dimensionality reduction

Spindle provides a compact, searchable index for spatial gene co-expression patterns in large-scale spatial-omics datasets, enabling fast querying and efficient analysis.

msiFlow 2.0 improves MSI data analysis with mass recalibration, lipid annotation, batch correction, and scalability, enhancing accuracy and reducing runtime.

This paper introduces f-LENNS, an AI framework that enhances fMRI resolution without retraining, improving spatial fidelity and generalizing to atypical brain function.

This paper introduces SHARP, a method using cosmological web analysis to characterize brain ageing and cognitive impairment by analyzing MRI data from CamCAN and OASIS-3.

RoDPAA integrates multi-view microbiome data using dissimilarity-based principal angle analysis, recovering shared structure in IBD cohorts where log-ratio methods failed.

This study uses optical clearing and light-sheet fluorescence microscopy to visualize 3D microanatomy of human head-and-neck tissues and correlate it with conventional histology.

This paper shows PHATE can better capture continuous population structure in genomic data than PCA or UMAP by tuning scale and balancing populations.

MUTUAL enables cross-modality analysis between transcriptome and chromatin by learning a shared RNA-ATAC space from multiome data without refitting.

The paper evaluates segmentation methods for reconstructing cell-like profiles from spatial transcriptomics data but finds no reliable method under the given constraints.

A reaction-diffusion model fitted to shell-averaged tumor density from one pre-treatment MRI estimates glioblastoma migration/proliferation ratio (D/k); in BraTS 2017, higher D/k went with shorter overall survival.

MiniMAP generates custom paediatric musculoskeletal models using CT data and demographic factors, achieving accurate bone geometry predictions with minimal error.

This paper decomposes whole-brain effective connectivity to reveal multiscale hierarchical dynamics and their relation to temporal irreversibility and individual-specific signatures.

The paper compares five algorithms for deriving structural covariance networks in the thalamocortical system and finds they emphasize different neurobiological aspects based on their mathematical properties.

The paper investigates drift in human EEG responses to images across sessions, finding coordinated drift along image identity dimensions and preserved global structure.

The paper evaluates sparse autoencoder features on various embeddings, finding that reproducibility does not guarantee meaningfulness, and proposes reporting features with concept coverage and purity.

The paper examines how auditory tracking changes during wakefulness and propofol anesthesia by analyzing response magnitude, temporal alignment, and anatomical distribution using sEEG data.

ProtCell connects fragmented proteomic profiles, extends information beyond measured panels, and guides more informative measurements.

clrcycle is a dimensionality reduction method for cyclic data that captures phase and magnitude in biological systems, showing effectiveness in circadian and cell-cycle analysis.

This paper introduces M/EEG-FUNCOIN, a normative modeling approach for whole-brain functional connectivity in MEG data, showing improved characterization of age and sex-related patterns and detection of connectivity deviations linked to cognitive ability.

The paper investigates the cellular and mitochondrial factors influencing regional glucose metabolism in the human cortex using multimodal data integration.

Streamline CNV is a Nextflow pipeline for CNV analysis that simplifies processing, visualization, and interpretation of copy number data across various sequencing types and species.

This study shows that heart/foregut-like structures form from human pluripotent stem cells, developing into vascularized cardiac organoids with multiple cell types.

SpacePath improves spatial metabolomics analysis by handling molecular ambiguity and identifying novel lipid families in spatial datasets.

The paper integrates gene expression and B cell receptor data to capture complementary B cell information, revealing substructure supported by both transcriptional and receptor features.

This paper introduces Rotational Component Analysis (RCA) to detect low-dimensional rotational dynamics in neural data and shows these dynamics constrain cue-evoked behavior and learning across species.

CPMsi is a computational pipeline that efficiently processes and integrates large-scale MSI data, enabling faster analysis and discovery of molecular patterns across tissue sections.

MorphCell learns interpretable 3D cellular morphology representations from point clouds, transferring across imaging modalities and biological contexts with improved classification performance.

scOmnom provides a scalable, semi-automated workflow for single-cell RNA-seq analysis, enabling auditable clustering-resolution selection and annotation refinement across large datasets.

The paper evaluates SABLE-MO's performance in identifying shared factors in multi-omics data, finding that stricter retention reduces errors but does not eliminate them.

The paper compares left ventricular phenotypes across humans, chimpanzees, and macaques to identify structural and functional traits associated with higher stroke volume in humans.