex":[0.9991491,0.0000998026,0.00007092537,0.0002198829,0.0003718766,0.00008853572],"domain_scores_gemma":[0.9986861,0.000475997,0.0001136521,0.0002800197,0.0003110546,0.0001330335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009372853,0.0001798532,0.002959428,0.001508893,0.000314835,0.0005565392,0.0003401092,0.03368494,0.0316437,0.01252885,0.5914459,0.3238995],"study_design_scores_gemma":[0.0004861478,0.0001363364,0.002866661,0.000313706,0.00005882941,0.0005147214,0.00006607988,0.6626505,0.09557214,0.02314094,0.2139092,0.000284826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00375616,0.0001852656,0.4977592,0.0002500236,0.0001354149,0.0001331092,0.01453533,0.4791577,0.004087789],"genre_scores_gemma":[0.09268232,0.0004198076,0.7186749,0.001108488,0.0001093179,0.001641974,0.0834288,0.08844051,0.01349386],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05457161,"threshold_uncertainty_score":0.1825602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01482127274179808,"score_gpt":0.2507821011509559,"score_spread":0.2359608284091579,"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."}}