Abstract The ongoing COVID-19 pandemic has created an urgency to identify novel vaccine targets for protective immunity against SARS-CoV-2. Consistent with observations for the closely related SARS-CoV, early reports identify a protective role for both humoral and cell-mediated immunity for SARS-CoV-2. In this study, we leveraged our bioinformatics binding prediction tools for human leukocyte antigen (HLA)-I and HLA-II alleles that cover nearly the entire population and were developed using mass spectrometry-based profiling of 74 individual HLA-I and 83 individual HLA-II alleles. We applied these binding predictors, initially developed to predict tumor neoantigen presentation, to identify T-cell epitopes from SARS-CoV-2 proteins. To determine the ability of our tools to identify viral T-cell epitopes, we validated HLA-I and HLA-II predictions on Coronaviridae family epitopes deposited in the Virus Pathogen Database and Analysis Resource (ViPR) database. We then applied our HLA-I and HLA-II predictors to 13 open reading frames (ORFs) of SARS-CoV-2 and identified 11,897 HLA-I and 8,046 HLA-II candidate peptides that were highly ranked for binding. From our SARS-CoV-2 predicted peptide-HLA-I allele pairs, 374 pairs identically matched previously reported pairs in the ViPR database, originating from other coronaviruses with homologous sequences. Of these pairs, 333 (89 %) had a positive HLA-binding assay result, reinforcing the validity of our predictions. Furthermore, we assayed a subset of epitopes with highly predicted binding scores for their ability to be recognized by specific CD8+ T cell in human donor PBMCs. These epitopes were chosen from four structural proteins (S, N, M, E) and one nonstructural protein (ORF1ab) from SARS-CoV-2, and epitopes from all five proteins were found to be immunogenic. Finally, it was important to address the expression of SARS-CoV-2 proteins within cells since their subsequent processing is necessary for MHC presentation and the generation of specific epitopes. We utilized publicly available proteomic data to infer the relative expression of SARS-CoV-2 proteins from infected cell lines and determined that the different proteins vary significantly in their expression levels, with the nucleocapsid being the most highly expressed viral protein across these studies. Our predictions identify few epitopes from each SARS-CoV-2 protein, which are predicted to bind multiple HLA-I or HLA-II alleles, potentially covering over 99% of the USA, European, and Asian populations. Finally, using our bioinformatic platform, we identify multiple putative epitopes that are potential targets for CD4+ and CD8+ T cells whose predicted HLA binding properties cover nearly the entire population. We further propose that when considering the protein expression levels of these epitopes and their ability to elicit a T-cell response, these epitopes may be effective when included in vaccines against SARS-CoV-2 to induce broad cellular immunity. Citation Format: Asaf Poran, Dewi Harjanto, Matt Malloy, Christina M. Arieta, Daniel A. Rothenberg, Divya Lenkala, Marit M. van Buuren, Terri A. Addona, Michael S. Rooney, Lakshmi Srinivasan, Richard B. Gaynor. Sequence-based prediction of SARS-CoV-2 vaccine targets using a mass spectrometry-based bioinformatics predictor identifies immunogenic T-cell epitopes [abstract]. In: Proceedings of the AACR Virtual Meeting: COVID-19 and Cancer; 2020 Jul 20-22. Philadelphia (PA): AACR; Clin Cancer Res 2020;26(18_Suppl):Abstract nr S03-02.