scholarly journals Leveraging information in spatial transcriptomics to predict super-resolution gene expression from histology images in tumors

2021 ◽  
Author(s):  
Minxing Pang ◽  
Kenong Su ◽  
Mingyao Li
Keyword(s):  
Gene Expression ◽  
Super Resolution ◽  
Spatial Dependency ◽  
Tissue Sections ◽  
Her2 Breast Cancer ◽  
Recent Developments ◽  
Transcriptomics Data ◽  
Hematoxylin And Eosin ◽  
Deep Learning Model ◽  
Predict Gene Expression

Recent developments in spatial transcriptomics (ST) technologies have enabled the profiling of transcriptome-wide gene expression while retaining the location information of measured genes within tissues. Moreover, the corresponding high-resolution hematoxylin and eosin-stained histology images are readily available for the ST tissue sections. Since histology images are easy to obtain, it is desirable to leverage information learned from ST to predict gene expression for tissue sections where only histology images are available. Here we present HisToGene, a deep learning model for gene expression prediction from histology images. To account for the spatial dependency of measured spots, HisToGene adopts Vision Transformer, a state-of-the-art method for image recognition. The well-trained HisToGene model can also predict super-resolution gene expression. Through evaluations on 32 HER2+ breast cancer samples with 9,612 spots and 785 genes, we show that HisToGene accurately predicts gene expression and outperforms ST-Net both in gene expression prediction and clustering tissue regions using the predicted expression. We further show that the predicted super-resolution gene expression also leads to higher clustering accuracy than observed gene expression. Gene expression predicted from HisToGene enables researchers to generate virtual transcriptomics data at scale and can help elucidate the molecular signatures of tissues.

scholarly journals Multidimensional transcriptomics provides detailed information about immune cell distribution and identity in HER2+ breast tumors

2018 ◽  
Author(s):  
Fredrik Salmén ◽  
Sanja Vickovic ◽  
Ludvig Larsson ◽  
Linnea Stenbeck ◽  
Johan Vallon-Christersson ◽  
...  
Keyword(s):  
Tumor Tissue ◽  
Immune Cell ◽  
Three Dimensional ◽  
Cell Infiltration ◽  
Immune Cell Infiltration ◽  
Cell Distribution ◽  
Tissue Sections ◽  
Disease States ◽  
Her2 Breast Cancer ◽  
Transcriptomics Data

AbstractThe comprehensive analysis of tumor tissue heterogeneity is crucial for determining specific disease states and establishing suitable treatment regimes. Here, we analyze tumor tissue sections from ten patients diagnosed with HER2+ breast cancer. We obtain and analyze multidimensional, genome-wide transcriptomics data to resolve spatial immune cell distribution and identity within the tissue sections. Furthermore, we determine the extent of immune cell infiltration in different regions of the tumor tissue, including invasive cancer regions. We combine cross-sectioning and computational alignment to build three-dimensional images of the transcriptional landscape of the tumor and its microenvironment. The three-dimensional data clearly demonstrates the heterogeneous nature of tumor-immune interactions and reveal interpatient differences in immune cell infiltration patterns. Our study shows the potential for an improved stratification and description of the tumor-immune interplay, which is likely to be essential in treatment decisions.

scholarly journals BayesSpace enables the robust characterization of spatial gene expression architecture in tissue sections at increased resolution

2020 ◽  
Author(s):  
Edward Zhao ◽  
Matthew R. Stone ◽  
Xing Ren ◽  
Thomas Pulliam ◽  
Paul Nghiem ◽  
...  
Keyword(s):  
Gene Expression ◽  
Single Cell ◽  
Spatial Information ◽  
Expression Patterns ◽  
Resolution Enhancement ◽  
Sequencing Data ◽  
Tissue Sections ◽  
Transcriptomics Data ◽  
Fully Bayesian ◽  
Comprehensive Measurement

