{"id":"W1996768014","doi":"10.1186/1472-6807-7-25","title":"Prediction of flexible/rigid regions from protein sequences using k-spaced amino acid pairs","year":2007,"lang":"en","type":"article","venue":"BMC Structural Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China","keywords":"Curse of dimensionality; Pattern recognition (psychology); Feature (linguistics); Protein methods; Computer science; Representation (politics); Threading (protein sequence); Feature selection; Protein structure prediction; Artificial intelligence; Support vector machine; Protein structure; Pseudo amino acid composition; Sequence (biology); Protein tertiary structure; Algorithm; Peptide sequence; Amino acid; Biology; Biochemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005105795,0.0007091667,0.0006458255,0.001935617,0.000309866,0.0003544495,0.0004363485,0.0006527929,0.0008860395],"category_scores_gemma":[0.001376099,0.000157793,0.0007128939,0.001114832,0.0002396869,0.0005119345,0.0002830275,0.0005312752,0.0007849011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003281163,"about_ca_system_score_gemma":0.0005420333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001934967,"about_ca_topic_score_gemma":0.00166516,"domain_scores_codex":[0.9996212,0.0000550468,0.00004012084,0.000154401,0.00008517446,0.00004400633],"domain_scores_gemma":[0.9990332,0.0003492772,0.0002839501,0.0000722918,0.0001949633,0.00006630313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002337813,0.0009173458,0.09633837,0.0008468933,0.0003203707,0.001311208,0.000200423,0.2203332,0.1903574,0.00149359,0.007640449,0.4779029],"study_design_scores_gemma":[0.00004154289,0.0001633202,0.01760275,0.00003251191,0.00005296676,0.0004870198,0.0000538915,0.961193,0.01797155,0.001071476,0.00130532,0.00002467107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7503201,0.00114872,0.242075,0.000143237,0.00005102742,0.0001291376,0.002762168,0.002152026,0.001218616],"genre_scores_gemma":[0.8371077,0.0002765503,0.1560417,0.00005218127,0.00003721635,0.00009298813,0.005838825,0.00006324872,0.0004896208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001935617,"threshold_uncertainty_score":0.003847361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03267685854606961,"score_gpt":0.2933025375500183,"score_spread":0.2606256790039487,"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."}}