{"id":"W2002030144","doi":"10.1016/j.physa.2006.03.004","title":"Probabilistic analysis of the frequencies of amino acid pairs within characterized protein sequences","year":2006,"lang":"en","type":"article","venue":"Physica A Statistical Mechanics and its Applications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Probabilistic logic; Amino acid residue; Amino acid; Proteome; Computational biology; Human proteome project; Statistical model; Computer science; Peptide sequence; Biology; Bioinformatics; Proteomics; Artificial intelligence; Genetics; Gene","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":[0.0001282205,0.0001090612,0.0002145371,0.00003510871,0.00007734735,0.00001227688,0.0001819407,0.00005144367,0.000009355213],"category_scores_gemma":[0.0001518761,0.00007852838,0.00006703191,0.0003260116,0.00009101239,0.00000432242,0.00008191101,0.00007406648,7.53092e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006360924,"about_ca_system_score_gemma":0.0000473826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003474337,"about_ca_topic_score_gemma":0.00002866988,"domain_scores_codex":[0.9991508,0.00004746752,0.0003558999,0.0001790603,0.0001544975,0.0001122579],"domain_scores_gemma":[0.9991973,0.00004322249,0.0003047546,0.0002870558,0.0001353458,0.00003232651],"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":[0.000006229224,0.00005782808,0.00003879927,0.00006479874,0.00007310695,2.44877e-8,0.00003014501,0.0001248826,0.5377456,0.4616247,0.000009457433,0.000224421],"study_design_scores_gemma":[0.0004443873,0.0003961579,0.008859697,0.00005103296,0.001131812,0.000002733208,0.00013242,0.2018113,0.7000954,0.08531708,0.001315186,0.0004428237],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7065716,0.00009408753,0.2901062,0.000251443,0.00002080488,0.0011942,0.00127419,0.00001604645,0.0004714865],"genre_scores_gemma":[0.9924554,0.000008373833,0.007055382,0.0000227318,0.00002297438,0.0001802761,0.000203658,0.000007789567,0.00004340447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3763076,"threshold_uncertainty_score":0.3202294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008029741016630742,"score_gpt":0.2403078593868441,"score_spread":0.2322781183702134,"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."}}