dimensionality reduction

How the brain distinguishes a bilingual's languages is partly shared across people and partly their own

The paper decodes language state in bilinguals using fMRI and identifies shared and individual brain organization patterns.

Unified Network Spectroscopy: Inferring Reduced Biological Dynamics from Fluctuations under Structured Noise and Broken Ergodicity

This paper introduces Unified Network Spectroscopy (UNS), a method to infer biological dynamics from fluctuations, addressing issues with noise structure and ergodicity.

MOSAIC: Learning Graph Node Embeddings from Spectrally Isolated Dominant Subspaces of Accumulated Diffusion Operators

MOSAIC learns graph node embeddings by analyzing dominant spectral components of diffusion operators, outperforming existing methods in biomedical graph tasks.

ASTRA enables zero-shot super-resolution of spatial transcriptomics across capture geometries

ASTRA enables zero-shot super-resolution of spatial transcriptomics across different capture geometries, improving accuracy and efficiency compared to existing methods.

Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity

STARIT converts spatial transcriptomics data into image tensors for deep learning analysis, enabling subcellular heterogeneity-based cell state identification.

Deep Learning-Meets-Active Surfaces: A Unified Framework for Multi-Object Segmentation and Shape Analysis in 3D Fluorescence Microscopy

This paper introduces Nagini3D, a 3D image segmentation method combining deep learning and active surfaces for improved shape analysis and consistency across 3D volumes.

Intrinsic dimensionality of deep learning representations reveals cell death-associated heterogeneity in Parkinsons disease iPSC-derived neurons

The paper uses deep learning to identify cell death-related heterogeneity in Parkinson's disease iPSC-derived neurons by analyzing intrinsic dimensionality.

NucLogic: Logic-based geometric 3D nuclear segmentation for fast and robust analysis of challenging biological imaging data

NucLogic provides a fast and robust 3D nuclear segmentation method that outperforms existing tools at low SNR and enables quantitative analysis of challenging biological imaging data.

LGTM: Gaussian Process Modulated Neural Topic Modeling for Longitudinal Microbiome

LGTM couples a neural topic model with additive basis-function Gaussian processes, learning microbial co-abundance topics and how covariates relate to their trajectories in longitudinal gut microbiome data.

Explainable t-SNE for Single-Cell RNA-seq Data Analysis: A Cell-DrivenInformation Fusion Framework

The paper introduces c-UMAP, a cell-driven information fusion framework for single-cell RNA-seq data that improves clustering accuracy and interpretability over traditional methods.

Slide-level batch structure limits histology-guided supervision of transcriptomic foundation models

This paper investigates whether histology can improve transcriptomic foundation models by providing cross-modal supervision, but finds limited benefits due to slide-specific structure in gene-expression embeddings.

An information-borrowing Bayesian method for inferring high-dimensional population-level brain connectivity from small samples

The paper introduces a Bayesian method for estimating population-level brain connectivity from small samples, showing improved accuracy over existing methods in simulations and real data.

Biology-guided machine learning for robust anatomical correspondence across biodiversity datasets

This paper introduces a biology-guided machine learning method for automated anatomical landmark transfer across diverse biological datasets, showing significant improvements in accuracy and robustness under severe perturbations.

The impact of behavioural activity on the EEG power spectrum, its source localisation, and global functional connectivity in rats

This study examines how behavioural activity affects EEG power spectrum, source localization, and global functional connectivity in freely moving rats, identifying specific frequency band changes.

A spectral partial information decomposition framework for quantifying information about cognitive variables in oscillatory brain networks

This paper introduces NeOPID, a framework to quantify information in brain oscillations, showing phase and amplitude co-modulations act as complementary coding channels with redundant and synergistic components.

A dataset of differentiable biologically-derived single neuron models

The paper presents a database of over 1,000 differentiable single-neuron models fitted to mouse and human patch-clamp recordings, with PyTorch code for integration into machine learning.

Automated inference of respiratory and syringeal biomechanical trajectories from birdsong acoustics

This paper introduces VIBE, a tool that automatically infers biomechanical control parameters from birdsong acoustics, validated against empirical measurements and neural data.

Decoding brain anatomy from neuronal neighborhoods with MYCEL

The paper introduces MYCEL, a graph neural network that improves decoding of brain anatomy from neuronal neighborhoods by learning local pooling, outperforming fixed aggregation on multiple datasets.

AREION: A Foundation Model for Atlas-Agnostic Representation Learning of Brain Connectome

AREION learns atlas-agnostic representations of brain connectomes, outperforming baselines with fewer parameters and strong transferability across atlases.

SFUMATO: Bayesian probabilistic clustering for uncertainty-aware spatialtranscriptomics analysis and mapping

SFUMATO provides a Bayesian probabilistic framework for spatial transcriptomics that captures uncertainty and enables continuous visualization of transcriptional domains.

Toward A Whole-Brain Interface Enabled by High-Resolution Surface Electrophysiology

This paper presents a functional atlas of the human central nervous system using high-resolution surface electrophysiology from 70 patients, revealing conserved electrophysiological patterns and enabling neuroprosthetic applications.

Lineage-informed factor analysis reveals heritable programs of single-cell gene expression

The paper introduces scPFA, a lineage-informed factor analysis method, to uncover heritable gene expression programs from single-cell lineage-tracing data.

Interpretable models for scRNA-seq data embedding with multi-scale structure preservation

This paper introduces two tools for improving the trustworthiness of single-cell dimensionality reduction by enhancing quality metrics and multi-scale structure preservation.

Foveation as self-supervision signal: Blur masks beat blank masks for learning robust visual representations

This paper introduces blur and retinal masks as self-supervision signals for vision transformers, showing improved robustness and generalization in visual representation learning.

CycloCross: Adversarial single-cell RNA-seq data translation across species

Translating cells between mouse, macaque and human scRNA-seq with a CycleGAN, without ortholog mapping, preserved developmental time structure, imputed missing states and produced more realistic synthetic cells than scGAN.

DisenTE: Sparse Pattern-Context Modeling for Interpretable Translation-Efficiency Matrix Completion

DisenTE improves translation-efficiency matrix completion by modeling sparse sequence-context patterns, achieving higher accuracy than existing methods.

A Single, Reproducible Dimension Organizes Associations Between the Early Environment and the Developing Brain

The paper identifies a single adversity-brain dimension linking childhood environments to neurodevelopment, primarily driven by socioeconomic deprivation.

Resting state EEG microstates: is a new FORM all you need?

The paper introduces FORM, a method that captures microstate geometry from EEG data independently of microstate solutions, showing high explanatory power for microstate maps and template organization.

Deciphering the gene-centric spatial dynamics across tissue and time with GeneSPOT

GeneSPOT is a gene-centric framework that characterizes spatial gene relationships and their reorganization across biological conditions and time.

SILICA-SNC: FROM STREAMLINES TO NETWORKS

SILICA-SNC transforms whole brain tractography into a network representation, revealing organized white matter architecture and coupling patterns.