dimensionality reduction

Subcortex visualization: A toolbox for custom data visualization in the subcortex and cerebellum

The paper introduces subcortex_visualization, an open-source tool for visualizing subcortical and cerebellar data across multiple atlases, enabling reproducible and flexible region-level data visualization.

Enhanced 2D structured illumination microscopy: super-resolution with optical sectioning and reduced reconstruction artifacts

This paper introduces enhanced 2D-SIM to reduce reconstruction artifacts and improve resolution in thick samples using optimized coarse and fine patterns.

Spatiotemporal Patterns and Structural Substrates of Individual Functional Variability in Youth

The paper quantifies spatiotemporal variability in functional parcellation and connectivity across development, finding distinct developmental trajectories and associations with brain structure and cognition.

SILICA: Streamline Independent Component Analysis for Trajectory-Resolved White Matter Decomposition

SILICA decomposes white matter tractograms into population-level statistical components while preserving individual streamline geometry, revealing recognizable brain systems and enabling trajectory-resolved visualization.

The Social Cognition Paradox in Long-Duration Spaceflight: A VEN Fatigue Hypothesis for Duration-Dependent Emotion Recognition Decline

The paper proposes a VEN Fatigue Hypothesis to explain duration-dependent emotion recognition decline in long-duration spaceflight, supported by multi-omics and neuroimaging data.

PIANO: Probabilistic Inference Autoencoder Networks for multi-Omics enables robust generative modeling of gene expression and scales single-cell integration to 100 million cells

PIANO integrates single-cell data across species and modalities, models gene expression, and scales to 100 million cells for drug perturbation analysis.

AdaGeneBudget: Cell-Adaptive Gene-Token Allocation for Efficient Single-Cell Foundation Models

AdaGeneBudget reduces gene-token usage in single-cell foundation models while preserving annotation utility and fine-grained cell identities.

Reliable single-cell perturbations explain and improve model performance

The paper evaluates perturbation reliability in single-cell data and shows that using reliable perturbations improves model performance and reduces training data needs.

Brain2VLM: Hierarchical Alignment Between Cortical Representations and Vision-Language Latent Spaces

A residual MLP beats ridge by Δ≈0.47 correlation decoding CLIP embeddings from higher visual areas, but only Δ≈0.05 to 0.06 decoding Stable Diffusion latents from early visual cortex.

Shared and Distinct High-Dimensional Object Spaces in Human and Macaque Inferotemporal Cortex

The paper aligns human and macaque inferotemporal cortex representations of objects using multivariate cross-species alignment, revealing shared high-dimensional spaces and species-specific differences.

KiMA: Kinematic Motion Analysis for Spinal Cord Injury Research

KiMA provides an open-source tool for analyzing rodent gait and kinematics, integrating pose estimation with automated parameter calculation and visualization.

MSGPCA: Multi-Slice Graph PCA for replicate-aware Spatial Omics analysis

MSGPCA improves spatial omics analysis by decomposing molecular variation into shared and slice-specific factors, enhancing the detection of tissue structure and microenvironmental variation.

Toward Robust Characterization of Dynamic Binding Pockets: Lessons from the HBV Capsid Assembly Modulator Site

The paper develops and validates a method to quantify dynamic protein binding pockets using the HBV capsid assembly modulator site as a model, demonstrating robust performance across conformational states.

Move BeTween modAlities (MBTA) employs flow matching to predict single cell data modalities

MBTA uses flow matching to address structural mismatch between molecular modalities, improving cross-modal translation and enabling multimodal analysis in single-cell data.

A generative model for dimensionality reduction with millions of features and few samples

This paper introduces a deep generative decoder model for dimensionality reduction with millions of features and few samples, showing it outperforms PCA and VAE in tumor classification.

Learning with Recurrence Geometric AI in Spatial Transcriptomics

This paper introduces RGAI, a geometric deep-learning framework for cross-domain analysis of spatial transcriptomics, enabling alignment of latent tissue states across diverse datasets.

Contrast-enhanced micro-XCT as a tool for organismal and reproductive trait observations in corals based on scans of Thesea nivea Deichmann, 1936

This study evaluates contrast-enhanced micro-XCT for visualizing soft tissue structures in corals, demonstrating its utility for systematics and histology.

DNA2Graph enables automated identification of non-linear DNA molecules in electron microscopy

DNA2Graph automates the identification of non-linear DNA molecules in electron microscopy images, significantly reducing the need for manual review and improving structure detection.

BRIDGE: A Computational Workflow from Single Neurons to Network of Mean-Field Models

BRIDGE is a Python pipeline that reconstructs and validates mean-field models from single neuron dynamics, enabling reproducible and reusable large-scale brain simulations.

Neural feature spaces: characterizing the geometry of brain activity across development

The paper characterizes the geometry of brain activity across development by analyzing neural feature spaces in children and adults using EEG data.

Physics-Guided Neural Reconstruction of Cellular Membranes for 3D Electron Microscopy

This paper introduces a physics-informed neural network framework to reconstruct 3D membrane shapes and curvatures from electron microscopy images, showing improved accuracy and mechanical insights.

Towards Video-LLM Driven Workflow for Behavioral Segmentation and Scoring in Mice Performing a Skilled Water Reaching Task: An Evaluation of Recent LLM Models

The paper evaluates video LLMs for automated behavioral segmentation and scoring in mice performing a water-reaching task, finding that Gemini 2.5 Pro achieves high accuracy with specific resolution and visibility requirements.

Musical training-induced plasticity reflects melodic rather than instrumental expertise

This study shows that musical training leads to behavioral generalization but neural plasticity is specific to the learned melody, not the instrument.

An end-to-end framework for single-cell-resolution, whole-transcriptomic spatial profiling in post-mortem human brain

This paper presents an end-to-end framework for single-cell whole-transcriptome spatial profiling of post-mortem human brain tissue, improving library quality and enabling cross-sample harmonization.

Supervised restricted data fusion with common, local & distinct components

PESCAR improves detection of subtle response-related patterns in multi-omics data by integrating response information into multiblock decomposition.

The emergence of the fractal bronchial tree

The paper quantifies the rearrangement of the embryonic bronchial tree into its fractal architecture and identifies biophysical principles governing its formation, showing these principles persist in adulthood and disease.

Machine learning on magnetoencephalography data yields generalizable low-dimensional neural fingerprints that distinguish individuals across task conditions

The paper uses lnBRRR to create low-dimensional neural fingerprints from MEG data that distinguish individuals across tasks, showing they are generalizable and intrinsic.

SpaMTP: Integrative Statistical Analysis and Visualisation of Spatial Metabolomics and Transcriptomics data.

SpaMTP integrates spatial metabolomics and transcriptomics data through a comprehensive analysis pipeline and visualization tools.

Connectivity patterns predictive of cognition, but not affect, reflect a segregated intrinsic network architecture

The paper examines how resting-state network connectivity relates to cognition and affect, finding that cognitive patterns reflect a segregated network architecture while affective patterns show less consistent signatures.

Biophysical characterization of novel biomarkers and bioaffinity reagents (NanoMIPs): on the road for a low-cost diagnostic test for intestinal schistosomiasis

The paper characterizes SmVAL11 and SmVAL13 as potential biomarkers for intestinal schistosomiasis and evaluates their recognition by antibodies and nanoMIPs for diagnostic development.