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.
An efficient algorithm is proposed to integrate large-scale microbiome datasets. This unbiased data integration method enables the identification of robust biomarkers associated with various diseases through assessing shifts of microbial network modules.
Weight-sharing is used to accelerate and to effectively pretrain neural network-based variational Monte Carlo methods when solving the electronic Schrödinger equation for multiple geometries.
Associating biotechnology to its lab of origin is a challenging task. A deep learning approach is proposed to find distances between engineered plasmids, which allows the ranking of their most probable labs of origin with high accuracy.
A protocol is developed to construct multi-domain protein structures from cryo-electron microscopy density maps. The results demonstrate the effectiveness of deep-learning-guided inter-domain structure assembly and refinement simulations.
Smart pandemic mitigation strategies are proposed to strategically close higher-risk economic sectors, while allowing dozens of other economic sectors to continue. This would enable schools to remain open and keep hospitalizations within capacity.
Unified structural descriptors of geometrical and graph-theoretical features are developed, allowing knowledge about protein lock-and-key complexes to be utilized to predict the formation of and interaction sites in protein–nanoparticle pairs.
Cascaded gated-recurrent-unit networks trained through a physics-informed multi-fidelity approach can accurately forecast long time sequences and capture their dynamics in a wide range of optical resonance structures and features.
A dynamic probabilistic algorithm that integrates many variables over time for forecasting severe acute graft-versus-host disease is proposed to improve healthcare decisions for individual patients on a case-by-case basis.
Scallop2 enables a more accurate assembly of transcripts at both single-cell resolution and sample level through a suite of algorithms that leverage the multi-end and paired-end information in Smart-seq3 and Illumina RNA-seq data.
A modeling pipeline for the stochastic binding behavior of antibodies on patterned antigen substrates predicts programmable walking behavior that can be manipulated and directed through pattern geometry.
A Bayesian method is presented for unbiased estimation of timescales from different types of experimental data; the method quantifies the estimation uncertainty and allows for comparing the alternative hypotheses on the underlying dynamics.
The authors propose a two-phase approach to solve the inverse problem of inferring dynamical principles of complex systems from incomplete and noisy data, and apply it to infer the spreading dynamics of H1N1, SARS, and COVID-19.
A fully automated, high-throughput computational framework is presented to predict stable species in liquid solutions. This framework combines density functional theory with classical molecular dynamics simulations to compute the NMR chemical shifts.
The authors demonstrate a robust and rigorous framework that can enumerate up to 100 fluorescent labels in a diffraction limited spot using Bayesian nonparametrics.
mm2-fast is an accelerated version of minimap2, a popular software for long-read data analysis. mm2-fast introduces high-performance parallel computing techniques to reduce the overall runtime of minimap2.
To help determine how life history traits of individuals result in emergent properties of a population, laboratory studies of Caenorhabditis elegans were combined with an individual-based simulation, pointing out to potential factors that influence old age as a cause of death.
A multiscale model is presented to quantitatively predict COVID-19 vaccine efficacies by describing the generation, activity and diversity of neutralizing antibodies.
Networks offer a powerful visual representation of complex systems. This study introduces network visualizations that are easy to interpret and can help explore large datasets, such as the map of all molecular interactions in the cell.
deepManReg uses deep neural networks to map various data types onto a topological space (manifolds) and unfold unseen data connections, thus improving prediction of phenotypes from multi-modal data.
