deep learning

The paper identifies a STAT1-CEBPB-NF-κB signaling pathway in diabetic kidneys that mediates FGF23's pro-inflammatory effects, suggesting CEBPB as a therapeutic target.

The paper identifies plasma B cells as the dominant immune subset in fibrotic hearts of chronic Trypanosoma cruzi-infected mice, revealing their role in sustaining cardiac fibrosis through interactions with fibroblasts.

CellVocal links spatial context to transcriptional dynamics by integrating spatial RNA velocity with cell-cell communication to attribute cell-state transitions to signalling modules and neighbouring cells.

This study uses single-nucleus long-read RNA sequencing to identify isoform usage shifts in mouse kidneys during acute injury, revealing changes in gene expression and isoform composition.

The paper develops a computational model to simulate the self-assembly of cortical microcircuits from progenitors, reproducing experimentally measured connectivity without prescribing individual connections.

spSheaf infers spatial domains from raw molecular data without cell segmentation, outperforming existing methods on benchmark datasets.

The paper compares larval single-cell transcriptomes of sponges and cnidarians to explore the evolutionary origins of neural and sensory cell types.

This study shows FLASH radiotherapy promotes intestinal regeneration by preserving stem cells, enhancing WNT4 signaling, and reducing T-cell inflammation in mice.

The paper develops a spatial proteomics workflow to study early astrocytic remodeling in an ALS mouse model, finding that motor neurons are surrounded by GFAP-high environments earlier than previously observed.

This paper introduces evidence-based re-identification to correct tracking mistakes in multi-animal behavior studies, showing improved reliability over time compared to existing methods.

PRISM simultaneously decontaminates ambient RNA and corrects doublets in spatial transcriptomics data, achieving high accuracy and purity in a mouse cerebellum dataset.

This study links cochlear immunity to adjacent bone marrow through anatomical and day-night profiling in mice, revealing synchronized clocks and immune cell dynamics.

The paper compares gene regulatory networks in mouse and pig limb development to reveal conserved and divergent regulatory programs and mechanisms of developmental robustness.

The paper identifies a dynamic stem cell state marked by Panx3 that responds to environmental cues and enables regeneration in aged and osteoarthritic joints.

This study uses single-cell multi-omics to identify OTP and NOVA1 as key regulators of leptin action in hypothalamic feeding circuits, revealing cell-type-specific transcriptional and regulatory changes.

This paper introduces Braincodec, a deep encoder that improves sound transmission via cortical stimulation, achieving high-fidelity sound reconstruction and matching non-implanted mice in sound discrimination.

ORBIS reconstructs 3D tissue geometry from single-cell gene expression without spatial references, achieving lower shape error and faster sampling than existing methods.

The paper uses a bio-realistic model of mouse primary visual cortex to show that cortical oscillations follow a spectrolaminar motif, with gamma in superficial layers and alpha/beta in deep layers, driven by specific cell types and synaptic properties.

The paper uses single-cell transcriptomics to track molecular changes from premalignancy to cancer in gastric tissue, identifying persistent and evolving tumorigenic lineages and markers like EMB.

MorphoProt predicts spatial protein abundance using RNA expression, multiscale histology, and tissue neighborhoods, outperforming baselines in human and mouse tissues.

SQANTI-evidence annotates genomes from long-read RNA-seq without a reference, achieving high precision in gene and isoform prediction across species.

The paper shows that neural populations adjust their optimal temporal resolution during stimulus processing, becoming faster and more nonlinear when decoding information is most accurate.

This paper benchmarks single-cell foundation models against baselines for annotation, perturbation and regulatory inference using diverse datasets.

This paper uses photographs of mice to predict biological age and finds that older appearance correlates with frailty and shorter survival.

This paper introduces a method to model social behavior using decomposed linear dynamical systems, showing it captures complex, compositional actions more effectively than existing methods.

This paper develops a 2D U-NET model to segment and quantify atherosclerotic lesions in mouse aortic sections, achieving high accuracy and significantly reducing measurement time.

This study develops DDR1-targeting nanobodies that remodel collagen-rich tumor stroma and immune compartments, enhancing tumor control without direct tumor-cell inhibition.

This paper uses the Resonant Recognition Model to analyze cGAS and FANCI sequences across species, identifying conserved spectral features and divergent phase signatures in naked mole-rats.

PHASOR is a pipeline that analyzes retinal multielectrode-array data using hidden Markov models to link stimulus timing with population activity states.