Team news, editorial projects and initiatives, plus a preview of what’s to come in 2026.

Nimbus, a deep learning model, uses a large multiplexed imaging dataset to predict the likelihood of marker positivity in single cells.

Two new methodologies for automated cell tracking allow rapid analysis of cellular-scale behaviors across diverse samples with minimal errors.

OrganoidTracker 2.0 enables fast and accurate cell tracking in complex systems such as developing organoids. A key aspect of the work is determining cell tracks with error probabilities for any tracking feature, from cell cycles to lineage trees.

CaCoFold-R3D is a probabilistic model that simultaneously predicts the RNA 3D motifs jointly with the secondary structure in a structural RNA using evolutionary information.

Manual analysis of single-molecule time traces is slow and subjective. Now, a transformer-based foundation model — META-SiM —automates key analysis tasks across diverse datasets and enables rapid, systematic discovery of subtle single-molecule behaviors. Application of this approach reveals a previously undetected pre-mRNA splicing intermediate, highlighting its potential to streamline biological discovery.

META-SiM brings foundation model power to single-molecule time traces, excelling across diverse analysis tasks. Paired with the web-based META-SiM Projector and entropy mapping, it rapidly reveals hidden molecular behaviors inaccessible by other means.

HippoMaps provides an open-source resource for studying the human hippocampus at different scales and with different modalities such as histology, fMRI, structural MRI and EEG.

Giotto Suite provides a comprehensive, flexible and scalable platform for technology-agnostic spatial omics analysis using R.

Adaptive optical vision Fourier transformer (AOViFT) is a machine learning-based framework for accurately inferring aberrations and restoring diffraction-limited performance in diverse biological specimens.

precisION discovers, localizes and quantifies protein modifications within complex proteoform assemblies through data-driven analysis of native top-down mass spectra.

Confocal microscopy enables high-resolution, high-plex 3D cyclic immunofluorescence of 30- to 50-µm-thick tissue sections. The approach allows for rich phenotypic assessments of intact cells and intercellular interactions with subcellular resolution.

InterPLM is a computational framework to extract and analyze interpretable features from protein language models using sparse autoencoders. By training sparse autoencoders on ESM-2 embeddings, this study identifies thousands of interpretable biological features learned by the different layers of the ESM-2 model.

FlexConsensus is a multi-autoencoder-based algorithm for merging different conformational landscapes from cryogenic electron microscopy heterogeneity analysis into a common latent space for the identification of similarities and differences among various methods. This helps in the validation of estimated conformational landscape and provides tools to streamline the heterogeneity workflow.

This work presents scEpi2-seq, a method for simultaneous single-cell profiling of DNA methylation and histone modifications, enabling direct investigation of the interplay between these two epigenomic marks.

EpiAgent is a foundation model for analyzing scATAC-seq data that excels in standard downstream tasks such as feature extraction, cell type annotation and data imputation while also enabling simulation of cCRE knockouts and cell state changes.

Squeezed light field microscopy (SLIM) combines ideas from tomography and compressed sensing with light field microscopy to enable volumetric imaging at kilohertz rates, as demonstrated in blood flow imaging in zebrafish and voltage imaging in leeches and mice.

A cryogenic scanning transmission electron microscopy (STEM) approach for analyzing thick biological specimens expands the reach of cryo-electron microscopy.

Tilt-corrected bright-field scanning transmission electron microscopy offers enhanced cryogenic electron microscopy contrast and substantial improvement in dose efficiency for thick samples such as bacterial cells and large organelles, while still being able to perform single-particle analysis.

CORAL can infer the occurrence of rare species based on common species, using DNA metabarcoding data or other high-dimensional biodiversity data. The approach is illustrated on a large-scale biodiversity survey from Madagascar.