E1: Retrieval-Augmented Protein Encoder Models
Sarthak Jain, Joel Beazer, Jeffrey A. Ruffolo, Aadyot Bhatnagar, Ali Madani
The paper introduces Profluent-E1, retrieval-augmented protein language models that improve performance by conditioning on homologous sequences, achieving state-of-the-art results in fitness prediction and contact-map prediction.
bioRxiv · Nov 12, 2025 · PreprintSynthetic Biology