dimensionality reduction

Catalytic rewiring of RuvC-II catalytic site activates trans-cleavage in Fanzor2

This study shows that catalytic rewiring of Fanzor2's RuvC-II site activates trans-cleavage, enabling new diagnostic applications.

Dynamic Compression Flows for Neuroscience Data

This paper introduces a dual flow approach for modeling neural data, producing more interpretable dynamics and better reconstructions than existing methods.

ComCat: Combating Covariate Effects in Brain Analysis

ComCat improves brain analysis by reducing unwanted variability from heterogeneous datasets, outperforming existing methods in brain age prediction across multiple datasets.

Self-Calibrated Hyperspectral Neural Radiance Fields for 3D Reconstruction of Bone and Bone Analogues

This paper introduces BoNeRF-HS, a self-calibrated hyperspectral neural radiance field for 3D reconstruction of bone and bone analogues, achieving better reconstruction quality and surface detail preservation.

HoloCell: A Generative Foundation Model for Holistic Cellular Modeling

HoloCell is a generative foundation model that integrates epigenomics, transcriptomics, and proteomics data across single-cell multi-omics modalities, demonstrating superior performance in representation learning and cross-modal generation.

Robust thermometry-imaging at sub-micrometer and millisecond-resolution by fluorescence lifetime microscopy allows for additional acquisition of multiple imaging channels

The paper introduces a method to measure temperature with high precision and resolution using fluorescence lifetime microscopy with Cy5 dye, enabling simultaneous multi-channel imaging.

VCBench: A Multi-Dimensional Benchmark for Single-Cell Foundation Models

VCBench evaluates single-cell foundation models across seven dimensions, finding baselines often outperform models, with TranscriptFormer showing unique strengths but tradeoffs.

Automated Segmentation of Prostatic Gold Fiducial Markers for MR-Only Radiotherapy Planning Using Multi-Modal Consensus Deep Learning

The paper develops a multi-model consensus deep learning approach for automated gold fiducial marker segmentation in prostate MRI, achieving high sensitivity and precision.

Exploring Synergies in Brain-Machine Interfaces: Compression vs. Performance

This study evaluates if brain and muscle synergies improve decoding performance in implanted brain-machine interfaces (iBMIs) using dimensionality reduction techniques, finding that they do not enhance performance or generalization.

Multivariate Random Forests for Cross-Modal Multi-Omics Integration

This paper introduces a random forest-based method for multi-omics integration that separates shared and modality-specific signals, showing improved clustering and biological insights in simulations and real datasets.

Benchmarking cell type annotation in spatial transcriptomics: resolving cellular hierarchies, biological fidelity, and dynamic cell states

This study benchmarks 20 cell type annotation methods on spatial transcriptomics data to evaluate their performance in resolving cell types, subtypes, and biological organization across diverse datasets.

Searchlight Optimization Using Representational Similarity Analysis for Subject-Level Voxel Selection in Emotional State Decoding

This paper introduces a subject-level searchlight optimization framework combining univariate and multivariate analyses to identify condition-sensitive voxels for emotional state decoding in fMRI.

BioBrain: A Multi-Agent Framework for Natural Language Driven Quantitative Microscopy Data Analysis

BioBrain translates natural language into reproducible microscopy analysis pipelines, outperforming language models in accuracy while enabling non-experts to analyze complex imaging data.

Increasing the reliability of functional connectivity by predicting long-scan functional connectivity based on short-scan functional connectivity: model exploration, explanation, validation, and application.

This paper develops three generalized linear models to predict long-scan functional connectivity from short-scan data, improving reliability and performance in connectome-based predictive models.

Structural Connectivity Selectively Constrains Intrinsic BOLD Timescales through Graph-Smooth Neural Activity

The paper uses graph signal processing to analyze how structural brain connectivity influences intrinsic BOLD timescales, showing structure-coupled signals strongly correlate with connectivity strength.

Deep Learning-Based Reconstruction: Model Comparison for Variable-Density GRAPPA 1H MRSI

This paper compares deep learning models for improving 1H MRSI reconstruction, finding that U-Net outperforms MultiNet in reducing lipid artifacts and improving metabolite map fidelity.

A detailed investigation of Shared Variance Component Analysis as a tool to characterize neural dimensionality

The paper investigates SVCA and PCA to determine reliable neural dimensionality, finding that reliable dimensionality saturates with increasing neuron count and decreases with higher correlation.

Latent Representations of Early Brain Development: A Multivariate Normative Model of Brain Structure and Behaviour

This paper uses a semi-supervised autoencoder to create multivariate normative models of brain structure and behaviour in children, showing associations between structural deviations and cognitive/behavioural differences.

Microstructural and Biomechanical Determinants of Biological Aging

The paper develops a multimodal model to predict biological age using vascular microstructure and biomechanical parameters in mice, achieving high predictive accuracy.

From topography to connectome: Towards an integrated understanding of the resting brain

The paper develops a deep-learning model to translate spatial topography maps into individualized connectomes, confirming its accuracy and ability to retain brain-cognition associations.

Deciphering shared and divergent tissue architectures from cross-species spatial transcriptomics

This paper introduces STACAME, a framework for analyzing cross-species spatial transcriptomics data to identify shared and divergent tissue architectures across species.

Robustness of NeuroMark-Derived Functional Networks to fMRI Spatial Normalization Across the Human Lifespan

This study evaluates the robustness of NeuroMark-derived functional networks to fMRI spatial normalization across different age groups, finding high stability regardless of normalization strategy.

MacaSurfer: unified surface-volume mapping of the macaque brain across the lifespan

MacaSurfer provides a unified framework for automated surface-volume mapping of the macaque brain across age and sites, showing high consistency and robustness.

Multidimensional feature tuning in category-selective areas of human visual cortex

This study identifies multidimensional tuning in human visual cortex, showing that category-selective areas encode both subcategory features and cross-category distinctions, supporting both local and global coding.

Facing pain is effortful: key role of the supplementary motor area and anterior midcingulate cortex

This study uses fMRI to investigate how brain regions like the supplementary motor area and anterior midcingulate cortex contribute to effort perception during pain and task performance.

A Shared Entropic Axis Spans States of Consciousness Across Pharmacological and Clinical Conditions

The paper quantifies consciousness states using entropy across pharmacological and clinical fMRI data, finding a shared entropic axis spanning from low-entropy anaesthesia to high-entropy psychedelic and schizophrenia states.

Functional Templates in fMRI: Building Accurate and Interpretable Group-Level Decoders

This paper compares functional alignment methods and template construction strategies in fMRI to improve group-level decoding accuracy and interpretability.

A generalizable Hi-C foundation model for chromatin architecture, single-cell and multi-omics analysis across species

HiCFoundation is a Hi-C-based model that integrates chromatin structure with epigenomic regulation across species, improving analysis of 3D genome architecture and single-cell data.

Root shape phenotyping using three-dimensional root system vector data in rice

This study defines parameters to quantify rice root system architecture (RSA) using 3D vector data, showing varietal differences in root shape parameters.

CASC: Content-Aware Compaction of Sparse Microscopy Images

CASC reduces microscopy image file sizes by removing spatial redundancy while preserving object-level biological structures.