scINSIGHT for interpreting single-cell gene expression from biologically heterogeneous data

Qian, Kun; Fu, Shiwei; Li, Hongwei; Li, Wei Vivian

doi:10.1186/s13059-022-02649-3

Cited by 22 publications

(27 citation statements)

References 85 publications

(91 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the factors are learned by minimizing the objective function, we include an additional post-processing step on the learned cell factors (Methods). Similar post-processing steps have been used in existing integration methods that use matrix factorizations 5 , 16 , 19 . The post-processing step constructs a neighborhood graph of all cells, which can be visualized using UMAP and clustered using Leiden cluster algorithm 20 .…”

Section: Resultsmentioning

confidence: 99%

scMoMaT jointly performs single cell mosaic integration and multi-modal bio-marker detection

et al. 2023

View full text Add to dashboard Cite

Single cell data integration methods aim to integrate cells across data batches and modalities, and data integration tasks can be categorized into horizontal, vertical, diagonal, and mosaic integration, where mosaic integration is the most general and challenging case with few methods developed. We propose scMoMaT, a method that is able to integrate single cell multi-omics data under the mosaic integration scenario using matrix tri-factorization. During integration, scMoMaT is also able to uncover the cluster specific bio-markers across modalities. These multi-modal bio-markers are used to interpret and annotate the clusters to cell types. Moreover, scMoMaT can integrate cell batches with unequal cell type compositions. Applying scMoMaT to multiple real and simulated datasets demonstrated these features of scMoMaT and showed that scMoMaT has superior performance compared to existing methods. Specifically, we show that integrated cell embedding combined with learned bio-markers lead to cell type annotations of higher quality or resolution compared to their original annotations.

show abstract

Section: Resultsmentioning

confidence: 99%

scMoMaT jointly performs single cell mosaic integration and multi-modal bio-marker detection

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Next, to explore the existence of gene programs and modules influencing the ICI response, we applied factorization using non-negative matrix factorization (NMF) and scINSIGHT 23 . Among 30 factors from NMF across all malignant cells, we identified factors showing high loadings for a specific RECIST group as NMF programs p1~4 (Fig.…”

Section: Systemic Evaluation Of the Immune Microenvironment Associate...mentioning

confidence: 99%

Unveiling the influence of tumor and immune signatures on immune checkpoint therapy in advanced lung cancer

Kim,

Park,

et al. 2024

Preprint

View full text Add to dashboard Cite

This study investigates the variability among patients with non-small cell lung cancer (NSCLC) in their responses to immune checkpoint inhibitors (ICI). Recognizing that patients with advanced-stage NSCLC rarely qualify for surgical interventions, it becomes crucial to identify biomarkers that influence responses to ICI therapy. We conducted an analysis of single-cell transcriptomes from 33 lung cancer biopsy samples, with a particular focus on 14 core samples taken before the initiation of palliative ICI treatment. Our objective was to link tumor and immune cell profiles with patient responses to ICI. We discovered that ICI non-responders exhibited a higher presence of CD4+ regulatory T cells, resident memory T cells, and TH17 cells. This contrasts with the diverse activated CD8+ T cells found in responders. Furthermore, tumor cells in non-responders frequently showed heightened transcriptional activity in the NF-kB and STAT3 pathways, suggesting a potential inherent resistance to ICI therapy. Through the integration of immune cell profiles and tumor molecular signatures, we achieved an accuracy rate exceeding 95% in predicting patient responses to ICI treatment. These results underscore the crucial importance of the interplay between tumor and immune microenvironment, including within metastatic sites, in affecting the effectiveness of ICIs in NSCLC.

show abstract

“…In this section, we tested the latent space disentanglement of scDisInFact on the simulated datasets, and compared its performance with scINSIGHT 14 . In practice, each batch often includes only a subset of the condition combinations.…”

Section: Scdisinfact Performs Latent Space Disentanglement and Batch ...mentioning

confidence: 99%

scDisInFact: disentangled learning for integration and prediction of multi-batch multi-condition single-cell RNA-sequencing data

Zhang

Zhao

Qiu

et al. 2023

Preprint

View full text Add to dashboard Cite

Single-cell RNA-sequencing (scRNA-seq) has been widely used for disease studies, where sample batches are collected from donors under different conditions including demographical groups, disease stages, and drug treatments. It is worth noting that the differences among sample batches in such a study are a mixture of technical confounders caused by batch effect and the biological variations caused by condition effect. However, current batch effect removal methods often eliminate both technical batch effects and meaningful condition effects, while perturbation prediction methods solely focus on condition effects, resulting in inaccurate gene expression predictions due to unaccounted batch effects. Here we introduce scDisInFact, a deep learning framework that models both batch effect and condition effect in scRNA-seq data. scDisInFact learns latent factors that disentangle condition effects from batch effects, enabling it to simultaneously perform three tasks: batch effect removal, condition-associated key gene detection, and perturbation prediction. We evaluated scDisInFact on both simulated and real datasets, and compared its performance to baseline methods for each task. Our results demonstrate that scDisInFact outperforms existing methods that focus on individual tasks, providing a more comprehensive and accurate approach for integrating and predicting multi-batch multi-condition single-cell RNA-sequencing data.

show abstract

scINSIGHT for interpreting single-cell gene expression from biologically heterogeneous data

Cited by 22 publications

References 85 publications

scMoMaT jointly performs single cell mosaic integration and multi-modal bio-marker detection

scMoMaT jointly performs single cell mosaic integration and multi-modal bio-marker detection

Unveiling the influence of tumor and immune signatures on immune checkpoint therapy in advanced lung cancer

scDisInFact: disentangled learning for integration and prediction of multi-batch multi-condition single-cell RNA-sequencing data

Contact Info

Product

Resources

About