{"id":"W2887325828","doi":"10.1109/tnb.2018.2845741","title":"Discovering Patterns From Sequences Using Pattern-Directed Aligned Pattern Clustering","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on NanoBioscience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Leverage (statistics); Computer science; Computational biology; Breakpoint; Data mining; Pattern recognition (psychology); Algorithm; Artificial intelligence; Genetics; Biology","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":[0.00008767805,0.0002125787,0.0001512734,0.00006142722,0.0003969869,0.00007037703,0.0003103773,0.0000870603,0.00004158429],"category_scores_gemma":[0.000004324694,0.0001996929,0.00008914456,0.000129379,0.000219716,0.00000549334,0.00001372104,0.00005135636,0.00001223076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003254977,"about_ca_system_score_gemma":0.00005268083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001452423,"about_ca_topic_score_gemma":0.001619713,"domain_scores_codex":[0.9986506,0.00004497006,0.0002172161,0.0005774567,0.0001686284,0.0003411616],"domain_scores_gemma":[0.9993938,0.00001757466,0.00007881621,0.0003606154,0.00006581163,0.0000834447],"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":[0.00001485456,0.00003753111,0.002479661,0.000005132182,0.00003233353,0.000002097565,0.0002180155,0.001140316,0.9874039,1.113143e-7,0.000006772239,0.008659276],"study_design_scores_gemma":[0.0002990506,0.000303533,0.007734201,0.0000572246,0.00002763412,0.00001085447,0.0001553773,0.008803383,0.9820353,0.000009499841,0.0002240603,0.0003398217],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6205617,0.00003380341,0.3783181,0.00002934341,0.0007745013,0.00008805877,0.0001518127,0.0000123827,0.00003035021],"genre_scores_gemma":[0.9984233,0.0000946305,0.0008565302,0.0003074302,0.0002171227,0.00001482195,0.000005037431,0.0000214584,0.00005968948],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3778616,"threshold_uncertainty_score":0.8143241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0211234114176969,"score_gpt":0.2558546205686612,"score_spread":0.2347312091509643,"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."}}