{"id":"W4283644199","doi":"10.1039/d1sc05681f","title":"GlyNet: a multi-task neural network for predicting protein–glycan interactions","year":2022,"lang":"en","type":"article","venue":"Chemical Science","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Glycomics Network; Alberta Innovates; Canada Foundation for Innovation; Compute Canada","keywords":"Glycan; Task (project management); Artificial neural network; Computer science; Artificial intelligence; Computational biology; Chemistry; Biology; Engineering; Biochemistry; Systems engineering; Glycoprotein","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":[0.0004045679,0.00008631207,0.00007098959,0.00003498305,0.000620364,0.00004925557,0.0004514274,0.00002797907,0.00007858384],"category_scores_gemma":[0.0003877083,0.0000841883,0.00006301657,0.0003886043,0.0002225572,0.000009329691,0.0004613507,0.0001804999,0.000003214855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006178673,"about_ca_system_score_gemma":0.0001476831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002394154,"about_ca_topic_score_gemma":0.00001180411,"domain_scores_codex":[0.9986939,0.00002722195,0.000143836,0.0004160689,0.0002942668,0.0004246388],"domain_scores_gemma":[0.99945,0.0000160801,0.00005312437,0.0002327122,0.0001029335,0.0001451378],"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":[0.00007348345,0.0000645867,0.0004974029,0.00000533431,0.000003657288,6.891983e-7,0.00002704686,0.0006630886,0.9952152,0.00005044128,0.0008806092,0.0025185],"study_design_scores_gemma":[0.0008205996,0.000366373,0.0004897745,0.000008044108,0.000004527043,0.00003219243,0.0001229936,0.06485159,0.8091167,0.0001014538,0.1238514,0.000234354],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954375,0.0000707547,0.002656966,0.0004501896,0.0001714733,0.0006444102,0.00003385242,0.00002380166,0.0005110206],"genre_scores_gemma":[0.994216,8.602881e-7,0.003729333,0.0001880394,0.000244429,0.000530633,0.00006117613,0.00001059357,0.001018978],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1860984,"threshold_uncertainty_score":0.4771401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02377617892430973,"score_gpt":0.3161801546644267,"score_spread":0.292403975740117,"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."}}