{"id":"W1998271648","doi":"10.1186/1471-2105-15-s12-s2","title":"Discovering co-occurring patterns and their biological significance in protein families","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Amino acid; Biology; Conserved sequence; Computational biology; Peptide sequence; Phylogenetic tree; Sequence alignment; Closeness; Genetics; Protein sequencing; Multiple sequence alignment; Taxonomic rank; Evolutionary biology; Bioinformatics; Gene; Ecology","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":[0.001624323,0.0004766808,0.0005872311,0.008117464,0.001041214,0.001360751,0.0007280969,0.0007317017,0.001437281],"category_scores_gemma":[0.008966723,0.000276238,0.0008752109,0.006576182,0.001108748,0.001506951,0.000995586,0.0007620401,0.000509791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007809444,"about_ca_system_score_gemma":0.0008393715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002091941,"about_ca_topic_score_gemma":0.001806993,"domain_scores_codex":[0.9981158,0.0003356558,0.0002092919,0.0006993681,0.0004610792,0.0001788476],"domain_scores_gemma":[0.9881377,0.007024296,0.002651371,0.0006582732,0.001057309,0.0004710949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001005161,0.0004281369,0.7268288,0.001002617,0.0005939352,0.001649785,0.001811782,0.01304442,0.03647539,0.006471784,0.002063348,0.2086249],"study_design_scores_gemma":[0.00009738743,0.0004327643,0.5701895,0.0002280099,0.0005791689,0.00671757,0.002951764,0.3268629,0.02509227,0.05795601,0.008754235,0.0001384379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9053385,0.001695503,0.08893724,0.0002539585,0.0000301556,0.00013426,0.001502185,0.0005158199,0.001592479],"genre_scores_gemma":[0.9397144,0.0003368797,0.05770634,0.00002447128,0.00003587597,0.00009004349,0.001818011,0.00004536004,0.0002286374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008117464,"threshold_uncertainty_score":0.008590281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01057686144615,"score_gpt":0.2285720905072953,"score_spread":0.2179952290611453,"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."}}