{"id":"W3104435397","doi":"10.1038/s42256-020-00260-4","title":"Personalized deep learning of individual immunopeptidomes to identify neoantigens for cancer vaccines","year":2020,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Workflow; Cancer immunotherapy; Identification (biology); Computational biology; Immunotherapy; Human leukocyte antigen; Personalized medicine; Cancer; Medicine; Deep learning; Computer science; Artificial intelligence; Bioinformatics; Antigen; Immunology; Biology; Internal medicine; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000196276,0.0002072816,0.0002633628,0.00005304014,0.00009212383,0.0000440125,0.0005281001,0.0002144068,0.0000693988],"category_scores_gemma":[0.0004502848,0.0001776276,0.0001731926,0.0002128526,0.00002592645,0.000009250411,0.0002423837,0.0003102056,0.000006407585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007079866,"about_ca_system_score_gemma":0.00004873811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002453984,"about_ca_topic_score_gemma":0.00001620012,"domain_scores_codex":[0.9989019,0.00002742361,0.0003647104,0.0002822987,0.0001811972,0.0002424755],"domain_scores_gemma":[0.9993185,0.00003168369,0.0001614036,0.0001871334,0.0002085838,0.00009270191],"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":[0.001450583,0.0001124842,0.009139496,0.0005980392,0.0008131241,0.000001710909,0.006239245,0.007446974,0.7871735,0.001722166,0.00348534,0.1818173],"study_design_scores_gemma":[0.0007701647,0.001185403,0.006593565,0.00007534045,0.0001334666,0.00001344556,0.001823806,0.009503007,0.8277786,0.0001155837,0.1513477,0.0006599111],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7824171,0.0408789,0.1719896,0.002493485,0.0004595947,0.001120527,0.0002082503,0.0000467737,0.0003858068],"genre_scores_gemma":[0.9926748,0.0008657579,0.004589235,0.001154811,0.0002313181,0.00005200909,0.0002085585,0.0000302561,0.000193205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2102578,"threshold_uncertainty_score":0.7243442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01702715128458461,"score_gpt":0.316839999424933,"score_spread":0.2998128481403484,"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."}}