Search bioRxivSearch

Biology subjects

O'Donnell, T.

Publications and source records attributed to O'Donnell, T..

2 recordsLinked to original sources

MHCflurry: open-source class I MHC binding affinity prediction

Machine learning prediction of the interaction between major histocompatibility complex I (MHC I) proteins and their small peptide ligands is important for vaccine design and other applications in adaptive immunity. We describe and benchmark a new open-source MHC I binding prediction package, MHCflurry. The software is a collection of allele-specific binding predictors incorporating a novel neural network architecture and adhering to software development best practices. MHCflurry outperformed the standard predictors NetMHC 4.0 and NetMHCpan 3.0 on a benchmark of mass spec-identified MHC ligands and showed competitive accuracy on a benchmark of affinity measurements. The accuracy improvement was due to substantially better prediction of non-9-mer peptide ligands, which offset a narrowly lower accuracy on 9-mers. MHCflurry was on average 8.6X faster than NetMHC and 44X faster than NetMHCpan; performance is further increased when a graphics processing unit (GPU) is available. MHCflurry is freely available to use, retrain, or extend, includes Python library and command line interfaces, and may be installed using standard package managers.

immunology

Chemotherapy weakly contributes to predicted neoantigen expression in ovarian cancer

BackgroundPatients with highly mutated tumors, such as melanoma or smoking-related lung cancer, have higher rates of response to immune checkpoint blockade therapy, perhaps due to increased neoantigen expression. Many chemotherapies including platinum compounds are known to be mutagenic, but the impact of standard treatment protocols on mutational burden and resulting neoantigen expression in most human cancers is unknown.\n\nMethodsWe sought to quantify the effect of chemotherapy treatment on computationally predicted neoantigen expression for 12 high grade serous ovarian carcinoma (HGSC) patients with pre- and post-chemotherapy samples collected in the Australian Ovarian Cancer Study. We additionally analyzed 16 patients from the cohort with post-treatment samples only, including five primary surgical samples exposed to neoadjuvant chemotherapy. Our approach integrates tumor whole genome and RNA sequencing with class I MHC binding prediction and mutational signatures of chemotherapy exposure extracted from two preclinical studies.\n\nResultsThe mutational signatures for cisplatin and cyclophosphamide identified in a preclinical model had significant but inexact associations with the relevant exposure in the clinical samples. In an analysis stratified by tissue type (solid tumor or ascites), relapse samples collected after chemotherapy harbored a median of 90% more expressed neoantigens than untreated primary samples, a figure that combines the effects of chemotherapy and other mutagenic processes operative during relapse. Neoadjuvant-treated primary samples showed no detectable increase over untreated samples. The contribution from chemotherapy-associated signatures was small, accounting for a mean of 5% (range 0-16) of the expressed neoantigen burden in relapse samples. In both treated and untreated samples, most neoantigens were attributed to COSMIC Signature (3), associated with BRCA disruption, Signature (1), associated with a slow mutagenic process active in healthy tissue, and Signature (8), of unknown etiology.\n\nConclusionRelapsed HGSC tumors harbor nearly double the predicted expressed neoantigen burden of primary samples, but mutations associated with chemotherapy signatures account for only a small part of this increase. The mutagenic processes responsible for most neoantigens are similar between primary and relapse samples. Our analyses are based on mutations detectable from whole genome sequencing of bulk samples and do not account for neoantigens present in small populations of cells.

cancer biology