{"id":"W2170330565","doi":"10.1093/bioinformatics/btr353","title":"A tree-based approach for motif discovery and sequence classification","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Multiple sequence alignment; Artificial intelligence; Pattern recognition (psychology); Parallelizable manifold; Sequence (biology); Tree (set theory); Data mining; Sequence alignment; Algorithm; Mathematics; Biology; Peptide sequence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001002318,0.00009898988,0.00007951495,0.00002486283,0.00005724966,0.00003559576,0.0001112757,0.00009267332,0.000001110297],"category_scores_gemma":[0.00002433312,0.00008879496,0.00004370089,0.0000311937,0.00006274204,0.000009486746,0.00003407602,0.00002785139,0.000001196929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008100741,"about_ca_system_score_gemma":0.00005253398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003308282,"about_ca_topic_score_gemma":0.000003563741,"domain_scores_codex":[0.9995083,0.000006349199,0.0001875985,0.0001146897,0.00004927132,0.0001337829],"domain_scores_gemma":[0.9995879,0.000005321723,0.0001000052,0.0002232402,0.00003957232,0.00004399114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009502728,0.00109899,0.03596165,0.003532096,0.0004550919,0.000001927927,0.004372886,0.001111438,0.7557876,0.03735758,0.005329407,0.1540411],"study_design_scores_gemma":[0.0009371779,0.0003901421,0.006248364,0.00001202542,0.00003846596,0.000009031803,0.0007037639,0.9652542,0.02417985,0.0003128055,0.001567395,0.0003467938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3782469,0.00004992103,0.6165149,0.00001638951,0.00004501057,0.0003177713,0.00008606643,0.00001199723,0.004711033],"genre_scores_gemma":[0.7720667,0.00003077853,0.2272374,0.0001180665,0.00002731523,0.00003594657,0.0003505102,0.00001069759,0.0001225731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9641427,"threshold_uncertainty_score":0.3620954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03837618621678023,"score_gpt":0.2335725413216516,"score_spread":0.1951963551048713,"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."}}