Articles

Using a dependency-aware deep generative framework, spaVAE efficiently models spatially resolved transcriptomics data and advances diverse analysis tasks. Following similar strategies, spaPeakVAE and spaMultiVAE enable spatial ATAC-seq data and spatial multi-omics data modeling and analysis, respectively.

STT is a method that connects mRNA splicing and cell-state transitions across spatiotemporal scales and at single-cell resolution.

The Pebblescout tool achieves an efficient search for subjects in a large nucleotide database such as runs in Sequence Read Archive data.

OpenFold is a trainable open-source implementation of AlphaFold2. It is fast and memory efficient, and the code and training data are available under a permissive license.

By learning to embed DNA k-mers and cells into a joint space, CellSpace improves single-cell ATAC-seq analysis in multiple tasks such as latent structure discovery, transcription factor activity inference and batch effect mitigation.

Single-cell quantitative expression reporters enable high-sensitivity quantitative characterization of cis-regulatory elements at the single-cell level in multicellular systems.

Molecular Pixelation is an optics-free method that uses DNA-tagged antibodies to enable identification of the relative location of proteins on single cells.

Combining genome-wide CRISPR–Cas9-mediated base editors with temporally resolved phosphoproteomics enables the functional screening of thousands of post-translational modification sites involved in T cell activation.

ESI-cryoPrep is a cryo-EM specimen preparation method that employs electrospray ionization techniques to deposit charged macromolecule-containing droplets on EM grids. Demonstrated across various protein samples, this approach effectively prevents biomolecule adsorption at air–water or graphene–water interfaces, addressing challenges related to protein denaturation and preferred orientation.

Super-resolution imaging of reference and target structures enables precise determination of the labeling efficiency of high-affinity binding proteins in cells for improved quantitative assessment of protein organization at the single-molecule level.

SABR-IIs are engineered bifunctional receptors that enable CD4⁺ T cell antigen discovery.

Generating training data for training deep-learning-based tools is time consuming. The DELiVR pipeline facilitates this process as demonstrated in this study on detecting c-Fos⁺ cells or microglia in the brain, following tissue clearing and imaging with light-sheet microscopy.

LiMCA offers a tool for co-profiling 3D genome structure and gene expression at the single-cell level, enabling researchers to elucidate the olfactory receptor gene selection process.

A pretrained foundation model (UniFMIR) enables versatile and generalizable performance across diverse fluorescence microscopy image reconstruction tasks.

scGHOST offers a computational tool to annotate single-cell subcompartments from scHi-C or imaging data through graph representation learning with constrained random walk sampling.

Kilosort4 is a spike-sorting algorithm with improved performance compared to previous versions, owing to the use of a graph-based clustering approach. The tool extracts the activity of individual neurons from electrophysiological recordings acquired with, for example, Neuropixels electrodes.

The combination of light sheet illumination and reversibly switchable fluorophores enables improved structured illumination microscopy for fast, low-background super-resolution imaging in cells and spheroids.

Deep interactome profiling by mass spectrometry (DIP-MS) combines affinity purification with native BN-PAGE fractionation and mass spectrometry to resolve protein complexes sharing the same target protein. The paper also presents PPIprophet, a data-driven neural network-based protein complex deconvolution approach.

RoboEM enables automated proofreading of electron microscopy datasets using a strategy akin to that of self-steering cars. This decreases the need for manual proofreading of segmented datasets and facilitates connectomic analyses.

Improved green cAMP and red calcium sensors were developed to facilitate dual-color imaging in vivo. These sensors will allow studying the relationship between calcium and cAMP signaling.