{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000178924,0.0001128715,0.0001420101,0.00004609233,0.00006962125,0.00001791106,0.0002044526,0.00006244936,0.000002592017],"category_scores_gemma":[0.0001780011,0.0001038158,0.00009000118,0.00007869912,0.00004836131,0.000002439384,0.0002814028,0.00003551821,0.000006546651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009196206,"about_ca_system_score_gemma":0.00001873661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003428058,"about_ca_topic_score_gemma":0.000009597163,"domain_scores_codex":[0.9993013,0.00001150292,0.0002946592,0.0001065151,0.00008734933,0.0001987123],"domain_scores_gemma":[0.9994816,0.00004005208,0.000155699,0.000217859,0.00007779973,0.0000270386],"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":[0.0002886033,0.00005729735,0.003506991,0.0007606338,0.0006630065,0.000001727853,0.009523402,0.01665666,0.8931152,0.0002743137,0.004818876,0.07033325],"study_design_scores_gemma":[0.004073843,0.002751258,0.005138761,0.0002131902,0.0001900974,0.00002813129,0.02434524,0.2256971,0.5699905,0.001389846,0.1648498,0.001332302],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9781172,0.0002619739,0.0193174,0.00007282563,0.0002729392,0.0003760844,0.00008698031,0.00001540429,0.001479239],"genre_scores_gemma":[0.9821962,0.0005617416,0.01662638,0.0000832818,0.00009897377,0.00005480687,0.00009746206,0.00001639251,0.0002647827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3231247,"threshold_uncertainty_score":0.4233485,"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."}}