dimensionality reduction

Clonal embeddings allow exploratory analysis of lineage-resolved single-cell data

The paper introduces clone2vec, a machine learning method for analyzing lineage-resolved single-cell data, revealing clonal patterns and continuous variation in development and disease.

Direction Selectivity in Naturalistic Action Observation: Distributed Representations Across the Action Observation Network

This study uses fMRI and MVPA/RSA to show that direction selectivity in action observation is distributed across multiple brain regions, including early visual and higher-order parietal and frontal areas.

Functional connectivity correlates of the hierarchical p-factor model in youth at neurodevelopmental risk

The paper examines functional connectivity patterns in youth at neurodevelopmental risk, linking mental health dimensions to brain network organization.

Active subspace learning for coarse-grained molecular dynamics

This paper introduces ASCG, a framework for coarse-graining molecular dynamics that learns reduced variables from atomistic simulations, achieving accurate free energy surfaces and faster timesteps with less training data.

Age-dependent spatial transfer of cortical harmonics to scalp EEG in infancy

The paper investigates how spatial brain coordinates change with age in infants using EEG and cortical harmonics, finding that age-specific templates and tracking improve consistency across developmental stages.

Clustering Strategies Improve Structure-Preserving Visualization of Single-Cell RNA-seq Data with CBMAP

This study evaluates CBMAP for scRNA-seq visualization, showing that clustering strategies significantly affect embedding quality and that Secuer improves global structure preservation.

A Minimal Regulatory Spatial Model for Emergent Multicellular Organization in Dissipative Environments

The paper introduces Evoscope, a computational framework that generates multicellular organization from minimal regulatory rules and demonstrates that morphology encodes internal regulatory dynamics through representation learning.

Cerebellar Gray Matter Volume Changes Across Development: Posterolateral and Vermal Transient Increases during Adolescence

This study examines cerebellar gray matter volume changes across development, finding peak volumes in adolescence for specific regions, with no adult regions exceeding adolescent volumes.

Segzoo: a turnkey system that summarizes genome annotations

Segzoo simplifies genome annotation analysis by automating data retrieval and analysis, providing a single visualization of results.

AlveolEye: Rapid and precise lung morphometry guided by computer vision

AlveolEye improves lung morphometry by using computer vision to rapidly and reproducibly calculate MLI and ASVD from H&E images, reducing variability and increasing precision across observers.

Yomix: An Interactive Tool for the Exploration of Low-Dimensional Embeddings in Omics Data

Yomix is an interactive tool for exploring low-dimensional embeddings in omics data, allowing users to define subsets, compute feature signatures, and compare distributions.

Automated Segmentation of Hepatic Vessels and Lobules in Whole-Slide Images Using U-Net Models

The paper develops a deep learning pipeline using U-Net models to segment hepatic vessels and lobules in histological images, achieving high Dice scores for various structures.

Multidimensional dynamics of object representations in the human visual system

The paper examines the temporal dynamics and latent dimensional structure of natural object representations in EEG and MEG data, revealing rapid dimensionality expansion and unexplained neural variance.

BundleWarp: Enhancing White Matter Tractometry and Morphometry with Precise Neuronal Mapping using Streamline-based Nonlinear Registration

BundleWarp improves white matter tractometry by aligning tracts while preserving anatomical features, enhancing sensitivity to disease-related changes in conditions like Alzheimer's and Parkinson's.

SMEW: An interactive multi-scale toolkit for cross-condition and network-based analysis of spatial metabolomics data

SMEW provides a code-free, interactive platform for analyzing spatial metabolomics data across multiple scales and conditions to identify metabolic patterns and biological pathways.

Morphological differences along the radial gradient of hippocampal area CA2 pyramidal neuron dendrites

The paper examines dendritic morphology of CA2 and CA1 pyramidal neurons, finding gradual morphological changes along the radial axis that suggest a continuum rather than distinct subtypes.

Data-driven lifespan transitions: cortical morphometry and intrinsic differences across network scales

This paper identifies lifespan transitions in cortical morphometry using a data-driven framework and shows that morphometric features exhibit distinct network organisation patterns across age.

charisma: An R package to perform reproducible color characterization of digital images for biological studies

The paper introduces the charisma R package for reproducible color characterization of digital images, demonstrating its utility in analyzing color evolution in birds.

New high accuracy diagnostics for avian Aspergillus fumigatus infection using Nanopore methylation sequencing of host cell-free DNA and machine learning prediction

The paper develops three diagnostic tests for Aspergillus fumigatus infection in chickens using methylation markers from serum cell-free DNA and machine learning, achieving high accuracy.

The language network responds robustly to sentences across diverse tasks

The paper investigates the stability of language network responses across different tasks and compares it to the multiple demand network, finding robust language processing in the language network and task-dependent responses in the MD network.

Characterization and Validation of Compressed Sensing for Time-of-Flight MRI Angiography of the Human Brain at 3T and 7T

This study evaluates compressed sensing in TOF-MRA at 3T and 7T, finding significant differences in CNR and vessel diameter measurements across CS factors.

H2O: A Foundation Model Bridging Histopathology to Spatial Multi-Omics Profiling

H2O predicts spatial transcriptomics and proteomics from H&E images using a contrastive learning framework, outperforming existing models and recovering biologically relevant cell-cell communication.

Voronoi tessellation as a complement or replacement for confidence ellipses in the visualization of data projection and clustering results

The paper compares Voronoi tessellation and confidence ellipses for visualizing 2D data projections, finding Voronoi better reveals group overlaps and heterogeneity while confidence ellipses better identify outliers.

Information Geometry Reconciles Discrete and Continuous Variation in Single-Cell and Spatial Transcriptomic Analysis

GAIA provides a framework for analyzing single-cell and spatial transcriptomic data by reconciling discrete and continuous gene expression variation through information geometry.

SpaceBender: Denoising Spatial Transcriptomics Data to Enhance Biological Signals

SpaceBender denoises spatial transcriptomics data by leveraging spatial information, improving biological signal clarity and statistical significance in simulations and real tissues.

DeepBranchAI: A Novel Cascade Workflow Enabling Accessible 3D Branching Network Segmentation

DeepBranchAI reduces annotation time for 3D branching network segmentation by using a cascade workflow that transforms sparse labels into comprehensive training data.

Structure-guided, physics-aware reconstruction expands scan-limited multiphoton imaging

SPARC improves temporal and spatial resolution in scan-limited multiphoton imaging by integrating denoising and deep upsampling with structural and physical constraints.

CHORD: a framework for cross-species single-cell integration across gene, cell and cell-type levels

CHORD integrates cross-species single-cell transcriptomic data to learn gene, cell, and cell-type representations, enabling cell-type annotation and cross-species comparison of developmental and phenotypic patterns.

Parallel processing chains span cytoarchitectures to organize association cortex

The paper identifies parallel processing chains in association cortex using multiple functional mapping modalities, showing they are experience-driven and organized across different cytoarchitectures.

SIMBA: an agentic AI platform for single-molecule multi-dimensional imaging

SIMBA is an AI platform that integrates single-molecule imaging analysis with deep learning, enabling automated and interactive processing of multi-dimensional fluorescence data.