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 optogenetic strategy enables selection of proteases with improved catalytic rates. The developed TEV protease variants are well suited for biotechnology applications, including FLARE assays with substantially improved temporal resolution.
MaSIF, a deep learning-based method, finds common patterns of chemical and geometric features on biomolecular surfaces for predicting protein–ligand and protein–protein interactions.
The unique advantages of single-particle cryo-electron microscopy and cryo-electron tomography are combined in a method called TYGRESS, here applied to determine the structure of the intact ciliary axoneme at a resolution of 12 Å.
An approach combining cryo-electron microscopy and mass spectrometry analysis of protein complexes enriched directly from cells enables structure determination of unknown complexes at atomic resolution.
Single-cell isolation following time-lapse imaging (SIFT) enables high-throughput screening of complex and dynamic phenotypes from pooled bacterial libraries. SIFT was used to generate ultraprecise synthetic gene oscillators.
A new method of autophagy measurement is based on the detection of phospho-ATG16L1, a conserved early marker of autophagy. Sensitive detection can be achieved in multiple biological systems and assays with advantages over standard methods.
Harmony, for the integration of single-cell transcriptomic data, identifies broad and fine-grained populations, scales to large datasets, and can integrate sequencing- and imaging-based data.
Directly sequencing RNA strands through a nanopore retains the full length of the transcript and allows for analysis of polyA tail length, transcript haplotypes and base modifications.
DuMPLING (dynamic μ-fluidic microscopy phenotyping of a library before in situ genotyping) enables screening of dynamic phenotypes in strain libraries and was used here to study genes that coordinate replication and cell division in Escherichia coli.
Probabilistic cell typing by in situ sequencing (pciSeq), leverages previous single-cell RNA sequencing classification and multiplexed in situ RNA detection to spatially map cell types accurately in the mouse hippocampus and isocortex.
Deep-Z uses deep learning to go from a two-dimensional snapshot to three-dimensional fluorescence images. The method improves imaging speed while reducing light dose, and was shown to be useful for accurate structural and functional imaging of neurons in Caenorhabditis elegans.
Simultaneous two-photon microscopic and one-photon mesoscopic imaging of calcium signals enables correlation of local cellular and brain-wide network activity.
mmvec, a neural-network-based algorithm, uses paired multiomics data (microbial sequence counts and metabolite abundances) to compute the conditional probability of observing a metabolite in the presence of a specific microorganism.
UniRep learns fundamental protein features from millions of amino-acid sequences using a recurrent neural network. This summary of features can then be used for protein engineering.
An engineering approach guided by machine learning results in high-performance channelrhodopsin variants that are suitable for systemic viral delivery and illumination through a thinned skull.
Cellular lipids, labeled with a charged reporter, yield characteristic MS1 and MS2 patterns during mass spectrometry. These reporters allow sample multiplexing and sensitive detection of lipid metabolism at single cell resolution.
An integrated pipeline for processing cryo-ET data implemented in EMAN2 streamlines data processing to minimize human bias, and improves the quality and resolution of resulting macromolecular structures, both in vitro and in cells.
SAUCIE, a deep learning platform to analyze single-cell data across samples and platforms, allows information to be obtained from the internal layers of the network, which provides additional mechanistic understanding that can be used to further tune data analysis.