scholarly journals Explainable autoencoder-based representation learning for gene expression data

2021 ◽  
Author(s):  
Yang Yu ◽  
Pathum Kossinna ◽  
Wenyuan Liao ◽  
Qingrun Zhang
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Hidden Variables ◽  
Representation Learning ◽  
The Cancer Genome Atlas ◽  
Expression Data ◽  
Rna Seq ◽  
Gene Expression Data Analysis ◽  
Cancer Genome Atlas ◽  
Modern Machine

Modern machine learning methods have been extensively utilized in gene expression data analysis. In particular, autoencoders (AE) have been employed in processing noisy and heterogenous RNA-Seq data. However, AEs usually lead to "black-box" hidden variables difficult to interpret, hindering downstream experimental validation and clinical translation. To bridge the gap between complicated models and biological interpretations, we developed a tool, XAE4Exp (eXplainable AutoEncoder for Expression data), which integrates AE and SHapley Additive exPlanations (SHAP), a flagship technique in the field of eXplainable AI (XAI). It quantitatively evaluates the contributions of each gene to the hidden structure learned by an AE, substantially improving the expandability of AE outcomes. By applying XAE4Exp to The Cancer Genome Atlas (TCGA) breast cancer gene expression data, we identified genes that are not differentially expressed, and pathways in various cancer-related classes. This tool will enable researchers and practitioners to analyze high-dimensional expression data intuitively, paving the way towards broader uses of deep learning.

scholarly journals Mining The Cancer Genome Atlas gene expression data for lineage markers in distinguishing bladder urothelial carcinoma and prostate adenocarcinoma

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ewe Seng Ch’ng
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
The Cancer Genome Atlas ◽  
Relative Importance ◽  
Expression Data ◽  
Gene Expressions ◽  
Urothelial Carcinomas ◽  
Cancer Genome Atlas ◽  
Lineage Markers ◽  
Genome Atlas

AbstractDistinguishing bladder urothelial carcinomas from prostate adenocarcinomas for poorly differentiated carcinomas derived from the bladder neck entails the use of a panel of lineage markers to help make this distinction. Publicly available The Cancer Genome Atlas (TCGA) gene expression data provides an avenue to examine utilities of these markers. This study aimed to verify expressions of urothelial and prostate lineage markers in the respective carcinomas and to seek the relative importance of these markers in making this distinction. Gene expressions of these markers were downloaded from TCGA Pan-Cancer database for bladder and prostate carcinomas. Differential gene expressions of these markers were analyzed. Standard linear discriminant analyses were applied to establish the relative importance of these markers in lineage determination and to construct the model best in making the distinction. This study shows that all urothelial lineage genes except for the gene for uroplakin III were significantly expressed in bladder urothelial carcinomas (p < 0.001). In descending order of importance to distinguish from prostate adenocarcinomas, genes for uroplakin II, S100P, GATA3 and thrombomodulin had high discriminant loadings (> 0.3). All prostate lineage genes were significantly expressed in prostate adenocarcinomas(p < 0.001). In descending order of importance to distinguish from bladder urothelial carcinomas, genes for NKX3.1, prostate specific antigen (PSA), prostate-specific acid phosphatase, prostein, and prostate-specific membrane antigen had high discriminant loadings (> 0.3). Combination of gene expressions for uroplakin II, S100P, NKX3.1 and PSA approached 100% accuracy in tumor classification both in the training and validation sets. Mining gene expression data, a combination of four lineage markers helps distinguish between bladder urothelial carcinomas and prostate adenocarcinomas.

scholarly journals IRIS-EDA: An integrated RNA-Seq interpretation system for gene expression data analysis

2019 ◽  
Vol 15 (2) ◽  
pp. e1006792 ◽  
Author(s):  
Brandon Monier ◽  
Adam McDermaid ◽  
Cankun Wang ◽  
Jing Zhao ◽  
Allison Miller ◽  
...  
Keyword(s):  
Gene Expression ◽  
Data Analysis ◽  
Gene Expression Data ◽  
Expression Data ◽  
Rna Seq ◽  
Gene Expression Data Analysis ◽  
Interpretation System

scholarly journals recount-brain: a curated repository of human brain RNA-seq datasets metadata

