Single-cell and spatial transcriptomics

Cleanet detects and classifies doublets in cytometry data using protein expression patterns, improving accuracy over traditional bivariate gating methods.

DeepScence identifies senescent cells in single-cell and spatial transcriptomics data, outperforming existing methods.

STAMapper maps and annotates cell types in single-cell spatial transcriptomics data using a graph neural network, achieving high accuracy and enabling unknown cell-type detection.

HALO models temporal causal relations in single-cell multi-omics data by distinguishing coupled and decoupled latent representations, revealing lineage specification dynamics in AT2 cells.

This paper introduces CellTransformer, a self-supervised framework for detecting fine-grained spatial domains in mouse brain spatial transcriptomics data, achieving high consistency across large datasets.

The paper constructs a single-cell RNA-seq atlas of the human pediatric liver and identifies age-related gene signatures that differ from adult livers and are relevant to pediatric liver diseases.

This study demonstrates using sex-dependent gene expression patterns to accurately deconvolve pooled snRNA-seq data, achieving 93-95% accuracy in cell sex classification.

The paper creates a multi-species DVC cell atlas using snRNAseq, identifying cell types and novel populations in mouse and rat.

The paper develops a workflow for differential detection analysis in single-cell RNA-seq data and shows it provides complementary information to differential expression analysis.

This paper introduces Unico, a method for deconvolving bulk genomic data into cell-type-resolved tensors, showing improved performance across gene expression and DNA methylation data.

This paper develops a deep single-cell mass cytometry approach to capture both canonical and noncanonical cell cycle states across diverse cell systems.

xCell 2.0 improves cell type proportion estimation from bulk RNA-seq data and predicts immune checkpoint blockade response more accurately than existing methods.

This study benchmarks six scRNA-seq CNV callers using 15 datasets, finding that reference choice and allelic information impact performance, with some methods being more robust but computationally intensive.

The paper introduces a statistically principled feature selection method for scRNA-seq that improves accuracy in identifying rare cell types compared to existing tools.

CellNavi predicts driver genes for cell state transitions using a deep learning framework that integrates gene graphs with transcriptomics data across diverse cell types and perturbations.

Cassini enables cost-effective, multiplexed profiling of mRNA and protein in tissue samples with high sensitivity and speed.

CAMUS improves cross-dataset cell type annotation by selecting optimal references and methods, achieving accuracy gains across multiple single-cell datasets.

NetworkSSC improves single-cell clustering by integrating gene network information, outperforming traditional methods on multiple scRNA-seq datasets.

This paper introduces stMSA, a deep learning model for integrating spatial omics data, improving domain detection, matching, and alignment across tissue slices.

The paper introduces PREFFECT, a probabilistic framework to improve analysis of FFPE-derived RNA-seq data by addressing transcript dropout and variance through generative models and graph attention mechanisms.

mcRigor improves metacell partitioning reliability by detecting heterogeneous metacells and optimizing hyperparameters for single-cell RNA-seq and multiome data.

The paper identifies a transient population of contractile fibroblasts in the mouse mammary gland that support branching morphogenesis through recruitment from the fat pad.

This paper introduces scProca, a deep generative model that integrates and generates single-cell proteomics data from transcriptomics using cross-attention mechanisms.

This paper introduces 3D CyCIF, a method for high-plex 3D profiling of cell states and immune niches in human tumors, revealing detailed spatial interactions and cytokine niches previously unattainable in thin sections.

This study identifies age-related transcriptomic and epigenetic changes in mouse hippocampus, highlighting cell-type-specific alterations in chromatin accessibility and gene regulation.

This study compares imaging-based spatial transcriptomics platforms using FFPE tumor samples, finding differences in performance and highlighting factors affecting data quality.

MitoDelta detects mitochondrial DNA deletions at cell-type resolution using single-cell RNA sequencing data, revealing distinct deletion burdens across neuronal subtypes in Parkinson's disease.

FUSION is a web-based tool that integrates spatial -omics data with histology to analyze tissue states and identify spatial linkages between molecular and histopathologic features.

Pan-cancer single-cell and spatial profiling resolves two antigen-presenting CAF lineages: tumor-adjacent mesothelial-like apCAFs and tertiary lymphoid structure-associated fibrocyte-like apCAFs, both secreting pro-tumorigenic SPP1.