scLM: automatic detection of consensus gene clusters across multiple single-cell datasets

Song, Qisheng; Su, Jing; Miller, Lance D.; Zhang, Wei

doi:10.1101/2020.04.22.055822

Cited by 4 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Uncovering the complex spatial architecture of heterogenous tissue is significant for understanding the cellular mechanisms and functions in diseases. The fast advance of single-cell RNA sequencing technologies (scRNA-seq) attracts the attention to elucidate the heterogenous cell formation [ 1–4 ] and trace the lineage relationship within tissue [ 5–7 ]. Unfortunately, due to the lack of spatial information, scRNA-seq is incapable of identifying the structural organization of heterogeneous cells within a complex tissue.…”

Section: Introductionmentioning

confidence: 99%

DSTG: deconvoluting spatial transcriptomics data through graph-based artificial intelligence

Song

2021

Briefings in Bioinformatics

Self Cite

127

102

View full text Add to dashboard Cite

Recent development of spatial transcriptomics (ST) is capable of associating spatial information at different spots in the tissue section with RNA abundance of cells within each spot, which is particularly important to understand tissue cytoarchitectures and functions. However, for such ST data, since a spot is usually larger than an individual cell, gene expressions measured at each spot are from a mixture of cells with heterogenous cell types. Therefore, ST data at each spot needs to be disentangled so as to reveal the cell compositions at that spatial spot. In this study, we propose a novel method, named deconvoluting spatial transcriptomics data through graph-based convolutional networks (DSTG), to accurately deconvolute the observed gene expressions at each spot and recover its cell constitutions, thus achieving high-level segmentation and revealing spatial architecture of cellular heterogeneity within tissues. DSTG not only demonstrates superior performance on synthetic spatial data generated from different protocols, but also effectively identifies spatial compositions of cells in mouse cortex layer, hippocampus slice and pancreatic tumor tissues. In conclusion, DSTG accurately uncovers the cell states and subpopulations based on spatial localization. DSTG is available as a ready-to-use open source software (https://github.com/Su-informatics-lab/DSTG) for precise interrogation of spatial organizations and functions in tissues.

show abstract

Section: Introductionmentioning

confidence: 99%

DSTG: deconvoluting spatial transcriptomics data through graph-based artificial intelligence

Song

2021

Briefings in Bioinformatics

Self Cite

127

102

View full text Add to dashboard Cite

show abstract

“…As microarrays and high-throughput sequencing step forward ( Song et al, 2020 ; Su et al, 2020 ; Song et al, 2021 ; Song and Su, 2021 ), gene signatures on the basis of mRNA expression profiles exhibit much potential for prediction of HCC outcomes. Several single genes may independently estimate survival outcomes of HCC subjects.…”

Section: Discussionmentioning

confidence: 99%

Development of a Toll-Like Receptor-Based Gene Signature That Can Predict Prognosis, Tumor Microenvironment, and Chemotherapy Response for Hepatocellular Carcinoma

Liu

et al. 2021

Front. Mol. Biosci.