2019 ◽  
Author(s):  
Ashkaun Razmara ◽  
Shannon E. Ellis ◽  
Dustin J. Sokolowski ◽  
Sean Davis ◽  
Michael D. Wilson ◽  
...  
Keyword(s):  
Gene Expression ◽  
Human Brain ◽  
Gene Expression Data ◽  
Differential Expression Analysis ◽  
Controlled Vocabulary ◽  
The Cancer Genome Atlas ◽  
Tissue Type ◽  
Expression Data ◽  
Rna Seq ◽  
Human Brain Tissue

AbstractThe usability of publicly-available gene expression data is often limited by the availability of high-quality, standardized biological phenotype and experimental condition information (“metadata”). We released the recount2 project, which involved re-processing ∼70,000 samples in the Sequencing Read Archive (SRA), Genotype-Tissue Expression (GTEx), and The Cancer Genome Atlas (TCGA) projects. While samples from the latter two projects are well-characterized with extensive metadata, the ∼50,000 RNA-seq samples from SRA in recount2 are inconsistently annotated with metadata. Tissue type, sex, and library type can be estimated from the RNA sequencing (RNA-seq) data itself. However, more detailed and harder to predict metadata, like age and diagnosis, must ideally be provided by labs that deposit the data.To facilitate more analyses within human brain tissue data, we have complemented phenotype predictions by manually constructing a uniformly-curated database of public RNA-seq samples present in SRA and recount2. We describe the reproducible curation process for constructing recount-brain that involves systematic review of the primary manuscript, which can serve as a guide to annotate other studies and tissues. We further expanded recount-brain by merging it with GTEx and TCGA brain samples as well as linking to controlled vocabulary terms for tissue, Brodmann area and disease. Furthermore, we illustrate how to integrate the sample metadata in recount-brain with the gene expression data in recount2 to perform differential expression analysis. We then provide three analysis examples involving modeling postmortem interval, glioblastoma, and meta-analyses across GTEx and TCGA. Overall, recount-brain facilitates expression analyses and improves their reproducibility as individual researchers do not have to manually curate the sample metadata. recount-brain is available via the add_metadata() function from the recount Bioconductor package at bioconductor.org/packages/recount.

scholarly journals The Analysis of Gene Expression Data Incorporating Tumor Purity Information

2021 ◽  
Vol 12 ◽  
Author(s):  
Seungjun Ahn ◽  
Tyler Grimes ◽  
Somnath Datta
Keyword(s):  
Gene Expression ◽  
Tumor Cells ◽  
Gene Expression Data ◽  
The Cancer Genome Atlas ◽  
Data Sets ◽  
Expression Data ◽  
Tumor Purity ◽  
Robust Model ◽  
Differential Network ◽  
Cancer Genome Atlas

The tumor microenvironment is composed of tumor cells, stroma cells, immune cells, blood vessels, and other associated non-cancerous cells. Gene expression measurements on tumor samples are an average over cells in the microenvironment. However, research questions often seek answers about tumor cells rather than the surrounding non-tumor tissue. Previous studies have suggested that the tumor purity (TP)—the proportion of tumor cells in a solid tumor sample—has a confounding effect on differential expression (DE) analysis of high vs. low survival groups. We investigate three ways incorporating the TP information in the two statistical methods used for analyzing gene expression data, namely, differential network (DN) analysis and DE analysis. Analysis 1 ignores the TP information completely, Analysis 2 uses a truncated sample by removing the low TP samples, and Analysis 3 uses TP as a covariate in the underlying statistical models. We use three gene expression data sets related to three different cancers from the Cancer Genome Atlas (TCGA) for our investigation. The networks from Analysis 2 have greater amount of differential connectivity in the two networks than that from Analysis 1 in all three cancer datasets. Similarly, Analysis 1 identified more differentially expressed genes than Analysis 2. Results of DN and DE analyses using Analysis 3 were mostly consistent with those of Analysis 1 across three cancers. However, Analysis 3 identified additional cancer-related genes in both DN and DE analyses. Our findings suggest that using TP as a covariate in a linear model is appropriate for DE analysis, but a more robust model is needed for DN analysis. However, because true DN or DE patterns are not known for the empirical datasets, simulated datasets can be used to study the statistical properties of these methods in future studies.

Sign in / Sign up

Export Citation Format

Share Document