# CNNeoPP: a large language model-enhanced deep learning pipeline for personalized neoantigen prediction and liquid biopsy applications

## TL;DR

This paper introduces CNNeoPP, a deep learning pipeline enhanced by large language models to improve neoantigen prediction for cancer immunotherapy and non-invasive tumor monitoring.

## Contribution

The novel CNNeo model and CNNeoPP pipeline use large language model-derived features to enhance neoantigen prediction accuracy and enable non-invasive detection.

## Key findings

- CNNeoPP outperforms existing tools in neoantigen prediction when validated with independent datasets and experimental assays.
- Plasma cell-free DNA can be used for non-invasive neoantigen prediction, with detectability improved by higher sequencing depth and prioritization strategies.
- CNNeoDB was created as a public database compiling neoantigen data from multiple sources.

## Abstract

Neoantigens have emerged as promising targets for personalized cancer immunotherapy. However, accurate identification of immunogenic neoantigens remains a challenge due to limitations in existing predictive models. Here, we present CNNeo, a novel deep learning-based neoantigen prediction model, and CNNeoPP, an integrated computational pipeline for neoantigen discovery. CNNeo employs large language model-derived sequence representations and multi-modal feature integration, demonstrating superior predictive performance compared to existing tools. CNNeoPP was rigorously validated using independent datasets, including the TESLA dataset, and experimental validation via ELISpot T-cell assays. Additionally, we conducted a proof-of-concept study utilizing plasma cell-free DNA to explore the feasibility of non-invasive neoantigen prediction. We found that increased sequencing depth enhances neoantigen detectability, further amplified by the prioritization strategy of CNNeoPP. CNNeoDB, a publicly accessible database was developed compiling neoantigen data from multiple sources. This study establishes robust tools for neoantigen prediction, with implications for optimizing cancer immunotherapy and liquid biopsy-based tumor monitoring. CNNeoPP is available at https://github.com/AaronChen007/neoantigen.