dimensionality reduction

Anatomy-to-Tract Mapping Infers White Matter Pathways Without Diffusion Streamline Propagation

This paper introduces Anatomy-to-Tract Mapping (ATM), a method that generates white matter streamlines directly from T1-weighted MRI without diffusion tractography, showing strong performance across multiple metrics.

Training neural networks from scratch in a videogame leads to brittle brain encoding

This study compares brain encoding performance of neural networks trained with different objectives on video game data, finding small advantages for reinforcement learning but overall brittle and limited generalization.

Cross-Species Cortical Geometry Reveals Conserved Gradients Across Primates and Human-Specific Expansion

The paper develops a cross-species cortical alignment framework to analyze structural connectivity and cortical expansion across primates, revealing conserved geometric patterns and human-specific expansions.

DeepCor: Denoising fMRI Data with Contrastive Autoencoders

DeepCor improves fMRI denoising by using contrastive autoencoders, outperforming CompCor on simulated data and enhancing connectivity differences in real datasets.

A deep learning-based multiscale integration of spatial omics with tumor morphology.

This paper introduces MISO, a deep learning method that predicts spatial transcriptomics data from H&E slides, enabling spatially resolved gene expression and patient representation for downstream tasks.

Compressed sensing expands the multiplexity of imaging mass cytometry

The paper extends compressed sensing to imaging mass cytometry, enabling higher multiplexity by recovering spatial protein expression from fewer measured channels.

Chrom-Sig: de-noising 1-dimensional genomic profiles by signal processing methods

Chrom-Sig de-noises 1-dimensional genomic coverage tracks using signal processing to separate signal from noise, validated across multiple datasets.

Error Correction Algorithms for Efficient Gene ExpressionQuantification in Single Cell Transcriptomics

This paper introduces an algorithm for error correction in scRNA-seq data, improving gene expression quantification efficiency and accuracy.

Robust Integration of Sparse Single-Cell Alternative Splicing and Gene Expression Data with SpliceVI

SpliceVI integrates sparse single-cell alternative splicing and gene expression data to better capture biological correlates and uncover splicing-based differences in mouse cells.

Distributed activity in the human posterior putamen distinguishes goal-directed from habitual control

The paper uses fMRI decoding to show that neural activity in the posterior putamen during learning predicts individual differences in habit versus goal-directed behavior across multiple cohorts.

LCSKPOA: Enabling banded semi-global partial order alignments via efficient and accurate backbone generation through extended lcsk++

The paper introduces an extended LCSk++ algorithm for graph-based alignment, improving memory and runtime efficiency for local and semi-global POA while maintaining alignment quality.

SIRP: A Self-Supervised Fluorescence Denoising method with Implicit Representation Priors

SIRP improves fluorescence microscopy image denoising by using self-supervised learning and implicit neural representations to preserve fine details under low SNR conditions.

Scalable integration and prediction of unpaired single-cell and spatial multi-omics via regularized disentanglement

This paper introduces scMRDR, a framework for integrating unpaired single-cell and spatial multi-omics data, showing strong performance in batch correction and spatial mapping.

BeadBuddy: user-friendly, nanometer-scale registration of single-molecule imaging data

BeadBuddy corrects chromatic errors in single-molecule imaging data using fluorescent bead images, achieving sub-voxel resolution in DNA FISH and applicable across SMLM modalities.

k-spaces: Mixtures of Gaussian latent variable models

The paper introduces k-spaces, a probabilistic framework for simultaneous dimension reduction, clustering, and latent space learning, demonstrating its application in genomic settings.

Emergence of a contrast-invariant representation of naturalistic texture in macaque visual cortex

The paper investigates how macaque visual cortex represents contrast and naturalistic texture, finding that V4 better decodes texture independently of contrast than V1 or V2.

Enhancing Functional Connectivity Analysis in Task-Based fMRI Using the BOLD-Filter Method: Greater Network and Activation Voxel Sensitivities

This study applies the BOLD-filter method to task-based fMRI data to improve functional connectivity analysis, resulting in increased sensitivity and clearer task-related patterns.

The ANTsX Ecosystem for Mapping the Mouse Brain

The paper demonstrates the use of ANTsX for precise spatial mapping of the mouse brain using standardized coordinate systems and presents novel workflows for longitudinal trajectory analysis and automated morphological measurements.

Assessing the performance of TRX and DUF148 antigens for detection of prepatent Guinea worm (Dracunculus medinensis) infection in dogs

This study evaluates TRX and DUF148 antigens for detecting prepatent Guinea worm infection in dogs using ELISA, finding DUF148 has higher sensitivity but cross-reactivity issues.

Cardiometabolic health and physical robustness map onto distinct patterns of brain structure and neurotransmitter systems

This study identifies two latent dimensions linking cardiometabolic health and physical robustness to brain structure and neurotransmitter systems using data from the UK Biobank.

RamanMAE: Masked Autoencoders Enable Efficient Molecular Imaging by Learning Biologically Meaningful Spectral Representations

RamanMAE uses masked autoencoders to learn spectral representations from Raman data, enabling efficient processing and noise reduction in biological imaging.

Topologically Optimized Intrinsic Brain Networks

This paper introduces TOIBN, a method that uses topological information from group-level brain networks to improve subject-level network estimation while preserving individual variability.

Accurate Probabilistic Reconstruction of Cell Lineage Trees from SNVs and CNAs with ScisTreeCNA

ScisTreeCNA jointly infers cell lineage trees from SNVs and CNAs, achieving higher accuracy than methods using only one type of variant.

RealtimeDecoder: A fast software module for online clusterless decoding

RealtimeDecoder is a Python-based system for real-time clusterless decoding of neural data with low latency and no spike sorting, demonstrated in rodent hippocampus recordings.

Independent Filter Analysis for Group Discrimination in fMRI

This paper introduces Independent Filter Analysis (IFA), a supervised method for group discrimination in fMRI that outperforms traditional ICA in detecting group differences.

Affinity-based selection of anti-Feline Leukaemia Virus p27 monoclonal antibodies for efficient lateral flow assay development

This study develops an efficient method to select monoclonal antibodies for lateral flow assays by combining ELISA and Spectral Shift, enabling rapid and resource-efficient antibody screening for diagnostic applications.

YibaoGaussian: Generate dynamic 3D models from text using Gaussian splatting as the explicit representation

This paper introduces YibaoGaussian, a method that generates high-quality dynamic 3D models from text descriptions efficiently.

The Rayleigh Quotient and Principal Component Analysis I

This paper introduces rho PCA, a method that improves upon contrastive PCA by approximating the Rayleigh quotient, offering better accuracy and efficiency for dimension reduction in genomics data.

MExConn: A Mechanistically Interpretable Multi-Expert Framework for Multi-Organelle Segmentation in Connectomics

MExConn is a multi-expert U-Net framework for segmenting multiple organelles in EM images, outperforming baselines and offering mechanistic interpretability.

Unified Generation of Regionalized Neural Organoids from Single-Lumen Neuroepithelium

This paper introduces a scalable platform to generate regionally specified neural organoids from uniform single-lumen neuroepithelium, improving reproducibility and fidelity to natural brain development.