AbstractRecently developed spatial gene expression technologies such as the Spatial Transcriptomics and Visium platforms allow for comprehensive measurement of transcriptomic profiles while retaining spatial context. However, existing methods for analyzing spatial gene expression data often do not efficiently leverage the spatial information and fail to address the limited resolution of the technology. Here, we introduce BayesSpace, a fully Bayesian statistical method for clustering analysis and resolution enhancement of spatial transcriptomics data that seamlessly integrates into current transcriptomics analysis workflows. We show that BayesSpace improves the identification of transcriptionally distinct tissues from spatial transcriptomics samples of the brain, of melanoma, and of squamous cell carcinoma. In particular, BayesSpace’s improved resolution allows the identification of tissue structure that is not detectable at the original resolution and thus not recovered by other methods. Using an in silico dataset constructed from scRNA-seq, we demonstrate that BayesSpace can spatially resolve expression patterns to near single-cell resolution without the need for external single-cell sequencing data. In all, our results illustrate the utility BayesSpace has in facilitating the discovery of biological insights from a variety of spatial transcriptomics datasets.

scholarly journals Splotch: Robust estimation of aligned spatial temporal gene expression data

2019 ◽  
Author(s):  
Tarmo Äijö ◽  
Silas Maniatis ◽  
Sanja Vickovic ◽  
Kristy Kang ◽  
Miguel Cuevas ◽  
...  
Keyword(s):  
Gene Expression ◽  
Expression Data ◽  
Rna Seq ◽  
Computational Framework ◽  
Temporal Gene Expression ◽  
Tissue Sections ◽  
Spatially Resolved ◽  
Transcriptomics Data ◽  
Approaches To Study ◽  
And Function

AbstractSpatial genomics technologies enable new approaches to study how cells interact and function in intact multicellular environments but present a host of technical and computational challenges. Here we describe Splotch, a novel computational framework for the analysis of spatially resolved transcriptomics data. Splotch aligns transcriptomics data from multiple tissue sections and timepoints to generate improved posterior estimates of gene expression. We demonstrate alignment of a large corpus of single-cell RNA-seq data into an automatically generated spatial-temporal coordinate and study optimal design for spatial transcriptomics experiments.

scholarly journals PathoFusion: An Open-Source AI Framework for Recognition of Pathomorphological Features and Mapping of Immunohistochemical Data

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 617
Author(s):  
Guoqing Bao ◽  
Xiuying Wang ◽  
Ran Xu ◽  
Christina Loh ◽  
Oreoluwa Daniel Adeyinka ◽  
...  
Keyword(s):  
Neural Network ◽  
Tumor Vasculature ◽  
Integrated System ◽  
Pathological Features ◽  
Adjacent Tissue ◽  
Tissue Sections ◽  
Contextual Feature ◽  
Hematoxylin And Eosin ◽  
Feature Information ◽  
Software Code

We have developed a platform, termed PathoFusion, which is an integrated system for marking, training, and recognition of pathological features in whole-slide tissue sections. The platform uses a bifocal convolutional neural network (BCNN) which is designed to simultaneously capture both index and contextual feature information from shorter and longer image tiles, respectively. This is analogous to how a microscopist in pathology works, identifying a cancerous morphological feature in the tissue context using first a narrow and then a wider focus, hence bifocal. Adjacent tissue sections obtained from glioblastoma cases were processed for hematoxylin and eosin (H&E) and immunohistochemical (CD276) staining. Image tiles cropped from the digitized images based on markings made by a consultant neuropathologist were used to train the BCNN. PathoFusion demonstrated its ability to recognize malignant neuropathological features autonomously and map immunohistochemical data simultaneously. Our experiments show that PathoFusion achieved areas under the curve (AUCs) of 0.985 ± 0.011 and 0.988 ± 0.001 in patch-level recognition of six typical pathomorphological features and detection of associated immunoreactivity, respectively. On this basis, the system further correlated CD276 immunoreactivity to abnormal tumor vasculature. Corresponding feature distributions and overlaps were visualized by heatmaps, permitting high-resolution qualitative as well as quantitative morphological analyses for entire histological slides. Recognition of more user-defined pathomorphological features can be added to the system and included in future tissue analyses. Integration of PathoFusion with the day-to-day service workflow of a (neuro)pathology department is a goal. The software code for PathoFusion is made publicly available.

scholarly journals Immune microenvironment and intrinsic subtyping in hormone receptor-positive/HER2-negative breast cancer

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Gaia Griguolo ◽  
Maria Vittoria Dieci ◽  
Laia Paré ◽  
Federica Miglietta ◽  
Daniele Giulio Generali ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Gene Expression Data ◽  
Hormone Receptor ◽  
Tumor Biology ◽  
Expression Data ◽  
Immune Microenvironment ◽  
Immune Infiltrate ◽  
Hormone Receptor Positive ◽  
Her2 Breast Cancer

