Aligning Proteins and Language: A Foundation Model for Protein Retrieval

TL;DR

This paper introduces a multimodal foundation model that aligns 3D protein structures with functional annotations, enabling effective retrieval of similar proteins and advancing structure-function understanding in biology.

Contribution

It presents a CLIP-style contrastive learning framework trained on a large-scale protein-caption dataset for structure-function protein retrieval.

Findings

Promising zero-shot retrieval performance on PDB and EMDB datasets.

Effective cross-database protein retrieval using the model.

Demonstrates potential of multimodal models in protein biology.

Abstract

This paper aims to retrieve proteins with similar structures and semantics from large-scale protein dataset, facilitating the functional interpretation of protein structures derived by structural determination methods like cryo-Electron Microscopy (cryo-EM). Motivated by the recent progress of vision-language models (VLMs), we propose a CLIP-style framework for aligning 3D protein structures with functional annotations using contrastive learning. For model training, we propose a large-scale dataset of approximately 200,000 protein-caption pairs with rich functional descriptors. We evaluate our model in both in-domain and more challenging cross-database retrieval on Protein Data Bank (PDB) and Electron Microscopy Data Bank (EMDB) dataset, respectively. In both cases, our approach demonstrates promising zero-shot retrieval performance, highlighting the potential of multimodal foundation models for structure-function understanding in protein biology.