{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007158589,0.0005876785,0.001028874,0.0004090977,0.00007430635,0.00008259767,0.0005821755,0.0006745518,0.000008811672],"category_scores_gemma":[0.0001576185,0.0005294508,0.000418569,0.0004587455,0.00006572377,0.0000150566,0.0001701427,0.000771036,0.0001110747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001088086,"about_ca_system_score_gemma":0.0005711853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002804347,"about_ca_topic_score_gemma":0.00001945577,"domain_scores_codex":[0.9975325,0.0001107042,0.001121601,0.0003773493,0.0002747674,0.0005830597],"domain_scores_gemma":[0.9987628,0.00003398225,0.000468051,0.0005854087,0.00004249544,0.0001072699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004573519,0.0001145399,0.00001261521,0.1007651,0.000297704,0.00003102858,0.001511043,0.00709421,0.00009799121,0.00008390979,0.000484947,0.8894612],"study_design_scores_gemma":[0.00160639,0.0003227558,0.000001504422,0.01538149,0.0003020005,0.00008006599,0.0003936384,0.1785878,0.0005554095,0.0001220485,0.8004369,0.002210025],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002403384,0.9100832,0.07891382,0.00004331995,0.0003185003,0.006528598,0.0002023712,0.000197171,0.003472697],"genre_scores_gemma":[0.00001998075,0.9553931,0.04118363,0.0001046829,0.0002068154,0.0008102948,0.001570126,0.0001875641,0.0005238038],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8872511,"threshold_uncertainty_score":0.9997157,"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."}}