Protein surface serves as an important representation of protein structure, determining the biological functions. With the flourishing of deep learning, various descriptors for protein surface have been proposed, delivering promising results in tasks like protein design and interaction prediction. These data-driven methods face the challenges of label scarcity, since labeled data are typically obtained through wet lab experiments. Self-supervised learning has shown great success in solving the lack of labeled data in the fields of natural language processing and computer vision and also has positive prospects in protein surface representation. However, current deep learning protein representation methods are not suitable for self-supervised learning.
To address this challenge, a research team led by Manning Wang published their new research on 15 October 2024 in Frontiers of Computer Science co-published by Higher Education Press and Springer Nature.
The team proposes SS-Pro, a simple and efficient contrastive self-supervised learning framework, which can be adapted to various protein surface networks. The team leverages a large dataset of unlabeled protein surface data for pre-training and fine-tune the downstream network with the pre-trained weights. To validate our approach's effectiveness, experiments are conducted on two downstream tasks: protein surface binding site recognition and protein-protein interaction prediction. The results demonstrate performance enhancements across four different protein surface networks, highlighting the strong generalization and efficacy of our approach across many applications.
DOI: 10.1007/s11704-024-3806-9