期刊
NATURE BIOTECHNOLOGY
卷 37, 期 11, 页码 1332-+出版社
NATURE PORTFOLIO
DOI: 10.1038/s41587-019-0280-2
关键词
-
资金
- National Institutes of Health (NIH) [U01 CA194389]
- NIH [K08 CA207882, GM 102365]
- NIH/Stanford MSTP training grant
- NSF GSF
- American Society of Hematology Scholar Award
- V-Foundation
- Damon Runyon-Rachleff Innovation Award
- W.M. Keck Foundation Medical Research Grant
- Conquer Cancer Foundation Young Investigator Award
- Leukemia and Lymphoma Society
- Knut and Alice Wallenberg Foundation
- PD Soros New American Fellowship
- Stanford Bio-X Fellowship
- Virginia and D.K. Ludwig Fund for Cancer Research
- Bakewell Foundation
- SDW/DT Foundation
- Shanahan Family Foundation
- National Science Foundation Major Research Instrumentation program [ACI-1429830]
- NIH S10 Shared Instrument Grant [S10RR027431-01]
Accurate prediction of antigen presentation by human leukocyte antigen (HLA) class II molecules would be valuable for vaccine development and cancer immunotherapies. Current computational methods trained on in vitro binding data are limited by insufficient training data and algorithmic constraints. Here we describe MARIA (major histocompatibility complex analysis with recurrent integrated architecture; https://maria.stanford.edu/), a multimodal recurrent neural network for predicting the likelihood of antigen presentation from a gene of interest in the context of specific HLA class II alleles. In addition to in vitro binding measurements, MARIA is trained on peptide HLA ligand sequences identified by mass spectrometry, expression levels of antigen genes and protease cleavage signatures. Because it leverages these diverse training data and our improved machine learning framework, MARIA (area under the curve = 0.89-0.92) outperformed existing methods in validation datasets. Across independent cancer neoantigen studies, peptides with high MARIA scores are more likely to elicit strong CD4(+) T cell responses. MARIA allows identification of immunogenic epitopes in diverse cancers and autoimmune disease.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据