Adoptive cell therapy has been proven a powerful approach for the cure of cancer and other diseases. In particular, the selection of appropriate immunogenic targets has been key to positive outcomes in clinical settings. The availability of RNA-Seq analysis, the accessibility to large data repositories such as TCGA and GTEx, and the creation of new bioinformatic tools have accelerated the process of neoantigen discovery. However, most of the current algorithms are encumbered by the intrinsic complexity of predicting antigen immunogenicity. Diamond™ is a novel artificial intelligence and cognitive machine and deep learning platform to predict peptide processing, HLA binding, and T cell activation. To validate the predictive value of DIAMOND algorithms, the meta-analyses of expression data of cancer-testis antigen New York Esophageal Squamous Cell Carcinoma 1 (NY-ESO-1) and predictions for the immunogenic peptides were compared to experimental data in the literature. In agreement with published clinical observations, DIAMOND metanalysis showed NY-ESO-1 genic overexpression in skin cutaneous melanoma, lung adenocarcinoma, and sarcoma. Moreover, DIAMOND predicted an MHC binding affinity of 0.289 with Supertype A2 for a new NY-ESO-1 peptide, which has been successfully targeted in clinical trials for patients with HLA-A*02:01, as well as it mirrored published data in its prediction of peptide affinity binding in NY-ESO-1–specific MHC II–restricted T cell receptors. Taken together these data support DIAMOND as a reliable platform for the discovery of new immunogenic targets for cancer therapy.

Citation Format: Lucia Piccotti, Leonardo Mirandola, Maurizio Chiriva-Internati. Identification of novel epitopes of NY-ESO-1 for solid malignancies by Kiromic proprietary search engine Diamond [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 243.