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.
The dissipation and bending of light waves by atmospheric turbulence adversely affects infrared imaging, leading to grayscale drift, distortion, and blurring. A deep learning method has been developed to both extract the two-dimensional atmospheric turbulence strength fields and obtain clear and stable images from turbulence-distorted infrared images.
A hierarchical Bayesian method identifies cell-type specific changes in gene regulatory circuits in disease by integrating single-cell and three-dimensional measurements of the genome.
While the adherence to fairness constraints has become common practice in the design of algorithms across many contexts, a more holistic approach should be taken to avoid inflicting additional burdens on individuals in all groups, including those in marginalized communities.
A recent work introduces a cellular deconvolution method, MeDuSA, of estimating cell-state abundance along a one-dimensional trajectory from bulk RNA-seq data with fine resolution and high accuracy, enabling the characterization of cell-state transition in various biological processes.
Real-time mobility data capturing city-wide human movement can be used to characterize cities, their segregation, and population responses to exogenous events such as pandemics.
Deep learning is used to accelerate the inference of genetic clusters, allowing the analysis of hundreds of thousands of human genomic datasets in a computationally efficient way.
The field of human mobility has evolved drastically in the past 20 years. In this Perspective, the authors discuss three key areas in human mobility, framed as minds, societies and algorithms, where they expect to see substantial improvements in the future.
Increasing the number of parameters in a quantum neural network leads to a computational ‘phase transition’, beyond which training the network becomes significantly easier. An algebraic theory has been developed for this overparametrization phenomenon and predicts its onset above a certain parameter threshold.
GRAPE is a software resource for graph processing, learning and embedding that is orders of magnitude faster than existing state-of-the-art libraries. GRAPE can quickly process real-world graphs with millions of nodes and billions of edges, enabling complex graph analyses and research in graph-based machine learning and in diverse disciplines.
Although the number of quantum chemical studies on atmospheric cluster formation continue to rise, data-driven approaches can greatly expand the number of chemically relevant systems that can be covered and increase our understanding of the aerosol particle formation process.
The carbon footprint of computational sciences is substantial, but there is an immense opportunity to lead the way towards sustainable research. In this Perspective the authors lay some fundamental principles to transform computational science into an exemplar of broad societal impact and sustainability.
Addressing plastic pollution in the environment is difficult due to the high complexity and diversity of physical and chemical properties. This Perspective argues that process-based mass-balance models could provide a viable solution for evaluating environmental exposure to plastic pollution.
Artificial photosynthesis has the potential to capture and store solar energy in the form of chemical bonds. Computational approaches provide useful guidelines for the experimental design of photosynthetic devices, but to make this possible, many challenges must be overcome.
A momentum-space algorithm is proposed to simulate electron dynamics with time-dependent density functional theory, which expands the scope of conventional real-space methods.
By conducting single-cell meta-analyses of inflammatory bowel disease, we identify rare or less-characterized cell subtypes linked to GWAS risk genes and therapeutic targets and dissect the commonalities and differences between ulcerative colitis and Crohn’s disease. Consequently, we present an interactive and user-friendly platform for the research community.
A computational tool based on an additive approach and linear algebra has been developed together with a fabrication strategy for the systematic exploration of rigid-deployable, compact and reconfigurable kirigami patterns.
We often encounter mental conflict in our lives. Such mental conflict has long been regarded as subjective. However, a machine learning method can be used to quantify the temporal dynamics of conflict between reward and curiosity from behavioral time-series.
An image-inspired deep-learning model is developed to generate realistic de novo protein structures and scaffolds around functional sites, which helps the search for new structures and functions in protein engineering.
A graph neural network — GAME-Net — has been developed to predict the adsorption energy of organic molecules on metal surfaces, which is a key descriptor of heterogeneous catalytic activity. This method allows for the study of large molecules derived from raw materials such as plastic waste, avoiding the use of costly and time-intensive first-principles simulations.