{"id":"W2044438398","doi":"10.1109/bibmw.2011.6112372","title":"Synthesizing Aligned Random Pattern Digraphs from protein sequence patterns","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Cluster analysis; Protein family; Sequence logo; Protein sequencing; Computational biology; Computer science; Pattern recognition (psychology); Biology; Sequence alignment; Algorithm; Peptide sequence; Artificial intelligence; 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":[0.0001626563,0.0001840092,0.0001525799,0.00003335646,0.00006498164,0.00002960171,0.000309181,0.000133625,0.0004670276],"category_scores_gemma":[0.00009575409,0.0001533186,0.00009637319,0.00004107789,0.00004797352,0.000006482277,0.000127832,0.00007569941,0.00006174941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000621108,"about_ca_system_score_gemma":0.00002211599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000952562,"about_ca_topic_score_gemma":0.0001426692,"domain_scores_codex":[0.9990141,0.00007556596,0.0002673756,0.0002594228,0.0001345356,0.0002489899],"domain_scores_gemma":[0.99928,0.00001626125,0.0001167796,0.000465814,0.00003953179,0.00008159908],"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":[0.0001927405,0.00009756466,0.1343002,0.0000685893,0.0001858561,0.00001681423,0.001015796,0.000006833902,0.8409303,0.0001252005,0.0003986987,0.0226614],"study_design_scores_gemma":[0.00128369,0.0002351423,0.01338638,0.00008944557,0.00003197471,0.00001204016,0.0002459149,0.001087401,0.9796218,0.0002278851,0.003237915,0.0005403907],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9273453,0.00004219523,0.06239765,0.00004908508,0.00007012267,0.0002893779,0.00003791005,0.00005594777,0.009712418],"genre_scores_gemma":[0.9904844,0.00001838688,0.008337933,0.0004526373,0.00008654282,0.00004091679,0.0001242193,0.00002453323,0.0004303878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1386916,"threshold_uncertainty_score":0.6252151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02138055697487432,"score_gpt":0.2347407782175735,"score_spread":0.2133602212426992,"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."}}