dimensionality reduction

Atacformer: A transformer-based foundation model for analysis and interpretation of ATAC-seq data

Atacformer is a transformer-based model for scATAC-seq data analysis that improves clustering, cell-type annotation, and cross-modal alignment with RNA-seq data.

MOFA-FLEX: A Factor Model Framework for Integrating Omics Data with Prior Knowledge

MOFA-FLEX is a flexible factor analysis framework that integrates multi-omics data with prior knowledge, improving robustness and disentangling variation in scRNA-seq and CITE-seq data.

Beyond retinotopy: exploiting native visual representations in cortical neuroprostheses for vision loss remediation

This paper improves visual prosthetics by incorporating orientation selectivity with retinotopy to better match natural neural responses in the visual cortex.

Structural changes in autism reflect atypical brain network organization and phenotypical heterogeneity: a deep network approach

This study uses 3D CNNs to analyze structural MRI data from ASD patients, identifying consistent brain region and network changes linked to phenotypic heterogeneity and clinical scores.

Unmixing of Imaging Mass Spectrometry Measurements Using Microscopy-Informed Constraints

This paper introduces TULIP, a method to unmix IMS data using microscopy constraints, improving analysis of tissue structures in synthetic and kidney datasets.

Natural Scene Coding Consistency in Genetically-Defined Cell Populations

The paper analyzes how genetically-defined cell populations encode natural scenes versus static gratings, finding that inhibitory cells show consistent encoding across individuals, and introduces IIRS as a metric for coding capacity.

Confocal-Compatible Workflow for Sectioning, Staining, and Imaging Serial Vibratome Sections for 3D Anatomical Reconstruction of the Lymph Node

This paper presents a confocal-compatible workflow for 3D anatomical reconstruction of murine lymph nodes using vibratome sectioning and immunostaining.

Cognitive modes involved in emotion regulation identified using Constrained Principal Component Analysis for fMRI (fMRI-CPCA)

The paper identifies four cognitive modes involved in emotion regulation during reappraisal using fMRI-CPCA, showing distinct neural engagement patterns for increasing and decreasing emotional responses.

skiftiTools: An R package for reading, writing, analysing, and visualising, tract-based spatial statistics (TBSS) derived diffusion MR images

skiftiTools enables statistical analysis and visualization of TBSS-derived diffusion MRI data using R, supporting advanced modeling and data manipulation.

NetFlow: A Framework to Explore Topological Representations of High-Dimensional Biomedical Data

NetFlow constructs graph representations of biomedical data to reveal structured patterns and refine clinical subtypes in cancer datasets.

Optimizing Genomic Data Compression with Genetic Algorithms

This paper optimizes genomic sequence compression using genetic algorithms, achieving high compression rates on large datasets like the human genome.

Dynamic and task-dependent decoding of the human attentional spotlight from MEG

This study uses MEG and machine learning to decode spatial attention in humans during different tasks, showing dynamic, task-dependent attentional patterns similar to those in non-human primates.

Rapid canalization of chromosome conformation-transcription fingerprints during embryogenesis revealed by fully-automated cell identity decoding with CeSCALE

The paper develops CeSCALE to analyze lineage-resolved conformation-transcription relationships in C. elegans embryos, revealing robust inheritance of local chromatin features during development.

Sparse Autoencoders Reveal Interpretable Features in Single-Cell Foundation Models

This study uses sparse autoencoders to analyze hidden representations in single-cell foundation models, revealing interpretable biological and technical features and demonstrating their functional relevance.

VESNA: An Open-Source Tool for Automated 3D Vessel Segmentation and Network Analysis

VESNA is an open-source Fiji macro for automated 3D vessel segmentation and network analysis, demonstrating adaptability across various experimental conditions and tissue culturing methods.

OLIVE Provides Rapid Visualization and Analysis of Chromatin Tracing Experiments

OLIVE provides a web-based tool for visualizing and analyzing chromatin tracing data, enabling interactive exploration and quantitative analysis of three-dimensional chromatin structures.

Compositional data modeling of high-dimensional single cell RNA-seq (CoDA-hd): its advantages over commonly used normalization approaches

This paper introduces CoDA-hd, a compositional data analysis approach for scRNA-seq, showing its advantages in dimension reduction, clustering, and trajectory inference compared to log-normalization.

Spatial learning in multi-scale environments: Roles of hippocampus, orbitofrontal cortex, and retrosplenial cortex

This study investigates how spatial learning influences cognitive map formation in multi-scale environments by analyzing brain activity patterns in the hippocampus, orbitofrontal cortex, and retrosplenial cortex.

ImplantoMetrics - Multidimensional trophoblast invasion assessment by combining 3D-in-vitro modeling and deep learning analysis

ImplantoMetrics quantitatively assesses trophoblast invasion using 3D-in-vitro models and deep learning, offering faster and more accurate analysis than manual methods.

Coarse-graining reveals collective predictive information in a sensory population

The paper identifies collective variables in retinal ganglion cells that best predict future neural activity using an information bottleneck method.

Representational Similarity and Pattern Classification of Fifteen Emotional States Induced by Movie Clips and Text Scenarios

This study investigates how 15 emotional states are represented in the brain using fMRI and finds that categorical labels better correlate with brain activity than dimensional ratings.

Intracortical microstructure profiling: a versatile method for indexing cortical lamination

This paper introduces a method for profiling intracortical microstructure to assess laminar organisation, showing its robustness and reliability across different datasets and sites.

LipidQMap - An Open-Source Tool for Quantitative Mass Spectrometry Imaging of Lipids

LipidQMap is an open-source tool for processing quantitative mass spectrometry imaging lipidomics data, enabling accurate and reproducible spatial lipid quantification across MSI platforms.

scConcept: Contrastive pretraining for technology-agnostic single-cell representations beyond reconstruction

scConcept improves single-cell representations by using contrastive learning instead of reconstruction, outperforming existing methods in multiple tasks.

Functional MRI signals at and beyond 1 Hz are coupled to brain states and predict spontaneous neural activity

This study shows high-frequency fMRI signals are linked to brain states and can predict spontaneous neural activity using machine learning.

Protein-protein interaction priors shape biologically coherent latent spaces for causally concordant cross-omic translation

This paper introduces a PPI prior to guide autoencoder embeddings, improving biological coherence and downstream task performance in multi-omic data.

scRetinaDB: A Comprehensive Database of Single-Cell and Spatial Omics from Cross-Species Retinas

scRetinaDB aggregates single-cell and spatial omics data from retinas across species to enable cross-species analysis and resource sharing.

Parallel frequency-multiplexed aberration measurement for widefield fluorescence microscopy

This paper introduces PFAM and PFAM-SIFT methods for parallel aberration measurement in widefield fluorescence microscopy, enabling accurate correction of spatially varying aberrations in complex samples.

Aged brain multi-omic integration captures immunometabolic and sex variation

This study integrates multi-omic data from aged human brains to identify immunometabolic and sex-related aging patterns.

Scale-dependent brain age with cosmological higher-order statistics from structural magnetic resonance imaging

The paper introduces a method using cosmological higher-order statistics to infer brain age from MRI data, revealing scale-dependent aging patterns with a Mean Absolute Error of 3.1 years.