2024Song RMSFNet
Citation
Song, Xintao / Bao, Lei / Feng, Chenjie / Huang, Qiang / Zhang, Fa / Gao, Xin / Han, Renmin. Accurate Prediction of Protein Structural Flexibility by Deep Learning Integrating Intricate Atomic Structures and Cryo-EM Density Information. 2024. Nature Communications, Vol. 15, No. 1, p. 5538
Abstract
The dynamics of proteins are crucial for understanding their mechanisms. However, computationally predicting protein dynamic information has proven challenging. Here, we propose a neural network model, RMSF-net, which outperforms previous methods and produces the best results in a large-scale protein dynamics dataset; this model can accurately infer the dynamic information of a protein in only a few seconds. By learning effectively from experimental protein structure data and cryo-electron microscopy (cryo-EM) data integration, our approach is able to accurately identify the interactive bidirectional constraints and supervision between cryo-EM maps and PDB models in maximizing the dynamic prediction efficacy. Rigorous 5-fold crossvalidation on the dataset demonstrates that RMSF-net achieves test correlation coefficients of 0.746 ± 0.127 at the voxel level and 0.765 ± 0.109 at the residue level, showcasing its ability to deliver dynamic predictions closely approximating molecular dynamics simulations. Additionally, it offers realtime dynamic inference with minimal storage overhead on the order of megabytes. RMSF-net is a freely accessible tool and is anticipated to play an essential role in the study of protein dynamics.
Keywords
Links
https://www.nature.com/articles/s41467-024-49858-x