deconvolution

JMod: Joint modeling of mass spectra for empowering multiplexed DIA proteomics

JMod improves sequence identification and quantification in multiplexed DIA proteomics by jointly modeling overlapping mass spectra, enabling higher throughput with maintained accuracy.

Robust Deep Denoising of Soft X-Ray Tomography Data for Biological Research: Targeting Tilt Series Versus Reconstructed Tomograms

This study compares denoising raw tilt series versus reconstructed tomograms in soft X-ray tomography, finding that denoising tilt series provides more reliable results and faster inference.

DynaMiCs - Dynamic cell-type deconvolution ensembles for Mapping in mixed Conditions

DynaMiCs integrates single-cell and bulk transcriptomics data to improve cell-type deconvolution and map population changes between phenotypes.

Combined genomic and phenotypic classification of inherited and acquired genetic disease with long-read sequencing

This paper uses long-read sequencing to simultaneously detect genetic variation and methylation, enabling phenotypic classification of inherited and acquired genetic diseases.

Variation in bulk RNA-seq and estimated cell type proportion using deconvolution when comparing pancreatic cancer samples within the same individual

The paper compares bulk RNA-seq and deconvolution results from paired pancreatic cancer samples in the same patients, finding variability in cell type proportions but no significant gene expression differences.

lute: estimating the cell composition of heterogeneous tissue with varying cell sizes using gene expression

lute improves cell composition estimation in bulk RNA-seq by accounting for varying cell sizes, using simulated and real datasets to demonstrate its accuracy.

Identifying Explainable and Generalizable Features for MEG Decoding

This study identifies time-resolved MEG features that generalize across individuals for decoding visual stimuli, showing early transient features outperform EEG wavelet features and suggest shared neural coding mechanisms.

A deconvolution solution to aliasing confusion in apparently undersampled oblique plane microscopy

The paper introduces a deconvolution method to reconstruct properly sampled volumes from apparently undersampled oblique plane microscopy data, improving upon a previous Fourier-stitching approach.

MONTAGE: A Computation Framework to Identify Spatially Resolved Functional Enrichment Gradients in the Tissue Microenvironment via Spatial Communities

MONTAGE identifies spatially resolved functional enrichment gradients in tumor microenvironments by analyzing spatial communities and their clinical relevance.

multideconv - an integrative pipeline for combining first and second generation cell type deconvolution results

multideconv reduces redundancy and improves accuracy in cell type deconvolution by integrating results from multiple methods and signatures.

CHAS, a deconvolution tool, infers cell type-specific signatures in bulk brain histone acetylation studies of neurological and psychiatric disorders

CHAS deconvolves bulk H3K27ac profiles to infer cell type-specific signatures in neurological and psychiatric disorders, revealing distinct genetic and epigenetic contributions across cell types.

Advancing Pediatric and Longitudinal DNA Methylation Studies with CellsPickMe, an Integrated Blood Cell Deconvolution Method

CellsPickMe improves blood cell deconvolution in longitudinal DNA methylation studies by integrating cord and adult references, enhancing accuracy across developmental stages.

Novel tensor decomposition-based approach for cell type deconvolution in Visium datasets when reference scRNA-seqs include multiple minor cell types

This paper introduces a tensor decomposition-based method for cell-type deconvolution in Visium spatial transcriptomics data, showing success where conventional methods fail due to inclusion of multiple minor cell types in reference profiles.

Unifying the Electron Microscopy Multiverse through a Large-scale Foundation Model

This paper introduces EM-DINO and OmniEM, a foundation model and architecture for EM image analysis, improving restoration and segmentation across diverse datasets.

DTractor enhances cell type deconvolution in spatial transcriptomics by integrating deep neural networks, transfer learning, and matrix factorization

DTractor improves cell-type deconvolution in spatial transcriptomics by integrating deep learning, transfer learning, and matrix factorization to better estimate cell-type proportions and gene expression with spatial coherence.

Benchmark of cellular deconvolution methods using a multi-assay reference dataset from postmortem human prefrontal cortex

The paper benchmarks cellular deconvolution methods using a multi-assay dataset from human prefrontal cortex, finding Bisque and hspe to be the most accurate.

Missing cell types in single-cell references impact deconvolution of bulk data but are detectable

The paper examines how missing cell types in single-cell references affect deconvolution of bulk data and shows that missing cell-type profiles can be detected using non-negative matrix factorization.

Interpretable deep learning for deconvolutional analysis of neural signals

This paper introduces an interpretable deep learning method for deconvolving neural signals, demonstrating its application in analyzing brain activity across different regions and recording modalities.

De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments

InstaNovo is a transformer model for de novo peptide sequencing that outperforms existing methods, enabling accurate identification of peptides and discovery of novel sequences and organisms.

Rescue Blood Contamination in scRNA-Seq Data by Originator, a Computational Deciphering Tool using Genetic and Contextual Information

Originator identifies and removes blood contamination in scRNA-seq data using genetic and contextual information, improving accuracy in downstream analysis.

Resolving malignant cell heterogeneity from bulk tumor RNA-seq data with CDState

CDState infers malignant cell subpopulations from bulk RNA-seq data, revealing gene programs and clinical associations in 33 cancer types.

LETSmix: a spatially informed and learning-based domain adaptation method for cell-type deconvolution in spatial transcriptomics

LETSmix improves cell-type deconvolution in spatial transcriptomics by integrating spatial context and domain adaptation, achieving better accuracy than existing methods.

PepGo: a deep learning and tree search-based model for de novo peptide sequencing

PepGo is a deep learning and tree search-based model for de novo peptide sequencing that outperforms existing methods by integrating Transformer networks with Monte Carlo Tree Search.

MuFIX - Enabling Combinations of Concurrent Optogenetics and Lock-in Amplification Fiber Photometry via Removal of Optogenetic Stimulation Crosstalk

MuFIX recovers crosstalk-contaminated photometry responses by interpolating across contaminated segments using multi-frequency lock-in amplification, accurately restoring original signals.

scDNAm-GPT Captures Genome-wide CpG Dependencies in Single-cell DNA methylomes to Revolutionize Epigenetic Analysis

scDNAm-GPT is a foundation model for single-cell DNA methylation analysis that improves clustering, trajectory inference, and deconvolution using context-aware tokenization and attention mechanisms.

ChromaFactor: deconvolution of single-molecule chromatin organization with non-negative matrix factorization

ChromaFactor deconvolves single-molecule chromatin organization data using non-negative matrix factorization to identify key functional components and their molecular contributions.

Deconvolution of Sample Identity in Single-Cell RNA Sequencing via Genome Imputation

The paper introduces a method to assign single-cell RNA-seq data to donor-of-origin without prior genetic information, achieving high concordance in tumor-derived data.

Random auditory stimulation disturbs traveling slow waves and declarative memory

This study investigates how random auditory stimulation during sleep affects slow-wave dynamics and declarative memory, finding reduced slow-wave sleep and impaired memory recall.

Flexible Analysis of Spatial Transcriptomics Data (FAST): A Deconvolution Approach

The paper introduces FAST, a reference-free deconvolution method for spatial transcriptomics data that integrates gene expression, spatial coordinates, and histology information, outperforming existing methods in simulations and real data.

BuDDI: Bulk Deconvolution with Domain Invariance to predict cell-type-specific perturbations from bulk

BuDDI predicts cell-type-specific perturbations from bulk data by integrating single-cell and bulk profiles using domain adaptation in a variational autoencoder.