{"id":"W2078685372","doi":"10.1142/9789812702456_0035","title":"DISCOVERING SEQUENCE-STRUCTURE MOTIFS FROM PROTEIN SEGMENTS AND TWO APPLICATIONS","year":2004,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Sequence (biology); Protein secondary structure; Cluster (spacecraft); Protein structure prediction; Structural alignment; Local structure; Protein tertiary structure; Support vector machine; Protein structure; Artificial intelligence; Dynamic programming; Data structure; Data mining; Pattern recognition (psychology); Sequence alignment; Algorithm; Peptide sequence; Biology; Physics; Genetics","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":[0.00002539362,0.00009545387,0.00006149135,0.00001295537,0.00006568401,0.00003422958,0.000101842,0.00005903265,0.00002539753],"category_scores_gemma":[0.00001489901,0.00008126436,0.00001806288,0.00003446263,0.00004085802,0.000004929625,0.0001044556,0.00007631336,0.000007569296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001230822,"about_ca_system_score_gemma":0.00002600661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001595059,"about_ca_topic_score_gemma":0.00009701839,"domain_scores_codex":[0.9995344,0.000007824849,0.000113015,0.000162576,0.00007017555,0.000112064],"domain_scores_gemma":[0.9996677,0.00000197156,0.00004523055,0.0002211951,0.00001538814,0.00004848122],"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":[0.000006946225,0.0000127919,0.003547232,0.00001841975,0.00002708067,4.861041e-7,0.0001156283,0.002702386,0.9897489,0.0009224215,0.00002014338,0.002877597],"study_design_scores_gemma":[0.001745869,0.0001429912,0.004661247,0.00004186002,0.00002411178,0.00002575725,0.0002167611,0.001681124,0.9690833,0.006378347,0.01549432,0.0005042769],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9360245,0.00005079833,0.06209994,0.000104725,0.00001642124,0.0002708049,0.00005298663,0.00001856823,0.001361251],"genre_scores_gemma":[0.9525788,0.000008527004,0.04659439,0.0001607715,0.00008532582,0.00002694473,0.0002437429,0.000009898254,0.0002916425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02066554,"threshold_uncertainty_score":0.3313864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005945630023237146,"score_gpt":0.2548494911316115,"score_spread":0.2489038611083744,"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."}}