Deep learning using tumor HLA peptide mass spectrometry datasets improves neoantigen identification.

Deep learning using tumor HLA peptide mass spectrometry datasets improves neoantigen identification.

Nature biotechnology (2018-12-18)

Brendan Bulik-Sullivan, Jennifer Busby, Christine D Palmer, Matthew J Davis, Tyler Murphy, Andrew Clark, Michele Busby, Fujiko Duke, Aaron Yang, Lauren Young, Noelle C Ojo, Kamilah Caldwell, Jesse Abhyankar, Thomas Boucher, Meghan G Hart, Vladimir Makarov, Vincent Thomas De Montpreville, Olaf Mercier, Timothy A Chan, Giorgio Scagliotti, Paolo Bironzo, Silvia Novello, Niki Karachaliou, Rafael Rosell, Ian Anderson, Nashat Gabrail, John Hrom, Chainarong Limvarapuss, Karin Choquette, Alexander Spira, Raphael Rousseau, Cynthia Voong, Naiyer A Rizvi, Elie Fadel, Mark Frattini, Karin Jooss, Mojca Skoberne, Joshua Francis, Roman Yelensky

PMID30556813

摘要

Neoantigens, which are expressed on tumor cells, are one of the main targets of an effective antitumor T-cell response. Cancer immunotherapies to target neoantigens are of growing interest and are in early human trials, but methods to identify neoantigens either require invasive or difficult-to-obtain clinical specimens, require the screening of hundreds to thousands of synthetic peptides or tandem minigenes, or are only relevant to specific human leukocyte antigen (HLA) alleles. We apply deep learning to a large (N = 74 patients) HLA peptide and genomic dataset from various human tumors to create a computational model of antigen presentation for neoantigen prediction. We show that our model, named EDGE, increases the positive predictive value of HLA antigen prediction by up to ninefold. We apply EDGE to enable identification of neoantigens and neoantigen-reactive T cells using routine clinical specimens and small numbers of synthetic peptides for most common HLA alleles. EDGE could enable an improved ability to develop neoantigen-targeted immunotherapies for cancer patients.