Corrigendum: Digitaldlsorter: Deep-Learning on scRNA-Seq to Deconvolute Gene Expression Data

Integrated analyses reveal the diagnostic and predictive values of COL5A2 and association with immune environment in Crohn's disease

The pathogenesis of Crohn's disease (CD) involves abnormal immune cell infiltration and dysregulated immune response. Therefore, thorough research on immune cell abnormalities in CD is crucial for improved treatment of this disease. Single-cell RNA sequencing (scRNA-seq) and bulk RNA-seq data of CD were obtained from the Gene Expression Omnibus (GEO) database. Cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT), weighted gene co-expression network analysis (WGCNA), protein-protein interaction (PPI) networks evaluated the proportion of immune infiltrating cells, constructed co-expression network and identified key genes, respectively. Based on the dataset (GSE134809), 15 cell clusters were defined and labeled as different cell types. Among the 11 modules, the yellow module had the closest relationship with plasma cells (cluster 5). Confirmed using RNA sequencing and IHC assay, the expression of COL5A2 in CD samples was higher than that in control samples. Furthermore, the COL5A2 protein expression remarkably decreased in the group of patients who responded to anti-tumor necrosis factor (TNF) treatments, compared to the non-response group. The comprehensive analyses described here provided novel insight into the landscape of CD-associated immune environment. In addition, COL5A2 were identified as potential diagnostic indicators for CD, as well as promising predictive markers for CD patients.

SpatialDDLS: an R package to deconvolute spatial transcriptomics data using neural networks

SUMMARY

Spatial transcriptomics has changed our way to study tissue structure and cellular organization. However, there are still limitations in its resolution, and most available platforms do not reach a single cell resolution. To address this issue, we introduce SpatialDDLS, a fast neural network-based algorithm for cell type deconvolution of spatial transcriptomics data. SpatialDDLS leverages single-cell RNA sequencing data to simulate mixed transcriptional profiles with predefined cellular composition, which are subsequently used to train a fully connected neural network to uncover cell type diversity within each spot. By comparing it with two state-of-the-art spatial deconvolution methods, we demonstrate that SpatialDDLS is an accurate and fast alternative to the available state-of-the art tools.

AVAILABILITY AND IMPLEMENTATION

The R package SpatialDDLS is available via CRAN-The Comprehensive R Archive Network: https://CRAN.R-project.org/package=SpatialDDLS. A detailed manual of the main functionalities implemented in the package can be found at https://diegommcc.github.io/SpatialDDLS.

Next-generation deconvolution of transcriptomic data to investigate the tumor microenvironment

Methods for in silico deconvolution of bulk transcriptomics can characterize the cellular composition of the tumor microenvironment, quantifying the abundance of cell types associated with patients' prognosis and response to therapy. While first-generation deconvolution methods rely on precomputed, transcriptional signatures of a handful of cell types, second-generation methods can be trained with single-cell data to disentangle more fine-grained cell phenotypes and states. These novel approaches can also be applied to spatial transcriptomic data to reveal the spatial organization of tumors. In this review, we describe state-of-the-art deconvolution methods (first-generation, second-generation, and spatial) which can be used to investigate the tumor microenvironment, discussing their strengths and limitations. We conclude with an outlook on the challenges that need to be overcome to unlock the full potential of next-generation deconvolution for oncology and the life sciences.

Breast cancer combined prognostic model based on lactate metabolism genes

To investigate the impact of lactate metabolism genes, lactate metabolism-related genes (LMRG), and immune infiltrating cells on the prognosis of breast cancer. LMRG was identified via single-cell sequencing. Immune cell infiltration was obtained by the CIBERSORT method. The prognostic genes were chosen by cox regression and the least absolute selection operator approach. lactate metabolism-associated immune-infiltrating cells was determined by difference analysis. The GSE20685 dataset was used as an external validation cohort. The model's prognostic usefulness was evaluated utilizing survival, immunological microenvironment, and drug sensitivity assessments. NDUFAF6 was most associated with breast cancer prognosis. We obtained a total of 450 LMRG. SUSD3, IL18, MAL2, and CDKN1C comprised the Model2. NK cell activation was most relevant to lactate metabolism. The combined prognostic model outperformed the individual model, with the area under the curve ranging from 0.7 to 0.8 in all three cohorts. The lactate metabolism-related combination model assisted in evaluating breast cancer prognosis, providing new insights for treatment, particularly immunotherapy.

Precise reconstruction of the TME using bulk RNA-seq and a machine learning algorithm trained on artificial transcriptomes

Cellular deconvolution algorithms virtually reconstruct tissue composition by analyzing the gene expression of complex tissues. We present the decision tree machine learning algorithm, Kassandra, trained on a broad collection of >9,400 tissue and blood sorted cell RNA profiles incorporated into millions of artificial transcriptomes to accurately reconstruct the tumor microenvironment (TME). Bioinformatics correction for technical and biological variability, aberrant cancer cell expression inclusion, and accurate quantification and normalization of transcript expression increased Kassandra stability and robustness. Performance was validated on 4,000 H&E slides and 1,000 tissues by comparison with cytometric, immunohistochemical, or single-cell RNA-seq measurements. Kassandra accurately deconvolved TME elements, showing the role of these populations in tumor pathogenesis and other biological processes. Digital TME reconstruction revealed that the presence of PD-1-positive CD8⁺ T cells strongly correlated with immunotherapy response and increased the predictive potential of established biomarkers, indicating that Kassandra could potentially be utilized in future clinical applications.

A novel prognostic model based on single-cell RNA sequencing data for hepatocellular carcinoma

Background

The tumour heterogeneous make-up of immune cell infiltrates is a key factor for the therapy response and prognosis of hepatocellular carcinoma (HCC). However, it is still a major challenge to comprehensively understand the tumour immune microenvironment (TIME) at the genetic and cellular levels.

Methods

HCC single-cell RNA sequencing (scRNA-seq) data were downloaded from the Gene Expression Omnibus (GEO) database, and gene expression data were retrieved from The Cancer Genome Atlas (TCGA) database and International Cancer Genome Consortium (ICGC) database. Cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT) was performed to evaluate the abundance of immune infiltrating cells. We employed weighted gene coexpression network analysis (WGCNA) to construct a gene coexpression network. Univariate Cox and least absolute shrinkage and selection operator (LASSO) analyses were further used to construct a risk model. Moreover, the expression levels of model genes were assessed by qPCR.

Results

We defined 25 cell clusters based on the scRNA-seq dataset (GSE149614), and the clusters were labelled as various cell types by marker genes. Then, we constructed a weighted coexpression network and identified a total of 6 modules, among which the brown module was most highly correlated with tumours. Moreover, we found that the brown module was most closely related to monocytes (cluster 21). Through univariate Cox and LASSO analyses, we constructed a 3-gene risk model (RiskScore = 0.257*Expression _CSTB + 0.263* Expression _TALDO1 + 0.313* Expression _CLTA). This risk model showed excellent predictive efficacy for prognosis in the TCGA-LIHC and ICGC cohorts. Additionally, patients with high risk scores were found to be less likely to benefit from immunotherapy.

Conclusions

We developed a 3-gene signature (including CLTA, TALDO1 and CSTB) based on the heterogeneity of the TIME to predict the survival outcome and immunotherapy response.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12935-022-02469-2.