PLM-eXplain: Divide and Conquer the Protein Embedding Space
This addresses the problem of limited biological interpretation for researchers in computational biology, offering an incremental solution to enhance PLM interpretability.
The authors tackled the lack of interpretability in protein language models (PLMs) by developing PLM-eXplain (PLM-X), an explainable adapter layer that factors PLM embeddings into interpretable and residual components, maintaining high performance across three protein classification tasks.
Protein language models (PLMs) have revolutionised computational biology through their ability to generate powerful sequence representations for diverse prediction tasks. However, their black-box nature limits biological interpretation and translation to actionable insights. We present an explainable adapter layer - PLM-eXplain (PLM-X), that bridges this gap by factoring PLM embeddings into two components: an interpretable subspace based on established biochemical features, and a residual subspace that preserves the model's predictive power. Using embeddings from ESM2, our adapter incorporates well-established properties, including secondary structure and hydropathy while maintaining high performance. We demonstrate the effectiveness of our approach across three protein-level classification tasks: prediction of extracellular vesicle association, identification of transmembrane helices, and prediction of aggregation propensity. PLM-X enables biological interpretation of model decisions without sacrificing accuracy, offering a generalisable solution for enhancing PLM interpretability across various downstream applications. This work addresses a critical need in computational biology by providing a bridge between powerful deep learning models and actionable biological insights.