Toward the Explainability of Protein Language Models

TL;DR

This paper reviews the application of explainable AI techniques to protein language models, highlighting their potential to improve understanding, trust, and utility in protein research and design.

Contribution

It categorizes the workflow of protein AI modeling into four contexts, identifies five roles of explainability, and discusses future challenges and directions.

Findings

XAI can serve as Evaluator, Multitasker, Engineer, Coach, and Teacher in protein research.

The Evaluator role is the most widely adopted among these roles.

Future needs include benchmarks, open-source tools, visualizations, and wet-lab validation.

Abstract

Protein language models (pLMs) excel in a variety of tasks that range from structure prediction to the design of functional enzymes. However, these models operate as black boxes, and their underlying working principles remain unclear. Here, we survey emerging applications of explainable artificial intelligence (XAI) to pLMs and describe the potential of XAI in protein research. We divide the workflow of protein AI modeling into four information contexts: (i) training sequences, (ii) input prompt, (iii) model architecture, and (iv) input-output pairs. For each, we describe existing methods and applications of XAI. Additionally, from published studies we distil five (potential) roles that XAI can play in protein research: Evaluator, Multitasker, Engineer, Coach, and Teacher, with the Evaluator role being the only one widely adopted so far. These roles aim to help both protein scientists and model developers understand the possibilities and limitations of implementing XAI for predictive and generative tasks. While our analysis focuses on pLMs, both this categorization and roles are broadly applicable to any other model architectures. We conclude by highlighting critical areas of application for the future, including risks related to security, trustworthiness, and bias, and we call for community benchmarks, open-source tooling, domain-specific visualizations, and wet-lab characterization to advance the interpretability of protein AI.