clustering

Resting Cortical Alpha and Beta Oscillations are Continuous Across Space and Frequency

This study shows that cortical alpha and beta oscillations form a continuous spatio-spectral gradient across the neocortex, correlating with cognition and aging.

Sensing the heart, seeing the world: Neural mechanisms of attentional allocation between interoception and exteroception

This study uses fMRI to compare neural networks for interoceptive and exteroceptive attention, finding distinct but interacting systems for internal and external sensory processing.

Discrete Morse Graph Construction for High-Dimensional Transcriptomic Data

This paper introduces scDMGC, a method to analyze high-dimensional transcriptomic data using topological data analysis, revealing cell-type organization and transcriptional gradients in brain datasets.

Minkowski Tensors as a Lightweight and Interpretable Representation for Three-Dimensional Morphology

This paper introduces Minkowski Tensors as interpretable 3D shape descriptors, showing competitive performance on biomedical image classification tasks.

ctDNA Release Heterogeneity in Luminal Breast Cancer Revealed by Single-Cell Multi-Omics Spatial Analysis

The paper identifies cellular and spatial determinants of ctDNA release in HR+/HER2- breast cancer using single-cell multi-omics spatial analysis, linking tumor states, mutations, and immune interactions to ctDNA release patterns.

Physics-Informed Neural Network for Mapping Vascular and Tissue Dynamics Using Laser Speckle Contrast Imaging

This paper develops a physics-informed neural network to rapidly estimate vascular and tissue dynamics from laser speckle contrast imaging data without ground-truth labels.

Unsupervised transcriptomic analysis of paired pre- and post-treatment specimens reveals divergent chemoimmunomodulatory induction trajectories in breast cancer

The paper uses unsupervised clustering to classify chemoimmunomodulatory trajectories in breast cancer, identifying two distinct patterns associated with different clinical outcomes.

Biologically grounded cell profiling across microscopy modalities

The paper introduces MorphAgent, a biologically grounded AI framework for cell profiling across microscopy modalities, improving feature design and performance in drug screening and disease analysis.

Holobiomes in succession: post-glacial microbial communities are structured by hosts, time and habitat heterogeneity

This study examines microbial community structure in glacier forefields, finding that host identity, time, and habitat heterogeneity shape bacterial and fungal communities across different successional stages.

SALL1 and neural microenvironmental contextspecify identity of stem cell derived humanmicroglia-like cells

This study identifies how SALL1 and neural microenvironmental context shape the identity of stem cell-derived human microglia-like cells in 2D and 3D cultures.

Serval: A modular framework for decoding imaging based spatial transcriptomics data

Serval is a modular framework for decoding spatial transcriptomics data that introduces Cosine, a method improving transcript recovery and correlation with expression references.

Advancing Wildlife Image Analysis: A Graph Attention Contrastive Learning Approach for Region-Specific Mammal Classification

This paper develops a region-specific AI model for mammal classification using graph attention contrastive learning, achieving high accuracy in recognizing local species and improving data cleaning efficiency.

A regulatory T cell signature provides a shared molecular basis for the therapeutic window of opportunity in rheumatic disease

The paper identifies a shared Treg dysfunction signature across rheumatic diseases, suggesting a therapeutic window of opportunity for Treg-targeted treatments.

Optimizing an Automated Processing Pipeline for Regional Macromolecular Proton Fraction and Volume Measurements in the Brain

The paper evaluates FreeSurfer parcellation workflows using MPF maps versus MPRAGE images to assess reliability and repeatability of regional MPF and volume estimates in the brain.

Autoencoders for unsupervised analysis of rat myeloarchitecture

This study uses unsupervised deep learning to analyze rat brain histology, revealing tissue organization and detecting pathological changes without manual annotations.

Major microbiota transitions across liver disease progression are mediated by key taxa linking host environments and microbial communities

The paper uses an energy landscape analysis framework to identify key microbial taxa linked to liver disease progression and host environments.

SubCortexMesh: A Python toolbox for surface-based analysis of subcortical brain regions

SubCortexMesh provides a Python toolbox for surface-based analysis of subcortical brain regions, enabling automated surface estimation and shape-related metrics computation.

An automated machine vision-based index for Rett Syndrome provides a generalizable framework for modeling rare disease therapeutics

This paper develops an automated machine vision-based index for Rett Syndrome that improves preclinical phenotyping by detecting disease-relevant behaviors and reducing animal use.

HiMaLAYAS: enrichment-based annotation and visualization of hierarchically clustered matrices

HiMaLAYAS, a Python package, cuts dendrograms, tests clusters for categorical annotation enrichment (hypergeometric, Benjamini-Hochberg FDR), and renders significant annotations beside clustered heatmaps in one workflow.

Physiological Aging and Cardiovascular Disease Distinctly Remodel the Human Cardiac Lymphatic Endothelium

This study identifies age- and disease-specific remodeling of cardiac lymphatic endothelial cells through single-nucleus transcriptomics and spatial analysis.

Biologically Informed Multi-Omics Integration Reveals Clinically Meaningful Patient Representations in Acute Myeloid Leukemia

This paper introduces SurvMOCA-GNN, a multi-omics integration framework that improves patient stratification in AML by incorporating biological networks and clinical data.

Smaller Genomes and Shorter Prophage Sequences Differentiate Clinical from Environmental Isolates of Pseudomonas aeruginosa

This study compares genome features of Pseudomonas aeruginosa isolates from cystic fibrosis patients and environmental sources, finding smaller genomes and shorter prophage sequences in clinical isolates.

Topologically-based parameter inference for agent-based model selection from spatiotemporal cellular data

The paper introduces TOPAZ, a framework that uses topological data analysis and Bayesian methods to infer agent-based models from spatiotemporal cellular data, showing it can accurately recover model parameters and distinguish between models.

Complex roles for a conserved two-component system in a honey bee symbiosis

This study identifies the conserved two-component system ChvGI as essential for the honey bee symbiont Bombella apis to survive in harsh host environments and regulate key bacterial behaviors.

Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria

This paper develops a deep learning model to identify drug modes of action from high-throughput images of chemically and genetically perturbed Corynebacteria.

Discovering Heterogeneous Neurodegenerative Disease Patterns From MRI Data for Improved Prediction

This paper introduces a mixture-of-experts framework for identifying clinically meaningful subtypes in neurodegenerative diseases, improving prediction of progression to Alzheimer's disease.

ClustSIGNAL identifies cell types and subtypes using an adaptive smoothing approach for scalable spatial omics clustering

ClustSIGNAL improves spatial transcriptomics clustering by adapting smoothing based on neighbourhood complexity, enabling scalable analysis of large datasets.

EISCA and EISTA: Full-Spectrum Pipelines for Single-Cell and Spatial Transcriptomics Analysis

EISCA and EISTA are pipelines for single-cell and spatial transcriptomics analysis that provide standardized, modular workflows for data processing and downstream analysis.

Benchmarking 16S rRNA gene amplicon analysis in high-diversity microbial communities reveals fundamental trade-offs in clustering and denoising

This study benchmarks 16S rRNA gene analysis pipelines in high-diversity datasets, revealing trade-offs between clustering accuracy, species recovery, and abundance reconstruction.

WHAT IS NORMAL? MULTIMODAL CHARACTERIZATION OF NON-DISEASED PEDIATRIC DUODENAL BIOPSIES USING MACHINE LEARNING IMAGE ANALYSIS AND TRANSCRIPTOMICS

The paper characterizes non-diseased pediatric duodenal biopsies across multiple domains, finding clinical and transcriptomic heterogeneity but limited histologic differences.