We recognize the importance of preprint posting in communicating research findings and encourage our authors to make use of this service.

Discovering improved semiconductor materials is essential for optimal device fabrication. In this Perspective, data-driven computational frameworks for semiconductor discovery and device development are discussed, including the challenges and opportunities moving forward.

This paper introduces an algorithm to uncover laws of skill acquisition from naturally occurring data. By combining deep learning and symbolic regression, it accurately identifies cognitive states and extracts algebraic equations.

MISATO is a database for structure-based drug discovery that combines quantum mechanics data with molecular dynamics simulations on ~20,000 protein–ligand structures. The artificial intelligence models included provide an easy entry point for the machine learning and drug discovery communities.

Seqwalk is a scalable method for designing orthogonal DNA barcode libraries, producing one million barcodes in 20 s on a standard laptop.

A self-consistent iterative procedure is proposed to compute the committor function for rare events, via a variational principle, and extensively sample the transition state ensemble, allowing for the identification of the relevant variables in the process.

This paper introduces an algorithm to uncover laws of skill acquisition from naturally occurring data. By combining deep learning and symbolic regression, it accurately identifies cognitive states and extracts algebraic equations.

The authors develop the tool RESHAPE to share reference panels in a safer way. The genome–phenome links in reference panels can generate re-identification threats and RESHAPE breaks these links by shuffling haplotypes while preserving imputation accuracy.

MISATO is a database for structure-based drug discovery that combines quantum mechanics data with molecular dynamics simulations on ~20,000 protein–ligand structures. The artificial intelligence models included provide an easy entry point for the machine learning and drug discovery communities.

A method based on a vector-quantized variational autoencoder, called CASTLE, can interpretably extract discrete latent embeddings and quantitatively generate the cell-type-specific feature spectrum for single-cell chromatin accessibility sequencing data.

Morphing soft matter, which is capable of changing its shape and function in response to stimuli, has wide-ranging applications in robotics, medicine and biology. Recently, computational models have accelerated its development. Here, we highlight advances and challenges in developing computational techniques, and explore the potential applications enabled by such models.

Dr Kelly Ruggles, associate professor at New York University Langone Health, discusses with Nature Computational Science how she uses computational approaches to gain insights into cancer, inflammation and cardiovascular disease, as well as the importance of mentorship.

We recognize the importance of preprint posting in communicating research findings and encourage our authors to make use of this service.

We highlight the vibrant discussions on quantum computing and quantum algorithms that took place at the 2024 American Physical Society March Meeting and invite submissions that notably drive the field of quantum information science forward.

Wildfires have increased in frequency and intensity due to climate change and have had severe impacts on the built environment worldwide. Moving forward, models should take inspiration from epidemic network modeling to predict damage to individual buildings and understand the impact of different mitigations on the community vulnerability in a network setting.