# NeoPrecis: enhancing immunotherapy response prediction through integration of qualified immunogenicity and clonality-aware neoantigen landscapes

## TL;DR

NeoPrecis improves immunotherapy response prediction by integrating neoantigen immunogenicity and tumor clonality data.

## Contribution

Introduces NeoPrecis, a novel framework combining immunogenicity and clonality for better immunotherapy prediction.

## Key findings

- NeoPrecis reveals the influence of MHC molecules on TCR recognition beyond antigen presentation.
- Benefit HLA alleles show significant predictive power for patient outcomes in melanoma and NSCLC.
- Clonality-aware neoantigen landscapes improve prediction in heterogeneous tumors like NSCLC.

## Abstract

Despite the transformative impact of cancer immunotherapy, the need for improved patient stratification remains critical due to suboptimal response rates. While neoantigens are central to anti-tumor immunity, current metrics, such as tumor mutation burden (TMB), are limited by their neglect of immunogenicity and tumor heterogeneity. Here we present NeoPrecis, a computational framework designed to improve immunotherapy response prediction by refining neoantigen characterization across MHC-I and MHC-II pathways and by integrating tumor clonality information. NeoPrecis features an interpretable T-cell-recognition model that reveals the critical influence of MHC molecules on TCR recognition beyond mere antigen presentation. Benefit HLA alleles, identified through model-driven contribution analysis, exhibit significant predictive power for patient outcomes in immune checkpoint inhibitor treatment (melanoma: p-value = 0.04; NSCLC: p-value = 0.01). NeoPrecis, via its clonality-aware neoantigen landscape feature, improves immunotherapy response prediction in tumor types with varying prevalence of neoantigens, including heterogeneous NSCLC, which retains more subclonal neoantigens due to lower immunoediting pressure. We thus propose NeoPrecis as a comprehensive evaluative framework for neoantigen assessment by incorporating both immunogenicity and tumor clonality, offering insights into the link between the collective quality of neoantigen landscapes and immunotherapy response.

Response to immune therapy varies among cancer types and individual cancer patients; thus, predictive biomarkers of success are urgently needed. Here, the authors present a computational framework that integrates tumor clonality and neoantigen characterization data to predict patient outcomes upon immune checkpoint inhibitor treatment.