{"id":"W4406361493","doi":"10.1101/2025.01.13.632824","title":"Repertoire-level generation of T-cell epitopes with a large-scale generative transformer","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Epitope; T-cell receptor; Computational biology; Biology; CD8; T cell; Antigen; Genetics; Immune system","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":[0.0003406295,0.0004838777,0.0005047139,0.0001303775,0.0001398044,0.00007878283,0.0004010421,0.0005263184,0.00001181743],"category_scores_gemma":[0.00003261127,0.0004275578,0.0001849351,0.0001966223,0.00006724011,0.0000160358,0.0002026503,0.0003122793,0.000003026546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004329434,"about_ca_system_score_gemma":0.0006672721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002858819,"about_ca_topic_score_gemma":0.00001761477,"domain_scores_codex":[0.9980561,0.00007289551,0.0006048093,0.0006529187,0.0002352872,0.0003779762],"domain_scores_gemma":[0.9979609,0.000008300311,0.000382944,0.001040506,0.0005105499,0.00009682363],"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":[0.00007784703,0.0001367143,0.0006222194,0.0004376087,0.0002110087,0.000001444973,0.00005021102,0.0003405355,0.997498,0.0001003361,0.000519235,0.000004794523],"study_design_scores_gemma":[0.0008911171,0.0001661079,0.002026641,0.0001390606,0.0001282912,2.322951e-8,0.00002072234,0.002325892,0.9894277,2.794848e-7,0.004359375,0.0005147316],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624345,0.001359262,0.03397951,0.0001196485,0.0003119738,0.0007262122,0.0009441018,0.00003552496,0.00008930003],"genre_scores_gemma":[0.9651151,0.000868032,0.0330647,0.0002449007,0.0003140726,0.0001916336,0.00001419729,0.00005857129,0.0001287441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008070286,"threshold_uncertainty_score":0.9998176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01764176149687263,"score_gpt":0.2133503253281071,"score_spread":0.1957085638312345,"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."}}