{"id":"W4293518025","doi":"10.1109/cibcb55180.2022.9863051","title":"Predicting the specific substrate for transmembrane transport proteins using BERT language model","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"UniProt; Computer science; Classifier (UML); Artificial intelligence; Transmembrane protein; Language model; Machine learning; Chemistry; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003811544,0.0001265359,0.00009796826,0.0000225598,0.0003783705,0.00001606631,0.0002637756,0.00004858274,0.00007394445],"category_scores_gemma":[0.000009815936,0.00009730958,0.00011273,0.00007039251,0.00003825757,0.000003867463,0.00003801899,0.0001765934,6.224323e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001433806,"about_ca_system_score_gemma":0.00006801334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003667327,"about_ca_topic_score_gemma":0.00003597025,"domain_scores_codex":[0.9991519,0.00003275369,0.0002334672,0.0001847151,0.000164816,0.0002322847],"domain_scores_gemma":[0.9995686,0.00001117832,0.00007383576,0.0002856119,0.00002500514,0.00003576003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001981516,0.00006734897,0.00180513,0.00009734913,0.00006265228,0.000002143289,0.002576328,0.4622047,0.5316782,0.0004375071,0.0002782227,0.000592222],"study_design_scores_gemma":[0.0008753429,0.0002561063,0.0002812726,0.000005954764,0.00003804419,0.00005230947,0.001719308,0.8970367,0.08720378,0.00004268013,0.01220508,0.0002834468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8518416,0.0001414049,0.1442881,0.0001996336,0.00006258774,0.0006797852,0.00009075682,0.00003050486,0.002665679],"genre_scores_gemma":[0.9841632,0.00001017884,0.01352151,0.0002671767,0.000110911,0.000114659,0.0002447774,0.00003008254,0.001537526],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4444745,"threshold_uncertainty_score":0.3968169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01587198441246351,"score_gpt":0.2557313749277768,"score_spread":0.2398593905153133,"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."}}