Integrating Structure and Sequence: Protein Graph Embeddings via GNNs and LLMs

Francesco Ceccarelli, Lorenzo Giusti, Sean B. Holden, Pietro Liò

2024

Abstract

Proteins perform much of the work in living organisms, and consequently the development of efficient computational methods for protein representation is essential for advancing large-scale biological research. Most current approaches struggle to efficiently integrate the wealth of information contained in the protein sequence and structure. In this paper, we propose a novel framework for embedding protein graphs in geometric vector spaces, by learning an encoder function that preserves the structural distance between protein graphs. Utilizing Graph Neural Networks (GNNs) and Large Language Models (LLMs), the proposed framework generates structure- and sequence-aware protein representations. We demonstrate that our embeddings are successful in the task of comparing protein structures, while providing a significant speed-up compared to traditional approaches based on structural alignment. Our framework achieves remarkable results in the task of protein structure classification; in particular, when compared to other work, the proposed method shows an average F1-Score improvement of 26% on out-of-distribution (OOD) samples and of 32% when tested on samples coming from the same distribution as the training data. Our approach finds applications in areas such as drug prioritization, drug re-purposing, disease sub-type analysis and elsewhere.

Paper Citation

in Harvard Style

Ceccarelli F., Giusti L., B. Holden S. and Liò P. (2024). Integrating Structure and Sequence: Protein Graph Embeddings via GNNs and LLMs. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 582-593. DOI: 10.5220/0012453600003654

in Bibtex Style

@conference{icpram24,
author={Francesco Ceccarelli and Lorenzo Giusti and Sean B. Holden and Pietro Liò},
title={Integrating Structure and Sequence: Protein Graph Embeddings via GNNs and LLMs},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={582-593},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012453600003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Integrating Structure and Sequence: Protein Graph Embeddings via GNNs and LLMs
SN - 978-989-758-684-2
AU - Ceccarelli F.
AU - Giusti L.
AU - B. Holden S.
AU - Liò P.
PY - 2024
SP - 582
EP - 593
DO - 10.5220/0012453600003654
PB - SciTePress