Driving Accurate Allergen Prediction with Protein Language Models and Generalization-Focused Evaluation

TL;DR

This paper introduces Applm, a new allergen prediction framework using large protein language models, which outperforms existing methods in challenging real-world scenarios and emphasizes generalization and mutation analysis.

Contribution

The paper presents Applm, a novel allergen prediction method leveraging a 100-billion parameter protein language model, with a focus on challenging real-world tasks and generalization.

Findings

Applm outperforms seven state-of-the-art methods across diverse tasks.

xTrimoPGLM captures general protein features crucial for allergen prediction.

The framework effectively identifies novel allergens and assesses mutation impacts.

Abstract

Allergens, typically proteins capable of triggering adverse immune responses, represent a significant public health challenge. To accurately identify allergen proteins, we introduce Applm (Allergen Prediction with Protein Language Models), a computational framework that leverages the 100-billion parameter xTrimoPGLM protein language model. We show that Applm consistently outperforms seven state-of-the-art methods in a diverse set of tasks that closely resemble difficult real-world scenarios. These include identifying novel allergens that lack similar examples in the training set, differentiating between allergens and non-allergens among homologs with high sequence similarity, and assessing functional consequences of mutations that create few changes to the protein sequences. Our analysis confirms that xTrimoPGLM, originally trained on one trillion tokens to capture general protein sequence characteristics, is crucial for Applm's performance by detecting important differences among protein sequences. In addition to providing Applm as open-source software, we also provide our carefully curated benchmark datasets to facilitate future research.