{"id":"W4382501959","doi":"10.1002/pmic.202300011","title":"Leveraging transformers‐based language models in proteome bioinformatics","year":2023,"lang":"en","type":"review","venue":"PROTEOMICS","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Technology, Taiwan","keywords":"Computer science; Proteome; Proteomics; Artificial intelligence; Machine learning; Transformer; Bioinformatics; Computational biology; Data science; Biology; Engineering","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":[0.001338598,0.001201078,0.001196319,0.001309689,0.0002446451,0.00174296,0.001515021,0.001068949,0.002248186],"category_scores_gemma":[0.002379459,0.0004436443,0.001132224,0.001727713,0.000753374,0.003394407,0.001048785,0.002229609,0.002137191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009313005,"about_ca_system_score_gemma":0.001563029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001619224,"about_ca_topic_score_gemma":0.001259333,"domain_scores_codex":[0.9996014,0.0001158676,0.0000338937,0.00007825455,0.0001422398,0.00002839503],"domain_scores_gemma":[0.9989191,0.0007919236,0.00005044963,0.00005004757,0.000161616,0.00002678397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007401571,0.0001170584,0.0006655661,0.008589895,0.0002376911,0.0003833479,0.0001432452,0.03214216,0.004235718,0.1089142,0.02288691,0.8216103],"study_design_scores_gemma":[0.00003380053,0.000145531,0.0005410528,0.003340766,0.0002719343,0.001755466,0.0001149832,0.1199915,0.006100129,0.1815743,0.6859689,0.0001616859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002475256,0.805907,0.1752349,0.003838112,0.0009327181,0.00009048732,0.0004405659,0.0009590861,0.01012177],"genre_scores_gemma":[0.02270695,0.9153922,0.05567868,0.001398432,0.0007656381,0.0001194241,0.0007255465,0.0001298252,0.003083396],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.002248186,"threshold_uncertainty_score":0.007520974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04552720635235382,"score_gpt":0.3288887288577784,"score_spread":0.2833615225054246,"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."}}