{"id":"W2557395024","doi":"10.1007/s00726-016-2362-5","title":"Novel “extended sequons” of human N-glycosylation sites improve the precision of qualitative predictions: an alignment-free study of pattern recognition using ProtDCal protein features","year":2016,"lang":"en","type":"article","venue":"Amino Acids","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Glycosylation; Computational biology; Robustness (evolution); N-linked glycosylation; Posttranslational modification; Sequence motif; Sequence (biology); Bioinformatics; Biology; Biochemistry; Glycoprotein; Gene; Enzyme","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":[0.0007723878,0.0001497502,0.0001948428,0.0001127439,0.0001038291,0.00001165431,0.0002893316,0.0001358726,0.0000331907],"category_scores_gemma":[0.0004380679,0.00009536998,0.00007408165,0.0001513776,0.0001853521,0.00002990208,0.0001760185,0.00008346295,7.962422e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002349356,"about_ca_system_score_gemma":0.00006036261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003208387,"about_ca_topic_score_gemma":0.0002710504,"domain_scores_codex":[0.9981192,0.0004228909,0.0004902032,0.0003297419,0.0004672026,0.0001707764],"domain_scores_gemma":[0.9983738,0.00005374709,0.0003783139,0.0006324472,0.000513875,0.00004780976],"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":[0.0003048555,0.0008028877,0.00176255,0.00004531926,0.00008182506,2.508695e-7,0.001809239,0.000008806779,0.9787764,0.00001762249,0.00001538368,0.01637484],"study_design_scores_gemma":[0.002287629,0.004628067,0.02073025,0.00009936519,0.00003486258,0.000002994777,0.00322684,0.0001897359,0.9681683,0.0004967287,0.00001018979,0.0001250326],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872912,0.00004096071,0.01016974,0.00004853913,0.00002799636,0.002087394,0.0002552235,0.000008083787,0.00007089337],"genre_scores_gemma":[0.9985293,0.000004980859,0.0009735426,0.000005666841,0.00006688212,0.0001773091,0.0001090147,0.0000188124,0.0001144802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0189677,"threshold_uncertainty_score":0.3889075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07411360301831732,"score_gpt":0.3738019129478066,"score_spread":0.2996883099294893,"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."}}