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.
LEAP is a deep-learning-based approach for the analysis of animal pose. LEAP’s graphical user interface facilitates training of the deep network. The authors illustrate the method by analyzing Drosophila and mouse behavior.
A transcriptional analysis of kidney organoids reveals batch effects as the key drivers of variation, mainly through differences in maturity, and provides a list of highly variable genes and a method for estimating differentiation stage for improved disease modeling.
A compressed sensing approach enables the identification of key neurons involved in a particular behavior with few measurements, using genetic tools with limited specificity. The approach is demonstrated in the C. elegans interneuron circuitry.
Segmental Duplication Assembler (SDA) uses long sequence reads to resolve segmental duplications that are collapsed in current genome assemblies. These assemblies correspond in total to the length of an average human chromosome.
Deep learning enables cross-modality super-resolution imaging, including confocal-to-STED and TIRF-to-TIRF-SIM image transformation. Imaging of a larger FOV and greater depth of field is possible with higher resolution and SNR at lower light doses.
The DNA-based, ratiometric fluorescent reporter CalipHluor enables quantitative imaging of pH and calcium in acidic organelles with single-organelle resolution. The probe was used to identify a lysosome-specific Ca2+ importer in animals.
fMRIPrep is a robust and easy-to-use pipeline for preprocessing of diverse fMRI data. The transparent workflow dispenses of manual intervention, thereby ensuring the reproducibility of the results.
An ex vivo 3D culture model of mycobacterial granulomas recapitulates the in vivo physiology of these structures and enables longitudinal imaging studies. The platform allows genetic and pharmacological manipulation of this key structure.
Imaging of neuronal activity across the whole zebrafish brain in combination with online analysis allows for manipulating neuronal activity according to function. This approach is used to ablate or activate neurons in fictively swimming zebrafish larvae.
A particle-filter algorithm for single-particle cryo-electron microscopy, implemented in a tool called THUNDER, provides high-dimensional parameter estimation, improving the obtainable resolution for several protein structures.
CellDMC finds cell type–specific differential methylation in mixtures of cells, including epithelial tissues, and scenarios in which methylation changes in opposite directions in different cell types.
scVI is a ready-to-use generative deep learning tool for large-scale single-cell RNA-seq data that enables raw data processing and a wide range of rapid and accurate downstream analyses.
YETI puts individual -omics experiments in the context of public genomics data by creating an integrated dataset-specific functional network, thus allowing more thorough interpretation of the data.
Content-aware image restoration (CARE) uses deep learning to improve microscopy images. CARE bypasses the trade-offs between imaging speed, resolution, and maximal light exposure that limit fluorescence imaging to enable discovery.
The machine learning approach FIT leverages public mouse and human expression data to improve the translation of mouse model results to analogous human disease.
Proximity-CLIP, a method that combines proximity-based protein biotinylation and UV crosslinking, profiles RNAs and ribonucleoproteins in any cellular compartment.
VARNAM is a red-shifted genetically encoded voltage sensor based on the Ace opsin. It is applied in Drosophila, mouse brain slices and behaving mice. It can be readily combined with blue-light-sensitive tools for dual-color applications.
BLINK2 is a light-activated potassium channel for optogenetic inhibition of neuronal activity. Alberio et al. apply the tool in systems as diverse as cultured rat neurons, mouse brain slices, behaving zebrafish and a rat model of neuropathic pain.
HUMAnN2 uses a tiered sequence search to provide rapid and accurate species-level functional profiles of microbial communities from metagenomic and metatranscriptomic data.