Abstract: The present invention includes methods of identifying a patient who will likely be responsive to treatment with a protein arginine N-methyltransferase 5 inhibitor, or a pharmaceutically acceptable salt thereof, and methods of treating the same.

Abstract: The invention relates to (i) an angiogenesis gene signature and (ii) a monocytic myeloid-derived suppressor cell (mMDSC) gene signature that are each predictive of patient response to treatment with a PD-1 antagonist, wherein the angiogenesis signature comprises five or more genes. More specifically, a lower angiogenesis score is associated with favorable response to a PD-1 antagonist in a patient with cancer. Similarly, a lower mMDSC score is associated with favorable response to a PD-1 antagonist in a patient with cancer. Also provided are methods of treating a cancer patient with a PD-1 antagonist that were identified as either (i) positive for the angiogenesis gene signature biomarker of the invention or (ii) positive for the mMDSC gene signature biomarker of the invention.

Abstract: The invention relates to a stromal/EMT/TGF? signature that is predictive of patient response to treatment with a PD-1 antagonist, wherein the stromal/EMT/TGF? signature comprises five or more genes selected from Table 1 disclosed herein. More specifically, a lower stromal/EMT/TGF-? score is associated with favorable response to a PD-1 antagonist in a patient with cancer. Also provided are methods of treating a cancer patient with a PD-1 antagonist that were identified as positive for the stromal/EMT/TGF? biomarker of the invention. The disclosure also provides methods and kits for testing tumor samples for the biomarkers.

Abstract: An immunogenic neoantigen peptide can be identified by receiving data characterizing a neoantigen peptide from a subject. Thereafter, a naturally processed (NP) antigen predictor (NP-predictor) score can be generated using a machine learning model trained using data derived from mass spectrometry of isolated peptides eluted from at least one major histocompatibility complex (MHC) molecule. A T-epitope predictor score can be generated independently using a second machine learning model trained using experimentally characterized peptides recognized by T-cells. Additionally, a MHC binding score can be generated using a third machine learning model. The scores generated by the machine learning models can be incorporated into a composite score for each neoantigen peptide based on each of the NP-predictor score, the T-epitope predictor score, and the MHC binding score, wherein the composite score identifies one or more immunogenic neoantigen peptides.