{"id":"W4281665783","doi":"10.3389/fgene.2022.885929","title":"ProtTrans-Glutar: Incorporating Features From Pre-trained Transformer-Based Models for Predicting Glutarylation Sites","year":2022,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Direktorat Jenderal Pendidikan Tinggi; University of Tokyo; Institute of Medical Science, University of Tokyo; Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi; Research Organization of Information and Systems","keywords":"Recall; Computer science; Artificial intelligence; Transformer; Machine learning; Random forest; Pattern recognition (psychology); Feature (linguistics); Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003773027,0.00023458,0.0002224177,0.0001212455,0.0002823685,0.00003661633,0.000330814,0.0001584279,0.0000103213],"category_scores_gemma":[0.00007017595,0.0002653082,0.0001193982,0.0001693056,0.00006156072,0.00001125502,0.00005195873,0.0002939336,1.641052e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006598796,"about_ca_system_score_gemma":0.0001551291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003383746,"about_ca_topic_score_gemma":0.00006899174,"domain_scores_codex":[0.9984441,0.0001110055,0.0004629399,0.0003658833,0.0002846897,0.0003313491],"domain_scores_gemma":[0.9993421,0.00003282535,0.0001996366,0.0003044594,0.00005557816,0.00006538243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004650891,0.00008374607,0.07945973,0.0001022271,0.00006737295,0.000001077101,0.001337927,0.8713886,0.03817956,0.0000252982,0.001657833,0.007231598],"study_design_scores_gemma":[0.001835217,0.0006742924,0.003844343,0.00001965502,0.00004753388,0.000002749239,0.0005651573,0.9659612,0.02091879,0.002567026,0.003179323,0.000384757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5009077,0.0009552932,0.4958308,0.0001414372,0.0003203782,0.001168566,0.0004014223,0.00003674704,0.0002377356],"genre_scores_gemma":[0.730542,0.00001887217,0.266588,0.0002015367,0.0001422523,0.0002968533,0.002102957,0.00004275317,0.00006480546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2296343,"threshold_uncertainty_score":0.9999799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00852542584177125,"score_gpt":0.2360370169068716,"score_spread":0.2275115910651004,"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."}}