AbstractLittle is known regarding the interaction between immune microenvironment and tumor biology in hormone receptor (HR)+/HER2− breast cancer (BC). We here assess pretreatment gene-expression data from 66 HR+/HER2− early BCs from the LETLOB trial and show that non-luminal tumors (HER2-enriched, Basal-like) present higher tumor-infiltrating lymphocyte levels than luminal tumors. Moreover, significant differences in immune infiltrate composition, assessed by CIBERSORT, were observed: non-luminal tumors showed a more proinflammatory antitumor immune infiltrate composition than luminal ones.

scholarly journals Key Genes and Prognostic Analysis in HER2+ Breast Cancer

2021 ◽  
Vol 20 ◽  
pp. 153303382098329
Author(s):  
Yujie Weng ◽  
Wei Liang ◽  
Yucheng Ji ◽  
Zhongxian Li ◽  
Rong Jia ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Differentially Expressed Genes ◽  
Protein Interaction ◽  
Differentially Expressed ◽  
Protein Kinase Activity ◽  
Protein Protein Interaction ◽  
Risk Of Death ◽  
Her2 Breast Cancer ◽  
Key Genes

Human epidermal growth factor 2 (HER2)+ breast cancer is considered the most dangerous type of breast cancers. Herein, we used bioinformatics methods to identify potential key genes in HER2+ breast cancer to enable its diagnosis, treatment, and prognosis prediction. Datasets of HER2+ breast cancer and normal tissue samples retrieved from Gene Expression Omnibus and The Cancer Genome Atlas databases were subjected to analysis for differentially expressed genes using R software. The identified differentially expressed genes were subjected to gene ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses followed by construction of protein-protein interaction networks using the STRING database to identify key genes. The genes were further validated via survival and differential gene expression analyses. We identified 97 upregulated and 106 downregulated genes that were primarily associated with processes such as mitosis, protein kinase activity, cell cycle, and the p53 signaling pathway. Visualization of the protein-protein interaction network identified 10 key genes ( CCNA2, CDK1, CDC20, CCNB1, DLGAP5, AURKA, BUB1B, RRM2, TPX2, and MAD2L1), all of which were upregulated. Survival analysis using PROGgeneV2 showed that CDC20, CCNA2, DLGAP5, RRM2, and TPX2 are prognosis-related key genes in HER2+ breast cancer. A nomogram showed that high expression of RRM2, DLGAP5, and TPX2 was positively associated with the risk of death. TPX2, which has not previously been reported in HER2+ breast cancer, was associated with breast cancer development, progression, and prognosis and is therefore a potential key gene. It is hoped that this study can provide a new method for the diagnosis and treatment of HER2 + breast cancer.

scholarly journals Deep learning-based transformation of H&E stained tissues into special stains

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Kevin de Haan ◽  
Yijie Zhang ◽  
Jonathan E. Zuckerman ◽  
Tairan Liu ◽  
Anthony E. Sisk ◽  
...  
Keyword(s):  
Visual Inspection ◽  
Kidney Diseases ◽  
Periodic Acid ◽  
Needle Core Biopsy ◽  
Silver Stain ◽  
Periodic Acid Schiff ◽  
Tissue Sections ◽  
Biopsy Tissue ◽  
Hematoxylin And Eosin

AbstractPathology is practiced by visual inspection of histochemically stained tissue slides. While the hematoxylin and eosin (H&E) stain is most commonly used, special stains can provide additional contrast to different tissue components. Here, we demonstrate the utility of supervised learning-based computational stain transformation from H&E to special stains (Masson’s Trichrome, periodic acid-Schiff and Jones silver stain) using kidney needle core biopsy tissue sections. Based on the evaluation by three renal pathologists, followed by adjudication by a fourth pathologist, we show that the generation of virtual special stains from existing H&E images improves the diagnosis of several non-neoplastic kidney diseases, sampled from 58 unique subjects (P = 0.0095). A second study found that the quality of the computationally generated special stains was statistically equivalent to those which were histochemically stained. This stain-to-stain transformation framework can improve preliminary diagnoses when additional special stains are needed, also providing significant savings in time and cost.

Sign in / Sign up

Export Citation Format

Share Document