SPIN-CGNN: Improved fixed backbone protein design with contact map-based graph construction and contact graph neural network

• Published in: PLoS computational biology Vol. 19; no. 12; p. e1011330
• Main Authors: Zhang, Xing, Yin, Hongmei, Ling, Fei, Zhan, Jian, Zhou, Yaoqi
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.12.2023; Public Library of Science (PLoS)
• Subjects: Amino acids; Artificial neural networks; Biology and Life Sciences; Complexity; Computer and Information Sciences; Conserved sequence; Datasets; Deep learning; Diffusion models; Energy; Engineering and Technology; Graph neural networks; Graph representations; Graph theory; Hydrophobicity; Information processing; Machine learning; Methods; Multilayer perceptrons; Multilayers; Neural networks; Physical Sciences; Protein engineering; Proteins; Research and Analysis Methods; Technology application; China
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1011330

Recent advances in deep learning have significantly improved the ability to infer protein sequences directly from protein structures for the fix-backbone design. The methods have evolved from the early use of multi-layer perceptrons to convolutional neural networks, transformers, and graph neural networks (GNN). However, the conventional approach of constructing K-nearest-neighbors (KNN) graph for GNN has limited the utilization of edge information, which plays a critical role in network performance. Here we introduced SPIN-CGNN based on protein contact maps for nearest neighbors. Together with auxiliary edge updates and selective kernels, we found that SPIN-CGNN provided a comparable performance in refolding ability by AlphaFold2 to the current state-of-the-art techniques but a significant improvement over them in term of sequence recovery, perplexity, deviation from amino-acid compositions of native sequences, conservation of hydrophobic positions, and low complexity regions, according to the test by unseen structures, “hallucinated” structures and diffusion models. Results suggest that low complexity regions in the sequences designed by deep learning, for generated structures in particular, remain to be improved, when compared to the native sequences.