Geographical disparities regarding the availability of GPU hardware are becoming a structural constraint on scientific participation itself and must be addressed.

Although social technologies are increasingly co-shaping the public sphere, these systems were not designed as democratic infrastructure. Here, we propose a framework for societal alignment that focuses on procedural fairness to mitigate urgent risks and align emerging technology with societal values.

FLOWR combines continuous and categorical flow matching with equivariant optimal transport and a separate protein pocket encoder to improve validity, pose accuracy and interaction recovery at substantially faster inference speeds.

This Resource presents the Quantum Optimization Benchmarking Library, which enables fair, reproducible benchmarks of quantum heuristics for ten difficult combinatorial optimization classes with baseline results to track progress towards quantum advantage.

A generative model designs information metamaterials from meta-atoms to programmable arrays, enabling beam steering, focusing and holography with experimental validation and more than 1,000-fold faster holographic design.

Universal machine learning force fields excel on computational benchmarks but consistently fail when tested against experimental measurements of real minerals, underscoring the need for evaluation frameworks grounded in real-world conditions and multiple material properties beyond energy and forces.

Larger language models do not always perform better at fitness prediction. Hou et al. found that performance depends on whether model outputs match evolutionary patterns in homologs, which is best achieved at moderate predicted sequence likelihoods.

This study shows that local pseudopotentials boost the efficiency of neural network-based quantum Monte Carlo while preserving accuracy, enabling reliable simulations of large, challenging iron–sulfur clusters.

The authors propose a framework that integrates cytological imaging and spatial transcriptomics to improve cell segmentation and enable reconstruction of spatial single-cell transcriptomes.

This study introduces DIPPER, a GPU-accelerated tool that efficiently reconstructs evolutionary trees from tens of millions of genome sequences, extending scalability by one to two orders of magnitude beyond that of existing tools.

We highlight how AlphaFold2 has advanced protein design and inspired the development of artificial intelligence-driven infrastructures for scientific discovery.

Geographical disparities regarding the availability of GPU hardware are becoming a structural constraint on scientific participation itself and must be addressed.

Although social technologies are increasingly co-shaping the public sphere, these systems were not designed as democratic infrastructure. Here, we propose a framework for societal alignment that focuses on procedural fairness to mitigate urgent risks and align emerging technology with societal values.

Nature Computational Science now takes part in the co-review initiative in order to encourage the involvement of early-career researchers in the peer review process and to ensure proper recognition of their service.

Protein language models can effectively decode evolution’s grammar, making structure prediction and design scalable. This transformative capability is accelerating biological discovery and engineering across all scales.

We discuss common feedback from reviewers based on our experience as editors.