{"id":"W2012019831","doi":"10.1145/2506583.2506630","title":"Classifying Proteins by Amino Acid Variations of Sequential Patterns","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Entropy (arrow of time); Pattern recognition (psychology); Cluster analysis; Artificial intelligence; Computer science; Mutual information; Redundancy (engineering); Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.00006880952,0.00008819756,0.0000809329,0.00002265009,0.00004174023,0.00002362708,0.0001399051,0.000099438,0.0005149997],"category_scores_gemma":[0.00005759396,0.000076649,0.00004641886,0.00003727481,0.00002928328,0.000005834568,0.00009191367,0.00007368995,0.00004250197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006330017,"about_ca_system_score_gemma":0.00002614825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001793888,"about_ca_topic_score_gemma":0.00001593944,"domain_scores_codex":[0.9994026,0.0000289315,0.0002161617,0.0001109532,0.0001006529,0.0001406798],"domain_scores_gemma":[0.9995394,0.00000452446,0.0001076024,0.0002340717,0.00007037238,0.00004396593],"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":[0.000002779852,0.0000370026,0.01150416,0.00003991825,0.00003446524,7.496175e-8,0.00005860933,0.0000215618,0.9798402,0.0003056242,0.006315625,0.00184],"study_design_scores_gemma":[0.0004890714,0.0002641129,0.01077698,0.00001518773,0.00001760115,0.000007402697,0.0001024209,0.005938172,0.9674881,0.00006999163,0.01457942,0.0002515891],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6841366,0.00003290188,0.3011331,0.0003322056,0.00008931399,0.0004063672,0.00003905711,0.00002673176,0.0138037],"genre_scores_gemma":[0.985443,0.000009418886,0.01212802,0.0001939412,0.00005701873,0.00003667086,0.0002203943,0.00001105572,0.001900507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3013064,"threshold_uncertainty_score":0.5638885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008144220186879816,"score_gpt":0.2406566223294175,"score_spread":0.2325124021425376,"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."}}