dimensionality reduction

High-temporal resolution metabolic connectivity resolved by component-based noise correction

This paper develops a noise correction method for high-temporal resolution fPET data, showing it improves metabolic connectivity estimation across different scanners and frequency bands.

Ion Mobility-Enhanced LA-REIMS Improves Molecular Resolution in Ambient Biofluid Metabolomics

This paper improves molecular resolution in ambient metabolomics by integrating ion mobility spectrometry with LA-REIMS, reducing background noise and enhancing chemical specificity.

Automated morphometry and weight prediction of juvenile Chinook Salmon leveraging open-source deep learning models

This paper develops an automated system using deep learning to estimate morphometric measurements and predict weight of juvenile Chinook Salmon from 2D images with high accuracy.

Unified Multi-Cohort Harmonisation and Normative Modelling of Neuroimaging Data via Hierarchical GAMLSS

This paper introduces a hierarchical GAMLSS framework for harmonizing and modeling neuroimaging data across multiple cohorts, showing improved removal of cohort effects and preservation of biological signals.

A hand biomechanics dataset of kinematics, kinetics, electromyography, and imaging in healthy adults

The paper introduces a biomechanics hand dataset containing kinematics, kinetics, electromyography, and imaging data from healthy adults to support musculoskeletal modeling.

Predicting Brain Volumes from Anthropometric and Demographic Features: Insights from UK Biobank Neuroimaging Data

The paper predicts brain volumes from anthropometric and demographic features using UK Biobank data, finding strong sex-based predictions for TIV and age-based predictions for other volumes.

Multi-task fMRI outperforms resting-state fMRI for revealing task-invariant organization of the human brain

This study shows that multi-task fMRI better predicts brain functional organization than resting-state fMRI across diverse tasks and datasets.

Paradoxical influences of prediction are resolved across time

The paper tests an opposing process theory of perception using EEG data, showing expectation influences change over time to support both accurate perception and learning from unexpected events.

BIBSNet: A Deep Learning Baby Image Brain Segmentation Network for MRI Scans

BIBSNet is a deep learning model for infant brain segmentation in MRI scans that outperforms JLF in accuracy and speed, with compatible outputs for further analysis.

Offline Reconstruction of Diffusion MRI Acquisitions for Comparison Between Complex PCA-based and AI-based Denoising

The paper develops an offline dMRI reconstruction pipeline and compares PCA-based and AI-based denoising methods on high-resolution dMRI data.

Mesoscale molecular architecture of the human striatum across cell types and lifespan

The paper maps a mesoscale molecular architecture of the human striatum across cell types and age, revealing zonal differences in gene expression and aging effects.

Scanless temporal focusing enables high-speed three-dimensional quantitative phase microscopy

This paper introduces a scanless, high-speed 3D quantitative phase microscopy technique with improved resolution and reduced noise, enabling label-free volumetric imaging of biological samples.

ESGI: Efficient splitting of generic indices in single-cellsequencing data

ESGI provides a flexible framework for demultiplexing and processing single-cell sequencing data with arbitrary barcode architectures, supporting complex and emerging experimental designs.

A Resolution-Agnostic Geometric Transformer for Chromosome Modeling Using Inertial Frame

This paper introduces InertialGenome, a transformer-based framework for resolution-agnostic chromosome 3D structure reconstruction, showing improved performance across multiple resolutions and experimental validation.

Toward Computationally Complete Spatial Omics

COSIE is a computational framework that integrates multiple spatial omics modalities to generate high-resolution molecular landscapes, outperforming existing methods across diverse datasets.

ggDNAvis: a ggplot2-based R package for creating high-quality DNA sequence and modification visualisations

ggDNAvis provides an R package for high-quality DNA sequence and methylation visualizations with customizable features and support for various data formats.

Visuomotor coordination on the road: low-dimensional representations reveal adaptive, context-dependent reductions in the dimensionality of natural driving behavior

This study identifies low-dimensional visuomotor coordination patterns in natural driving behavior, showing they simplify during critical events and distinguish driving modes.

A foundation AI model enhances electron microscopy image analysis

DF5T improves EM image quality through five tasks, enhancing segmentation and 3D restoration of organelles.

Single Capture Quantitative Oblique Back-Illumination Microscopy

This paper introduces single-capture qOBM, a deep learning-enhanced technique for fast, label-free 3D phase imaging, achieving accuracy comparable to traditional methods with improved speed and simplicity.

MONICA: A Web Application for Automated Whole Optic Nerve Contour Extraction and Morphometric Analysis Validated Across Taxonomic Orders and Image Quality Levels

MONICA is a web-based tool that automatically extracts optic nerve boundaries and calculates morphometric metrics, validated across species and image qualities.

Scalable mass-spectrometry-based molecular phylogeny with TreeMS2

TreeMS2 constructs molecular phylogenies from raw MS/MS data, revealing relationships based on molecular phenotype and identifying deviations from genetic-based trees.

Atlas-scale spatially aware clustering with support for 3D and multimodal data using SpatialLeiden

The paper extends SpatialLeiden to handle atlas-scale, 3D, and multimodal spatial omics data, improving modularity and scalability across multiple samples.

Beyond alignment: synergistic integration is required for multimodal cell foundation models

This paper introduces a metric to evaluate synergistic integration in multimodal cell models and shows when it benefits tasks over unimodal approaches.

Deep Learning-Enhanced TopoStats for the Automated Quantification of DNA and Complex Biomolecular Structures

The paper introduces an enhanced TopoStats tool using deep learning to automate and quantify AFM data, enabling detailed structural analysis of biomolecules.

Comparative analysis of nuclei isolation methods for brain single-nucleus RNA sequencing

This study compares three nuclei isolation methods for brain snRNA-seq, finding protocol-dependent differences in cell type proportions, transcriptional homogeneity, and RNA contamination levels.

GxP Single-cell RNA-seq and Spatial Transcriptomics end-to-end pipeline for clinical research

The paper introduces NNclinSSOAP, a GxP-ready pipeline for processing single-cell and spatial transcriptomics data, enabling reproducible and scalable analysis in clinical settings.

GALA: A Unified Landmark-Free Framework for Coarse-to-Fine Spatial Alignment Across Resolutions and Modalities in Spatial Transcriptomics

GALA provides a landmark-free framework for spatial alignment across resolutions and modalities in spatial transcriptomics, improving accuracy and efficiency.

Procrustean pseudo-landmark methods in Python to measure massive quantities of leaf shape data

The paper introduces a Python-based method using pseudo-landmarks and Procrustes analysis to compare leaf shapes across species and development, showing shape transitions and genetic correlations.

Next generation statistical framework for next generation spatial transcriptomics data

This paper introduces TranspaceR, an R package with statistical methods for analyzing spatial transcriptomics data, improving quality control, gene selection, and normalization for large-scale datasets.

stVCR: Spatiotemporal dynamics of single cells

stVCR reconstructs spatiotemporal dynamics from time-series spatial transcriptome data by integrating generative deep learning with optimal transport and spatial priors.