{"id":"W1606410455","doi":"10.1186/1471-2105-7-301","title":"Improving the accuracy of protein secondary structure prediction using structural alignment","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":148,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Prairie; Genome Canada","keywords":"Sequence (biology); Protein secondary structure; Computer science; Structural genomics; Protein structure database; Set (abstract data type); Alignment-free sequence analysis; Structural alignment; Sequence alignment; Protein structure prediction; Multiple sequence alignment; Data mining; Protein structure; Test set; Computational biology; Artificial intelligence; Sequence database; Peptide sequence; Biology; 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":[0.0001125924,0.0001727472,0.0001316823,0.00003425611,0.000136892,0.00003893785,0.0002252935,0.0001674718,0.00001275388],"category_scores_gemma":[0.00007878875,0.0001176709,0.00008401018,0.00008514545,0.0001050602,0.00002067906,0.0001396975,0.0001243012,5.241499e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002557146,"about_ca_system_score_gemma":0.000164995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000859532,"about_ca_topic_score_gemma":0.00005825904,"domain_scores_codex":[0.9989462,0.00002776432,0.0004891912,0.0001284067,0.0001968105,0.0002115992],"domain_scores_gemma":[0.9990741,0.00001356892,0.0004051676,0.0003980627,0.00007833586,0.00003078096],"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":[0.0000946591,0.00001221733,0.003389782,0.0004645968,0.00005441652,4.790527e-7,0.0001595287,0.01148612,0.9731296,0.001052379,0.0002080435,0.009948151],"study_design_scores_gemma":[0.001168399,0.0002500464,0.00749189,0.00005223399,0.00007674077,0.0001066053,0.0004332929,0.4148193,0.5713325,0.002002443,0.001842229,0.0004243439],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9088926,0.0002683657,0.08954392,0.00001041266,0.0001926239,0.0005492051,0.0002675861,0.00001509396,0.000260157],"genre_scores_gemma":[0.9080148,0.000002974186,0.09133133,0.00004801704,0.0002571878,0.000007221646,0.0002809296,0.0000148987,0.00004262235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4033332,"threshold_uncertainty_score":0.479848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006201983545477943,"score_gpt":0.2175972890365775,"score_spread":0.2113953054910996,"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."}}