dimensionality reduction

TAGINE: Fast Taxonomy-based Feature Engineering for Microbiome Analysis

TAGINE optimizes microbiome feature sets using taxonomy-based splitting, reducing features while maintaining accuracy and speed.

The electro-MICA toolbox for integrating electrophysiology within multimodal imaging and connectomics workflows

electro-MICA projects electrophysiological features onto cortical surfaces using numerical solutions to electromagnetic equations, outperforming conventional models in iEEG validation.

Spine-Prints: Transposing Brain Fingerprints to the Spinal Cord

This paper demonstrates that functional connectivity patterns in the human cervical spinal cord exhibit individual-specific properties, suggesting the existence of a spinal cord 'fingerprint' similar to brain fingerprints.

Rapid cortical mapping with cross-participant encoding models

This study introduces cross-participant encoding models for rapid cortical mapping, showing improved accuracy and efficiency compared to within-participant models.

Brain functional network connectivity interpolation characterizes the neuropsychiatric continuum and heterogeneity

This paper introduces a variational autoencoder framework to interpolate functional network connectivity data across neuropsychiatric disorders, revealing continuous gradients and heterogeneity.

Modelling Discrete States and Long-Term Dynamics in Functional Brain Networks

This paper introduces DyNeStE, a model that combines recurrent neural networks with Bayesian inference to capture long-term dynamics in brain networks while maintaining interpretability, outperforming HMMs in simulations and resting-state MEG data.

Sparse dimensionality reduction for analyzing single-cell-resolved interactions

The paper introduces a sparse dimensionality reduction workflow for analyzing single-cell cell-cell interactions using the Boosting Autoencoder approach, with a Jupyter notebook for implementation.

SUITPy: A Python-based toolbox for the analysis of cerebellar functional and anatomical imaging data across the human lifespan

SUITPy improves cerebellar imaging analysis by isolating the cerebellum with a U-Net model, enhancing alignment and reducing contamination from surrounding cortical structures.

Holotomography-driven learning for in-silico staining of single cells in flow cytometry avoiding co-registration

This paper introduces a Holotomography-driven learning method for virtual staining in flow cytometry without requiring co-registration, enabling label-free single-cell analysis.

RAVEN: Robust, generalizable, multi-resolution structural MRI upsampling using Autoencoders

RAVEN upsamples brain MRIs to higher resolution, preserving anatomical details across various modalities and field strengths.

Modelling variability in functional brain networks using embeddings

This paper introduces HIVE, a method using embeddings and HMMs to model individual brain network variability across groups, showing improved performance on simulated and real MEG data.

Excessive Censoring Degrades Individual-Specific Cortical Parcellations and Personalized TMS Targets

The paper evaluates how different censoring strategies affect cortical parcellations and TMS targets in rs-fMRI, finding that lenient censoring yields better results than strict censoring.

Morphometrics of the preserved post-surgical hemisphere in pediatric drug-resistant epilepsy and implications for post-operative cognition

This study compares morphometric differences in pediatric epilepsy patients with preserved hemispheres to healthy controls, finding reduced gray matter and cortical measures in those with preserved right hemispheres.

Scalable Non-negative Matrix Factorization of the Human Cell Census Reveals Interpretable Transcriptional Programs

The paper presents a scalable Non-negative Matrix Factorization of the Human Cell Census to create interpretable transcriptional programs for biological reasoning.

Bridging the Dimensional Gap from Planar Spatial Transcriptomics to 3D Cell Atlases

SpatialZ generates dense 3D cell atlases from planar spatial transcriptomics data by reconstructing virtual slices, validated with real 3D data and enabling new spatial analyses.

Kernel-Based Style Transfer Mapping for Cross-Subject Biological Signal Classification

This paper introduces a kernel-based style transfer mapping method for cross-subject biosignal classification, showing improved accuracy over linear methods.

Multi-task spatial omics analytics for high-precision modeling of tissue architecture with STAX

STAX is a multi-task learning platform for spatial omics that addresses multiple analytical challenges, offering superior performance and biological insights.

TransBrain: A computational framework for translating brain-wide phenotypes between humans and mice

TransBrain translates brain-wide phenotypes between humans and mice, improving homology mapping and enabling cross-species analysis of brain organization and function.

STEAP4+ neutrophils: a promising circulating biomarker for lung metastasis

The paper identifies STEAP4+ neutrophils as a circulating biomarker for lung metastasis, validated in both human and mouse models.

MAGNET: an all-in-one foundation model for cross-modal and cross-dimensional microscopic image restoration

MAGNET is a foundation model for microscopic image restoration that handles multiple modalities and tasks, achieving state-of-the-art results across various restoration tasks.

Self-Supervised Missing Wedge Correction in Soft X-Ray Tomography: Towards Accurate Cellular Morphology and Volume Quantification

This paper introduces a self-supervised model to correct missing wedge artifacts in soft X-ray tomography, improving volume quantification and morphology accuracy in cellular structures.

MMonitor: Software for Real-Time Monitoring of Microbial Communities Using Long Reads

MMonitor provides real-time analysis and visualization of metagenomic data, enabling dynamic microbiome research through automated pipelines and interactive dashboards.

DendroTweaks: An interactive approach for unraveling dendritic dynamics

DendroTweaks provides an interactive toolbox for exploring and validating detailed biophysical neuronal models with active dendrites.

IndivSTATIS: A multivariate approach to analyze brain network configurations with individualized parcellation

IndivSTATIS integrates individualized brain parcellations into a shared component space to compare network configurations and predict individual differences.

Context-dependent low-dimensional neural dynamics unfold in distinct subspaces, dimensionality, and dynamical strength for natural walking and reaching

The paper compares neural dynamics during walking and reaching, finding that reaching has higher dimensionality and faster decay in dynamical systems than walking.

Joint representation of spliced and unspliced RNA expands information content in single-cell expression data

The paper shows that preserving both spliced and unspliced RNA data in single-cell analysis reveals more latent structure than using either alone or their sum.

Probabilistic Brain MR Image Transformation Using Generative Models

This paper compares probabilistic generative models for MR image transformation, finding NCSN most accurate and DDPM best at detecting out-of-distribution inputs.

Claustrum volume in human lifespan trajectory and effect of age, hemisphere, and sex

This study examines how age, hemisphere, and sex affect claustrum volume across the human lifespan using MRI data from 3,474 healthy participants.

Pathway Anchored Multimodal Clustering Reveals Circuit Level Signatures in Parkinsons Disease

The paper introduces a pathway-anchored clustering framework to analyze multimodal imaging data in Parkinson's disease, identifying stable patient clusters and structure-function associations.

High-Parameter Spatial Multi-Omics through Histology-Anchored Integration

This paper introduces SpatialEx and SpatialEx+ frameworks to integrate spatial multi-omics data using histology as an anchor, achieving high-parameter co-profiling across tissue sections.