Data-driven design of targeted gene panels for estimating immunotherapy biomarkers

Abstract

We introduce a novel data-driven framework for the design of targeted gene panels for estimating exome-wide biomarkers in cancer immunotherapy. Our first goal is to develop a generative model for the profile of mutation across the exome, which allows for gene- and variant type-dependent mutation rates. Based on this model, we then propose a new procedure for estimating biomarkers such as Tumour Mutation Burden and Tumour Indel Burden. Our approach allows the practitioner to select a targeted gene panel of a prespecified size, and then construct an estimator that only depends on the selected genes. Alternatively, the practitioner may apply our method to make predictions based on an existing gene panel, or to augment a gene panel to a given size. We demonstrate the excellent performance of our proposal using an annotated mutation dataset from 1144 Non-Small Cell Lung Cancer patients.

Data-driven design of targeted gene panels for estimating immunotherapy biomarkers

“…Using the Non-Small Cell Lung Cancer dataset from Campbell et al (2016), we have demonstrated the excellent predictive performance of our proposal for estimating Tumour Mutation Burden and Tumour Indel Burden, and shown that it outperforms the state-of-the-art procedures. Our framework can be applied to any tumour dataset containing annotated mutations, and we provide an R package (Bradley and Cannings, 2021) which implements the methodology.…”

“…Experimental results are given in Section 3 and we conclude in Section 4. Finally, we also provide an R package ICBioMark (Bradley and Cannings, 2021) which implements the methodology and reproduces the experimental results in the paper.…”