SOURCE-LINKED INTELLIGENCE

Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Recently, there has been a growing adoption of protein language models (PLMs) in biomedical science. Their embeddings provide a rich numerical representation of protein sequences which achieve state-of-the-art performance on several downstream tasks including protein fitness prediction. However, PLM embeddings are not directly interpretable and, thereby, it remains unclear what features they encode. To gain insight into which biochemical properties of the protein are driving the prediction, we leverage an orthogonal projection technique that removes linear effects of known tabular features fro

Read original source ↗ Open in workspace

recordType

paper

region

Global