View full text Add to dashboard Cite

Objective: Emerging evidence highlights the implications of the toll-like receptor (TLR) signaling pathway in the pathogenesis and therapeutic regimens of hepatocellular carcinoma (HCC). Herein, a prognostic TLR-based gene signature was conducted for HCC.Methods: HCC-specific TLRs were screened in the TCGA cohort. A LASSO model was constructed based on prognosis-related HCC-specific TLRs. The predictive efficacy, sensitivity, and independency of this signature was then evaluated and externally verified in the ICGC, GSE14520, and GSE76427 cohorts. The associations between this signature and tumor microenvironment (stromal/immune score, immune checkpoint expression, and immune cell infiltrations) and chemotherapy response were assessed in HCC specimens. The expression of TLRs in this signature was verified in HCC and normal liver tissues by Western blot. Following si-MAP2K2 transfection, colony formation and apoptosis of Huh7 and HepG2 cells were examined.Results: Herein, we identified 60 HCC-specific TLRs. A TLR-based gene signature (MAP2K2, IRAK1, RAC1, TRAF3, MAP3K7, and SPP1) was conducted for HCC prognosis. High-risk patients exhibited undesirable outcomes. ROC curves confirmed the well prediction performance of this signature. Multivariate Cox regression analysis demonstrated that the signature was an independent prognostic indicator. Also, high-risk HCC was characterized by an increased immune score, immune checkpoint expression, and immune cell infiltration. Meanwhile, high-risk patients displayed higher sensitivity to gemcitabine and cisplatin. The dysregulation of TLRs in the signature was confirmed in HCC. MAP2K2 knockdown weakened colony formation and elevated apoptosis of Huh7 and HepG2 cells.Conclusion: Collectively, this TLR-based gene signature might assist clinicians to select personalized therapy programs for HCC patients.

show abstract

“…As 42 more and more single-cell data becomes available, there is an urgent need to leverage existing data 43 with the newly generated data in a reliable and reproducible way, learning from the established 44 single-cell data with well-defined labels as reference, and transferring labels to new datasets to 45 assign cell-level annotations [10,11]. However, existing datasets and new datasets are often 46 collected from different tissues and species [14,15], under various experimental conditions, 47 generated by different platforms [16,17], and in the form of different omics types [18]. Thus a 48 reliable and accurate knowledge transfer method must overcome the following challenges: 1) the 49 unique technical issues of single-cell data (e.g., dropouts and dispersion) [19][20][21][22]; 2) batch effects 50 arisen from different operators, experimental protocols [23], and technical variation (e.g., mRNA quality, pre-amplification efficiency, technical settings during data generation) [24][25][26];…”

Section: Introductionmentioning

confidence: 99%

“…210Single-cell omics technologies have allowed biologists to gain unprecedented views into the 211 individual cellular components of complex biological ecosystems[45,46]. Facing the explosive and fast-growing single-cell data, there is a critical need to leverage the existing, wellcharacterized datasets as reference to ensure reliable and consistent annotations of new data.…”

mentioning

confidence: 99%

scGCN: a Graph Convolutional Networks Algorithm for Knowledge Transfer in Single Cell Omics

Song

Zhang

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Single-cell omics represent the fastest-growing genomics data type in the literature and the public genomics repositories. Leveraging the growing repository of labeled datasets and transferring labels from existing datasets to newly generated datasets will empower the exploration of the single-cell omics. The current label transfer methods have limited performance, largely due to the intrinsic heterogeneity and extrinsic differences between datasets. Here, we present a robust graph-based artificial intelligence model, single-cell Graph Convolutional Network (scGCN), to achieve effective knowledge transfer across disparate datasets. Benchmarked with other label transfer methods on totally 30 single cell omics datasets, scGCN has consistently demonstrated superior accuracy on leveraging cells from different tissues, platforms, and species, as well as cells profiled at different molecular layers. scGCN is implemented as an integrated workflow as a python software, which is available at https://github.com/QSong-github/scGCN.

show abstract

scLM: automatic detection of consensus gene clusters across multiple single-cell datasets

Abstract: 1 2 2 7 Counts of letters in the running title: 50 2 8 Counts of keywords: 5 2 9 Total word counts in Abstract: 207 3 0 3 1 3 2 Abstract 3 3

Cited by 4 publications

References 47 publications

DSTG: deconvoluting spatial transcriptomics data through graph-based artificial intelligence

DSTG: deconvoluting spatial transcriptomics data through graph-based artificial intelligence

Development of a Toll-Like Receptor-Based Gene Signature That Can Predict Prognosis, Tumor Microenvironment, and Chemotherapy Response for Hepatocellular Carcinoma

scGCN: a Graph Convolutional Networks Algorithm for Knowledge Transfer in Single Cell Omics

Contact Info

Product

Resources

About