Structure prediction articles from across Nature Portfolio

Icing plays an important role in various physical-chemical process. Here, the authors identify a critical value of surface energy parameter, above which two-dimensional and three-dimensional coexisting ice can form on the surface.

Geometric deep learning methods have the advantage of being expressive, while denoising diffusion probabilistic models have great generative power. Here, the authors introduce a geometry-complete diffusion model for effective 3D molecule generation for specific protein pockets that can also consistently optimize the geometry and chemical composition of existing 3D molecules for molecular stability and property specificity

Deep learning models have gained popularity for chemical reaction outcome prediction due to their ability to learn representations directly from the molecular structure, whereas Gaussian processes provide reliable uncertainty estimates but are unable to learn representations from the data. Here, the authors combine the feature learning ability of neural networks with uncertainty quantification of Gaussian processes in a deep kernel learning framework to predict reaction outcomes.

LLMs can be augmented with tools to increase their capabilities. Here, authors have developed an artificial intelligence system called ChatMOF combining LLMs and specialised libraries and utilities to predict and generate metal-organic frameworks.

A fully automated, high-throughput computational framework accurately predicts stable species in liquid solutions by computing the nuclear magnetic resonance chemical shifts. Data collected from the framework can provide fingerprints to guide the rational design of liquid solutions with optimal properties.

Machine learning algorithms are fast surpassing human abilities in multiple tasks, from image recognition to medical diagnostics. Now, machine learning algorithms have been shown to be capable of accurately predicting the folded structures of proteins.

The Hückel rule defines that monocyclic and planar conjugated systems containing [4n + 2] π electrons are aromatic. Here, the authors highlight boron species that feature a globally 4n π system, defying the Hückel rule, but nonetheless exhibit aromaticity.

Models for polyhedral clusters with different symmetries enable us to understand their electronic structures and predict the formation of new clusters.

A comprehensive chemical space of potential inorganic ternary metal nitrides has been explored by computational methods as a guideline for their experimental synthesis and discovery.