Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Efficient protein model refinement with deep learning
Protein refinement methods, which are used to improve the quality of protein structural models, commonly rely on extensive conformational sampling, and therefore, are very time-consuming. In this issue, Xiaoyang Jing and Jinbo Xu propose a method that uses graph neural networks to substantially reduce the time taken to refine protein models, from hours to minutes on a single CPU, while having comparable accuracy with the leading approaches in the field.
While it is crucial to guarantee the reproducibility of the results reported in a paper, let us also not forget about the importance of making research artifacts reusable for the scientific community.
Gravitational-wave discoveries have ignited a new era of astronomy. Numerical relativity plays a crucial role in modeling gravitational-wave sources for current and next-generation observatories, but it doesn’t come without computational challenges.
A graph-neural-network-based framework is proposed for the refinement of protein structure models, substantially improving the efficacy and efficiency of refining protein models when compared with the state-of-the-art approaches.
Making sense of single-cell data requires various computational efforts such as clustering, visualization and gene regulatory network inference, often addressed by different methods. DeepSEM provides an all-in-one solution.
Deep graph neural networks can refine a predicted protein model efficiently with less computing resources. The accuracy is comparable to that of the leading physics-based methods that rely on time-consuming conformation sampling.
An evidence-based approach for dealing with insufficient, conflicting and biased materials data is proposed for recommending high-entropy alloys, showing good capabilities for extrapolating the number of components.
This work demonstrates that large gains still exist in accelerating and improving the coverage of reaction prediction algorithms. These advances create opportunities for computationally exploring deeper and broader reaction networks.
The authors propose a deep learning model that analyzes single-cell RNA sequencing (scRNA-seq) data by explicitly modeling gene regulatory networks (GRNs), outperforming the state-of-art methods on various tasks, including GRN inference, scRNA-seq analysis and simulation.