{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002897578,0.000905227,0.001645913,0.003404419,0.0006074141,0.00207677,0.002944512,0.001498909,0.001686288],"category_scores_gemma":[0.01417859,0.001304977,0.001996887,0.004322966,0.001226151,0.003514061,0.002220785,0.002054385,0.0007648881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005382344,"about_ca_system_score_gemma":0.0007112388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001297282,"about_ca_topic_score_gemma":0.002700264,"domain_scores_codex":[0.9981865,0.0004006748,0.0001831464,0.00059507,0.0005517087,0.00008289322],"domain_scores_gemma":[0.988809,0.00930772,0.00058384,0.0007547429,0.0003799596,0.0001648031],"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":[0.0003138618,0.0002577133,0.01648045,0.001000019,0.0004325009,0.0004928326,0.0004599194,0.1190431,0.03158114,0.02365335,0.00503871,0.8012463],"study_design_scores_gemma":[0.00002551593,0.0000842472,0.003075751,0.00004687007,0.0000958524,0.0008445656,0.00008835972,0.8603823,0.005328682,0.1272008,0.002774707,0.00005232275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01466738,0.001140825,0.9828302,0.0002061323,0.00001961248,0.00003005924,0.0002419603,0.0005872363,0.0002766775],"genre_scores_gemma":[0.1085936,0.001174063,0.8879039,0.0001148183,0.0001015573,0.0001029682,0.001034816,0.0002037586,0.0007704717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003404419,"threshold_uncertainty_score":0.01532406,"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."}}