{"id":"W4377194946","doi":"10.1101/2023.05.17.541163","title":"iDeLUCS: A deep learning interactive tool for alignment-free clustering of DNA sequences","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","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; Compute Canada","keywords":"Cluster analysis; Computer science; Metagenomics; Scalability; Data mining; Artificial intelligence; DNA sequencing; Set (abstract data type); Identifier; Genome; Unsupervised learning; Software; Machine learning; Pattern recognition (psychology); Computational biology; DNA; Biology; Database; Gene; Genetics","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":[0.001598252,0.001753906,0.001071507,0.001892453,0.0005536022,0.001432657,0.004773034,0.001266335,0.03160524],"category_scores_gemma":[0.004973621,0.001485833,0.001592862,0.00138033,0.0007162328,0.001643643,0.002945835,0.002498822,0.01151889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001140891,"about_ca_system_score_gemma":0.001726574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005153596,"about_ca_topic_score_gemma":0.00624404,"domain_scores_codex":[0.9989207,0.0001465678,0.00008505367,0.0002805927,0.0004524744,0.0001146257],"domain_scores_gemma":[0.9986171,0.0006131694,0.0001016777,0.0002552024,0.0002901501,0.0001228029],"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":[0.001642041,0.0003019409,0.004839971,0.001881954,0.0005653315,0.0005876438,0.0005441523,0.1308918,0.03446868,0.01853835,0.3504633,0.4552748],"study_design_scores_gemma":[0.0003512279,0.0001020468,0.001646759,0.000160264,0.00004379746,0.0001934284,0.00007289235,0.8558428,0.04891307,0.01942353,0.07308311,0.0001670901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.006428717,0.0002018188,0.5819739,0.0001748597,0.0001089298,0.0001476682,0.0115184,0.3962069,0.003238806],"genre_scores_gemma":[0.1155259,0.0003954529,0.777061,0.000695852,0.00007034864,0.001713224,0.0440466,0.05257487,0.007916819],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03160524,"threshold_uncertainty_score":0.1057301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01686040663622417,"score_gpt":0.2397961979941763,"score_spread":0.2229357913579522,"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."}}