Enhancing Multimodal Protein Function Prediction Through Dual-Branch Dynamic Selection with Reconstructive Pre-Training
This work addresses protein function prediction for bioinformatics, offering incremental advances through hybrid techniques.
The paper tackled the challenge of predicting protein functions from multimodal features by proposing DSRPGO, a method that uses reconstructive pre-training and dynamic selection, resulting in significant improvements in BPO, MFO, and CCO metrics on human datasets.
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.