{"id":"W3119864298","doi":"10.1016/j.compbiomed.2021.104212","title":"Incorporating a transfer learning technique with amino acid embeddings to efficiently predict N-linked glycosylation sites in ion channels","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Technology, Taiwan","keywords":"Glycosylation; Hyperparameter; Chemistry; Amino acid; Computer science; Embedding; Computational biology; Artificial intelligence; Biological system; Biochemistry; Biology","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":[0.0004752402,0.0001510404,0.0002316981,0.0001610444,0.0000570144,0.000007965758,0.00009045496,0.0001918461,0.000004333575],"category_scores_gemma":[0.0002223049,0.000122496,0.0000154694,0.0002693927,0.000125638,0.000005409598,0.00008613764,0.0002792187,6.962717e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001861609,"about_ca_system_score_gemma":0.00003584951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000147852,"about_ca_topic_score_gemma":0.0000529542,"domain_scores_codex":[0.9990103,0.0001322764,0.0002858776,0.0003036128,0.00006437352,0.0002035282],"domain_scores_gemma":[0.9996473,0.00004914724,0.00005602562,0.0001277277,0.00005648522,0.00006336981],"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":[0.0002432008,0.00004963706,0.2035927,0.000100226,0.00002375366,0.00002728938,0.001669917,0.008702463,0.7778665,0.0004108615,0.00005728628,0.007256213],"study_design_scores_gemma":[0.01876294,0.02087362,0.1860739,0.004762667,0.0001083611,0.001231982,0.00249491,0.2550029,0.4953275,0.001345379,0.01167358,0.00234224],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8071294,0.0002202701,0.1916275,0.0004459211,0.0001139525,0.0002396933,0.000001101866,0.00001772407,0.0002044318],"genre_scores_gemma":[0.9848069,0.00005568661,0.01414139,0.0005061643,0.000150441,0.00002851769,0.0002752017,0.00001053038,0.00002519213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.282539,"threshold_uncertainty_score":0.499524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007960776197928825,"score_gpt":0.2747291888283461,"score_spread":0.2667684126304173,"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."}}