The immunopeptidome can be used to directly discover and quantify all HLA-presented peptides on the cell surface. Comprehensive analysis of the cancer immunopeptidome will help researchers in accurately identifying distinct classes of tumor neoantigens with higher resolution and lower noise, which is crucial for the development of personalized cancer immunotherapy. MaNeo was trained on the comprehensive immunopeptidomics data for 531 samples across 14 cancer and 29 normal tissues, including 307,656 tumor peptides and 151,358 normal peptides. MaNeo integrated two machine learning-based classifiers, random forest (RF) and XGBoost, designed to achieve excellent performance and prioritize the neo-peptides. To help researchers apply the MaNeo model described here to tumors of interest, we developed this user-friendly immunogenic search engine, ISE, for neoantigen prioritization. ISE will serve as a guide for biologists interested in identifying the immunogenicity of candidate peptides.