{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002029802,0.000187058,0.0002045393,0.00007516475,0.00009486558,0.000009622811,0.0002254451,0.0003231271,0.00005540418],"category_scores_gemma":[0.0001892682,0.0001532798,0.00009399407,0.000117581,0.0002762561,0.00000775661,0.0001095366,0.0001448012,0.000003193356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002517925,"about_ca_system_score_gemma":0.00007442412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003519617,"about_ca_topic_score_gemma":0.0001122647,"domain_scores_codex":[0.9988201,0.00009590764,0.0004059945,0.0002785082,0.00009217415,0.0003072902],"domain_scores_gemma":[0.9991642,0.00002919531,0.0003040197,0.0003442493,0.00008742892,0.00007093045],"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":[0.000115817,0.000004526274,0.09419873,0.00002117154,0.00004602544,6.184446e-7,0.0001146007,0.0001002852,0.90359,0.0008327683,0.00004285633,0.0009326678],"study_design_scores_gemma":[0.000730915,0.0006704578,0.1340322,0.00003946878,0.00004227495,0.00005850845,0.0003719762,0.001964105,0.8579974,0.001424826,0.002337386,0.0003304419],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714014,0.0002535821,0.02712071,0.00002643504,0.0003341783,0.0002616131,0.0001504375,0.00003680991,0.000414816],"genre_scores_gemma":[0.9603918,0.000006668544,0.03852324,0.00004452367,0.0002741202,0.000005411609,0.0006162848,0.00001303794,0.0001248814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04559255,"threshold_uncertainty_score":0.6250569,"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."}}