Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, United States of America.
Departments of Internal Medicine and Human Genetics and School of Public Health, University of Michigan, Ann Arbor, Michigan, United States of America.
PLoS Comput Biol. 2022 Sep 16;18(9):e1010539. doi: 10.1371/journal.pcbi.1010539. eCollection 2022 Sep.
Despite the immense progress recently witnessed in protein structure prediction, the modeling accuracy for proteins that lack sequence and/or structure homologs remains to be improved. We developed an open-source program, DeepFold, which integrates spatial restraints predicted by multi-task deep residual neural-networks along with a knowledge-based energy function to guide its gradient-descent folding simulations. The results on large-scale benchmark tests showed that DeepFold creates full-length models with accuracy significantly beyond classical folding approaches and other leading deep learning methods. Of particular interest is the modeling performance on the most difficult targets with very few homologous sequences, where DeepFold achieved an average TM-score that was 40.3% higher than trRosetta and 44.9% higher than DMPfold. Furthermore, the folding simulations for DeepFold were 262 times faster than traditional fragment assembly simulations. These results demonstrate the power of accurately predicted deep learning potentials to improve both the accuracy and speed of ab initio protein structure prediction.
尽管最近在蛋白质结构预测方面取得了巨大的进展，但对于缺乏序列和/或结构同源物的蛋白质，其建模准确性仍有待提高。我们开发了一个开源程序 DeepFold，它集成了多任务深度残差神经网络预测的空间约束以及基于知识的能量函数，以指导其梯度下降折叠模拟。在大规模基准测试中的结果表明，DeepFold 创建的全长模型的准确性远远超过经典折叠方法和其他领先的深度学习方法。特别有趣的是，在具有非常少同源序列的最困难目标上的建模性能，在这些目标上，DeepFold 的 TM 评分平均比 trRosetta 高 40.3%，比 DMPfold 高 44.9%。此外，DeepFold 的折叠模拟速度比传统的片段组装模拟快 262 倍。这些结果表明，准确预测的深度学习势能在提高从头蛋白质结构预测的准确性和速度方面具有强大的作用。
