Mutant RIT1 cooperates with YAP to drive an EMT-like lung cancer state.

The discovery of oncogene addiction in cancer has led to the development of over a dozen FDA-approved biomarker-driven therapies in lung adenocarcinoma. Somatic mutations of the "Ras-like in all tissues" (RIT1) gene are non-canonical driver events in lung cancer, occurring in ~2% of lung adenocarcinomas in a mutually exclusive fashion with and mutations. Patients with -mutant lung cancer lack targeted therapy treatment options, and a lack of pre-clinical models has hindered the development of therapeutic strategies for -mutant lung cancer.

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

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.