Enhancing Protein Function Prediction Through the Fusion of Multi-Type Biological Knowledge With Protein Language Model and Graph Neural Network

Proteins play crucial roles in diverse biological functions. Accurately annotating their functions is essential for understanding cellular mechanisms and developing therapies for complex diseases. Computational methods have been proposed as alternatives to labor-intensive and expensive experimental approaches. Existing computational methods have demonstrated that protein evolution information and Protein-Protein Interactions (PPIs) are essential for protein function prediction. However, traditional computational approaches for generating evolution information are time-consuming. On the other hand, proteins lacking interactions are ignored in previous studies. To address these limitations, we propose a novel deep learning framework, named DeepFMB, which incorporates multi-type biological knowledge. DeepFMB leverages a pre-trained protein language model to extract evolution information. Moreover, DeepFMB generates PPI-related features and orthology-related features using graph neural networks on the constructed PPI and orthology networks. Then, these multi-type features are fused adaptively for protein function prediction. Compared to eight state-of-the-art methods, DeepFMB outperforms all of them in terms of F-max and AUPR. Additionally, with the combination of sequence similarity-based inference, our predicted model predicts protein functions more accurately. Experimental results also validate the superior performance of our methods in predicting low-frequency GO terms. Ablation studies demonstrate that the multi-type biological knowledge we use is highly relevant to protein functions.

I. Introduction

Proteins are essential biomolecules within living organisms and play indispensable roles in diverse biological processes, including cell motility and metabolic pathways [1]. Accurately annotating protein functions is crucial for understanding biological activities and disease pathology mechanisms [2]. However, traditional experimental approaches for functional annotation are costly, time-consuming, and unable to keep up with the rapidly increasing number of protein sequence generated by high-throughput sequencing technologies [3]. Consequently, over 99% of protein sequences in the UniProt [4] database lack experimentally validated functional annotations. Faced with this challenge, it is essential to develop computational approaches to accurately predict protein functions [5]. Such approaches not only enhance our understanding of protein functions but also expedite new drug discoveries and facilitate the development of disease treatment strategies.