{"id":"W2098324440","doi":"10.1007/978-3-642-00727-9_15","title":"Detecting Motifs in a Large Data Set: Applying Probabilistic Insights to Motif Finding","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Probabilistic logic; Hamming distance; Computer science; Motif (music); Sequence motif; Sequence (biology); Set (abstract data type); Algorithm; Artificial intelligence; Pattern recognition (psychology); Data mining; Genetics; DNA; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007550848,0.0003956488,0.0003432695,0.0005134438,0.0001442727,0.0001498485,0.001717673,0.0002995045,0.000007634158],"category_scores_gemma":[0.0002621477,0.0003915373,0.00005085579,0.0003659579,0.0001147131,0.00001734638,0.001710215,0.0004506175,0.0000148703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001542732,"about_ca_system_score_gemma":0.0002097997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001473442,"about_ca_topic_score_gemma":0.0005529145,"domain_scores_codex":[0.9969378,0.00002955199,0.0003903987,0.001593093,0.0004266931,0.0006224274],"domain_scores_gemma":[0.9982505,0.0000576239,0.0001391417,0.001348641,0.00008066888,0.0001234116],"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":[0.00002217132,0.00006785606,0.0004970465,0.0001290837,0.00002661114,0.0001094057,0.001160784,0.06658615,0.03221041,0.0001027041,0.00001610998,0.8990717],"study_design_scores_gemma":[0.003660602,0.002209528,0.00430121,0.003699306,0.0001073565,0.0002616499,0.00001312732,0.84627,0.03980794,0.04556547,0.04772452,0.006379302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02057867,0.0008549035,0.9758027,0.0001093955,0.0004822972,0.00126809,0.00003078582,0.00003066062,0.0008424739],"genre_scores_gemma":[0.9068519,0.00003692478,0.09130258,0.000639685,0.0006835816,0.00002698012,0.000159203,0.00006036093,0.0002387854],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8926924,"threshold_uncertainty_score":0.9998537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03155034304489479,"score_gpt":0.2733723973246741,"score_spread":0.2418220542797793,"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."}}