An Effective GCN-based Hierarchical Multi-label classification for Protein Function Prediction

2021/12/06 by Choi, Kyudam, Lee, Yurim, Kim, Cheongwon +1
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2112.02810

Abstract

We propose an effective method to improve Protein Function Prediction (PFP) utilizing hierarchical features of Gene Ontology (GO) terms. Our method consists of a language model for encoding the protein sequence and a Graph Convolutional Network (GCN) for representing GO terms. To reflect the hierarchical structure of GO to GCN, we employ node(GO term)-wise representations containing the whole hierarchical information. Our algorithm shows effectiveness in a large-scale graph by expanding the GO graph compared to previous models. Experimental results show that our method outperformed state-of-the-art PFP approaches.

Related

• DEEPGONET: Multi-label Prediction of GO Annotation for Protein from Sequence Using Cascaded Convolutional and Recurrent Network
• DeepGATGO: A Hierarchical Pretraining-Based Graph-Attention Model for Automatic Protein Function Prediction
• STAR-GO: Improving Protein Function Prediction by Learning to Hierarchically Integrate Ontology-Informed Semantic Embeddings
• Multi-task Deep Neural Networks in Automated Protein Function Prediction
• Using the Gene Ontology Hierarchy when Predicting Gene Function