Enhancing Multimodal Protein Function Prediction Through Dual-Branch Dynamic Selection with Reconstructive Pre-Training

TL;DR

This paper introduces DSRPGO, a novel multimodal protein function prediction method that employs dynamic feature selection and reconstructive pre-training to improve accuracy across multiple protein function categories.

Contribution

The work presents a new model integrating reconstructive pre-training, a bidirectional interaction module, and dynamic feature selection for enhanced protein function prediction.

Findings

Significant improvement in BPO, MFO, and CCO prediction accuracy.

Outperforms existing benchmark models on human datasets.

Effective handling of hierarchical multi-label classification.

Abstract

Multimodal protein features play a crucial role in protein function prediction. However, these features encompass a wide range of information, ranging from structural data and sequence features to protein attributes and interaction networks, making it challenging to decipher their complex interconnections. In this work, we propose a multimodal protein function prediction method (DSRPGO) by utilizing dynamic selection and reconstructive pre-training mechanisms. To acquire complex protein information, we introduce reconstructive pre-training to mine more fine-grained information with low semantic levels. Moreover, we put forward the Bidirectional Interaction Module (BInM) to facilitate interactive learning among multimodal features. Additionally, to address the difficulty of hierarchical multi-label classification in this task, a Dynamic Selection Module (DSM) is designed to select the feature representation that is most conducive to current protein function prediction. Our proposed DSRPGO model improves significantly in BPO, MFO, and CCO on human datasets, thereby outperforming other benchmark models.