dimensionality reduction

Metabolic Connectivity Gradients of the Human Brain

This study identifies four metabolic connectivity gradients in the human brain, linking metabolic activity, cortical structure, and cognitive function across the lifespan.

Major transitions in early coral development: novel insights enabled by visualisation of a comprehensive transcriptomic dataset for Acropora millepora

The paper provides a comprehensive transcriptomic dataset and visualization tool for Acropora millepora development, revealing major gene expression transitions during gastrulation and post-settlement.

MCA: A Multicellular analysis Calcium Imaging toolbox for ImageJ

MCA is an ImageJ-based tool for analyzing calcium imaging data, validated on zebrafish datasets and applicable to multiple organisms and modalities.

Modeling 3D Mesoscaled Neuronal Complexity through Learning-based Dynamic Morphometric Convolution

This paper introduces a convolution framework for neuronal morphology reconstruction, showing improved performance on mesoscaled neuronal datasets.

BULLKpy: An AnnData-Inspired Unified Framework for Comprehensive Bulk OMICs Analysis

BULLKpy provides a unified framework for bulk OMICs analysis, offering tools for preprocessing, visualization, and integrative cancer research.

stGCL: A versatile cross-modality fusion method based on multi-modal graph contrastive learning for spatial transcriptomics

stGCL integrates multi-modal spatial transcriptomics data using graph contrastive learning to improve clustering and spatial pattern analysis.

A Fully Automated, Data-Driven Approach for Dimensionality Reduction and Clustering in Single-Cell RNA-seq Analysis

The paper introduces a fully automated clustering pipeline for scRNA-seq that improves performance by 10-14% by integrating scLENS with existing tools.

Neuromark Fusion: A Replicable Multimodal Template for Structure-Function Fusion of Brain MRI

The paper develops a normative template for multimodal brain MRI fusion using ICA, showing it guides new dataset analyses and correlates with age.

High-fidelity bioimage restoration via adversarial learning

This paper introduces NAFNet GAN, a bioimage restoration framework that achieves high fidelity and low latency, suitable for real-time microscopy applications.

Utility of recombinant envelope domain III as a diagnostic antigen for the specific detection of Kyasanur Forest Disease

This paper develops a specific ELISA test for Kyasanur Forest Disease using recombinant envelope domain III protein as an antigen, showing high specificity and sensitivity.

Beta Diversity Meta-Analysis Shows Transformations Have Broadly Similar Performance in Machine Learning Applications Regardless of Compositional or Phylogenetic Awareness

This study compares beta diversity methods in machine learning, finding no substantial performance difference between phylogenetically aware and simpler methods.

X-intNMF: A Cross- and Intra-Omics Regularized NMF Framework for Multi-Omics Integration

X-intNMF improves multi-omics integration by modeling both cross-omics and intra-omics interactions, outperforming existing methods in cancer phenotype prediction and survival analysis.

Platform Biological Divergence: quantifying gene-level differences between bulk and single-cell transcriptomics in breast cancer

The paper introduces a gene-level divergence score to quantify differences between bulk and single-cell transcriptomics in breast cancer and other tissues, identifying genes that systematically differ between platforms.

SparseAEH: Scalable autoregressive expression histology discovery in spatial transcriptomics via sparse Gaussian kernels

SparseAEH accelerates spatial transcriptomics analysis by using sparse Gaussian kernels, achieving faster computation with accuracy comparable to existing methods.

miniMTI: minimal multiplex tissue imaging enhances biomarker expression prediction from histology

miniMTI reduces the number of molecular markers needed for multiplex tissue imaging by combining H&E with a few measured markers, preserving biological and clinical information.

Patch deconvolution for Fourier light-field microscopy

This paper introduces patch deconvolution to accelerate 3D cellular imaging in Fourier light-field microscopy, achieving faster reconstruction speeds without compromising quality.

A Watershed Algorithm GUI for Personalized fMRI-guided rTMS Target

This paper introduces a watershed algorithm GUI for fMRI-guided rTMS target localization, showing reduced spatial displacement and bias compared to conventional methods.

Deep Variational Autoencoders for Population Genetics

This paper applies variational autoencoders to genomic data to capture population structure, enable dimensionality reduction, and improve data compression across diverse populations.

Latent biophysical diffusion properties underlying cerebral microstructure revealed through multimodal MRI covariation in the squirrel monkey

sf-pediatric: A robust and age-adaptable end-to-end pipeline for pediatric diffusion MRI

sf-pediatric provides an age-adaptable dMRI pipeline for pediatric studies, improving modeling and reproducibility across brain development.

Deep learning-based event classification of mass photometry data for optimal mass measurement at the single-molecule level

This paper introduces a deep learning method to classify mass photometry events, improving single-molecule mass measurement accuracy by reducing artifacts and enhancing resolving power.

Seeing more than schemas: the vmPFC represents imagery- rich mental scenarios

The paper investigates the role of the vmPFC in representing imagery-rich mental scenarios using fMRI and MVPA, finding it encodes detailed visual content beyond abstract representations.

Learning the Shape of Evolutionary Landscapes: Geometric Deep Learning Reveals Hidden Structure in Phenotype-to-Fitness Maps

This paper introduces a geometric deep learning method to model phenotype-to-fitness maps, showing it outperforms linear methods in capturing nonlinear structure and predicting fitness landscapes.

AtlasMap: enabling low-cost, map-style exploration of million-cell single-cell atlases

AtlasMap provides a scalable visualization framework for large single-cell atlases, enabling efficient exploration of million-cell datasets through a tile-based, server-side rendering approach.

Deciphering Multiway Multiscale Brain Network Connectivity:Insights from Birth to 6 Months

This study investigates multiway, multiscale brain network interactions in infants, finding that tri-FNC provide additional insights beyond pairwise interactions during early brain development.

RadarOmics: Intuitive visualisation of multidimensional omics data in ecological, evolutionary, and developmental studies

RadarOmics provides a visualization tool for multidimensional omics data, revealing coordinated molecular responses across biological processes in ecological, evolutionary, and developmental studies.

Mapping Brain Growth and Sex Differences Across Prenatal to Postnatal Development

This study analyzes a large MRI dataset to model age-related brain volume changes and sex differences from prenatal to postnatal development.

Cross-brain transfer of high-performance intracortical speech and handwriting BCIs

This paper demonstrates cross-brain transfer learning for intracortical BCIs decoding speech and handwriting, showing improved performance with limited training data and specific decoder design.

Rhythms and Background (RnB): The Spectroscopy of Sleep Recordings

The paper introduces RnB, a wavelet-based method to separate rhythmic and arrhythmic components in sleep EEG data, improving time-domain analysis of NREM sleep oscillations.

Identification of a Novel miRNA Expression Signature for Lung Adenocarcinoma Using Systematic Machine Learning Optimization

This paper identifies a miRNA signature for lung adenocarcinoma using machine learning on TCGA data, achieving high accuracy and stability.