{"id":"W4406184320","doi":"10.21203/rs.3.rs-5709065/v1","title":"High-Accuracy De Novo Prediction for N- and O-linked Glycopeptides Across Multiple Fragmentation Techniques","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"","keywords":"Glycopeptide; Fragmentation (computing); Computer science; Computational biology; Chemistry; Biology; Programming language; Biochemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003658784,0.00222508,0.001234157,0.001319273,0.001052652,0.002331735,0.001759676,0.002134691,0.002025175],"category_scores_gemma":[0.005408038,0.001020192,0.001748055,0.001078424,0.0003832823,0.001704744,0.001611099,0.002542859,0.002552613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007878889,"about_ca_system_score_gemma":0.001344882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002150917,"about_ca_topic_score_gemma":0.003605011,"domain_scores_codex":[0.9985488,0.000245218,0.00007564502,0.0004984527,0.0005037846,0.0001281141],"domain_scores_gemma":[0.9960426,0.001370699,0.0004274402,0.0009850425,0.001011186,0.0001630293],"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":[0.002140451,0.0004823412,0.02047206,0.001003795,0.001245611,0.001274591,0.0002492005,0.06677666,0.5510399,0.002949714,0.01460735,0.3377583],"study_design_scores_gemma":[0.0001433547,0.0002224397,0.01428544,0.00007602535,0.0004494848,0.001625649,0.0001028331,0.6795906,0.2860514,0.008141292,0.009175876,0.000135691],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2015535,0.002234332,0.7762275,0.0004608665,0.0003170772,0.0001409108,0.003910786,0.01326649,0.001888585],"genre_scores_gemma":[0.3061951,0.0008995301,0.6759667,0.0001814864,0.00009626985,0.00009778355,0.01270275,0.001664975,0.00219544],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003658784,"threshold_uncertainty_score":0.01934975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04433325180429946,"score_gpt":0.4275734044071867,"score_spread":0.3832401526028872,"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."}}