PLM-eXplain: Divide and Conquer the Protein Embedding Space
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912319221530624 |
|---|---|
| author | van Eck, Jan Gogishvili, Dea Silva, Wilson Abeln, Sanne |
| author_facet | van Eck, Jan Gogishvili, Dea Silva, Wilson Abeln, Sanne |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07156 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PLM-eXplain: Divide and Conquer the Protein Embedding Space van Eck, Jan Gogishvili, Dea Silva, Wilson Abeln, Sanne Biomolecules Artificial Intelligence Machine Learning 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. |
| title | PLM-eXplain: Divide and Conquer the Protein Embedding Space |
| topic | Biomolecules Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.07156 |