Abstract
AbstractPredicting the effects of mutations on protein function is an outstanding challenge. Here we assess the performance of the deep learning based RoseTTAFold structure prediction and design method for unsupervised mutation effect prediction. Using RoseTTAFold in inference mode, without any additional training, we obtain state of the art accuracy on predicting mutation effects for a set of diverse protein families. Thus, although the architecture of RoseTTAFold was developed to address the protein structure prediction problem, during model training RoseTTAFold acquired an understanding of the mutational landscapes of proteins comparable to that of large recently developed language models. The ability to reason over structure as well as sequence could enable even more precise mutation effect predictions following supervised training.
Publisher
Cold Spring Harbor Laboratory
Reference8 articles.
1. Protein design and variant prediction using autoregressive generative models
2. Mutation effects predicted from sequence co-variation
3. Deep generative models of genetic variation capture the effects of mutations;Nature Methods,2018
4. Alexander Rives Proceedings of the 38th International Conference on Machine Learning;PMLR,2021
5. Meier, J. , Rao, R. , Verkuil, R. , Liu, J. , Sercu, T. , & Rives, A. (2021). Language models enable zero-shot prediction of the effects of mutations on protein function. 1–28.
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献