{"id":"W2942383137","doi":"10.1101/620468","title":"Personalized deep learning of individual immunopeptidomes to identify neoantigens for cancer vaccines","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Workflow; Identification (biology); Human leukocyte antigen; Computational biology; Cancer immunotherapy; Computer science; Cancer; Immunotherapy; Medicine; Antigen; Immunology; Biology; Database; Internal medicine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005867211,0.0005171023,0.0006835526,0.0002001659,0.0001343223,0.0001688292,0.0008364789,0.0005231317,0.00003217977],"category_scores_gemma":[0.0002493269,0.0005273944,0.0003472559,0.0002066288,0.00004294812,0.00001481015,0.0009632189,0.0003457335,0.00001403354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004765118,"about_ca_system_score_gemma":0.000433465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004749689,"about_ca_topic_score_gemma":0.000003173141,"domain_scores_codex":[0.997782,0.0000666309,0.0006787333,0.0006730698,0.0002842835,0.0005152697],"domain_scores_gemma":[0.9976756,0.00002988956,0.0005981199,0.000908788,0.0006554984,0.0001321258],"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":[0.0001735368,0.00006632604,0.008224984,0.0008910244,0.0007485296,6.144845e-7,0.0000832701,0.001527925,0.9876277,0.0000862308,0.0005444891,0.00002532968],"study_design_scores_gemma":[0.001978579,0.0004064289,0.1213113,0.0004906263,0.0003969608,4.153169e-8,0.0001140669,0.0009987729,0.8343283,0.000001185212,0.03866904,0.001304735],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9847317,0.007728821,0.004885356,0.00009796453,0.0008342004,0.001295729,0.0003751871,0.00004515072,0.000005876792],"genre_scores_gemma":[0.9913691,0.001461562,0.005966887,0.0001521204,0.0004061602,0.0004307738,0.00001133059,0.0001359768,0.00006607462],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1532995,"threshold_uncertainty_score":0.9997178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01681622067429637,"score_gpt":0.2619885452418447,"score_spread":0.2451723245675483,"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."}}