Uncertainty in RNA

1.
Introduction

This github repository contains code to reproduce the analysis in our paper "Uncertainty in RNA-seq gene expression data". A copy of the paper can be found here.

1.1.
Additional Figures

This github includes a large number of additional supplementary figures, not present in the online version of this paper.
Additional Fig1 : Example of a few discordant Genes in TCGA 
Additional Fig2 : Example of a few discordant Genes in GTEx 
Additional Fig 3. TCGA batch effects
Additional Fig 4: GTEX batch effects

2.
Downloading Data

2.1.
Data folder Organization

To run our code, you need to download data from two different sources
a) Download all source data and processed Summarized Experiment objects from Amazon S3 bucket.
b) These vignettes from the github directory.
Both the folder from Amazon s3 bucket (ie OriginalTCGAGTExData) and the folder containing vignettes (git repository) should be saved in the same folder. As an example, one could save both of the above folders under "Downloads" as shown below

# folder where S3BUCKET data and github directory are stored. eg: ~/Downloads # github directory eg: ~/Downloads/UncertaintyRNA 

# S3 bucket directory eg: ~/Downloads/OriginalTCGAGTExData # when you run our RMD files, a new subfolder called "data will be created"

# This will essentially remake the "data" subfolder from github repository. # eg:~/Downloads/data

Shift+Enter to run

Language:Bash

2.2.
Amazon S3 Bucket Data

2.2.1.
Download Processed Data

If you want to download only the final SE Objects to recreate figures in our paper, the below mentioned  code will create a folder called "OriginalTCGAGTExData" and only one sub-folder "SE_objects" and its contents will be downloaded to it.

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/SE_objects/index.html /results

Language:Bash

2.2.2.
Download complete data in chunks

If you would like to download all the data associated with this Paper, it is recommended to download the data in chunks using the following commands

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/annotations/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/datasource_XENA/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/datasource_GDC/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/datasource_GTEX_v6/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/datasource_MSKCC/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/datasource_PICCOLO/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/datasource_RECOUNT2_GTEX/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/datasource_RECOUNT2_TCGA/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/combined_SEobjects/index.html /results

Shift+Enter to run

Language:Bash

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/SE_objects/index.html /results

Shift+Enter to run

Language:Bash

2.2.3.
Complete Data Download

WARNING: Please note that downloading all the data will take take a long time.

wget --recursive -nH --cut-dirs=1 https://s3-us-west-2.amazonaws.com/fh-pi-holland-e/OriginalTCGAGTExData/index.html /results

Shift+Enter to run

Language:Bash

The above line will create a folder called "OriginalTCGAGTExData" and the following sub-folders
annotations
data source_GDC
data source_GTEX_v6
data source_MSKCC
data source_PICCOLO
data source_RECOUNT2_GTEX
data source_RECOUNT2_TCGA
data source_XENA
combined_SEobjects
SE_objects

2.3.
Clone this github repository

One can clone this github repository with :

git clone https://github.com/sonali-bioc/UncertaintyRNA.git

Shift+Enter to run

Language:Bash

Or you can use Nextjournal's GitHub access component:

sonali-bioc/UncertaintyRNA

Public

ls -lah /UncertaintyRNA

0.9s

Language:Bash

2.4.
MD5SUM for downloaded files

The md5sum for all downloaded files from s3 bucket have been places here.

3.
Vignette Overview

The steps below provide a roadmap for the analysis done in the paper:

3.1.
Acquiring TCGA data

In this vignette we show in detail how data was downloaded from each source of TCGA Data. For easier manipulation of this large data set, we convert the large text files to SummarizedExperiment objects.

3.2.
Acquiring GTEX data

In this vignette we show in detail how data was downloaded from each source of GTEx Data. For easier manipulation of this large data set, we convert the large text files to SummarizedExperiment objects.

3.3.
Creating TPM Normalized SE objects for TCGA data.

In this vignette , we first find common genes and common samples present in each source of TCGA Data. Next, we convert RPKM normalized data to TPM normalized data.

3.4.
Creating TPM Normalized SE objects for GTEx data

In this vignette , we first find common genes and common samples present in each source of GTEx Data. Next, we convert RPKM normalized data to TPM normalized data.

3.5.
PCA using RPKM normalized data

In this vignette, we take RPKM normalized data from all sources of TCGA and GTEx data and compute Principal Components to see how similar/dissimilar these data sources are. The results from PCA analysis are stored as text files, which can be used later on for plotting in multi-panel figures.

3.6.
PCA using TPM normalized data

In this vignette, we use TPM normalized data from all sources of TCGA and GTEx data and compute Principal Components to see how similar/dissimilar these data sources are. The results from PCA analysis are stores as text files, which can be used later on for plotting in multi-panel figures.

3.7.
Discordant Genes

In this vignette, we calculate
discordant genes across various TCGA sources
discordant genes across various GTEx sources
discordant samples across various TCGA sources
discordant samples across various GTEx sources
compare the discordant genes to disease related genes
compare the discordant genes to multi-mapped reads as reported by Robert et al.

3.8.
7(b) Differences in absolute log2 fold change of discordant samples within a data source

In this vignette, we show detailed calculation for Fig2b of our paper.

3.9.
7(c) Discordant Genes

The authors from Xena/Toil have made available both the log2(TPM+0.001) and log2(FPKM+0.001) counts. In this vignette, we explore the two datasets from Xena/Toil, and explain why we use one source over the other.

3.10.
Supplemental Tables

In this vignette, we calculate various Supplemental Tables for our paper. These tables are also subsequently used in our analysis. They include
mRNA correlations across various TCGA sources
mRNA correlations across various GTEx sources
Protein-mRNA correlations across various TCGA sources

3.11.
Supplemental Figures

In this vignette, we make various supplemental figure for our paper.

3.12.
Batches in TCGA Data

In this vignette, we make various PCA plots for each type of cancer using the following Batch variables: TSS, PlateID and Sequencing center for various source of TCGA data.

3.13.
Batches in GTEx Data

In this vignette, we make various PCA plots using "Nucleic Acid" and "Genotype" Batches for all sources of GTEx data.

3.14.
Combining GTEx and TCGA Data

In this vignette, we follow the approach showed in Wang et al, to taking three example regions = "Thyroid, Stomach and Liver" from GTEx, and their corresponding cancer Types( "THCA", "LIHC", "STAD") and making PCA plots  for each data source to see how similar/dissimilar TCGA and GTEx data are, for various data sources.

3.15.
Figure 1 of submitted paper

In this vignette, we reproduce Figure 1 of our paper.

3.16.
Figure 2 of submitted paper

In this vignette, we reproduce Figure 2 of our paper.

4.
References

Grossman, Robert L., Heath, Allison Pet al. (2016) Toward a Shared Vision for Cancer Genomic Data. New England Journal of Medicine
Vivian J, Rao AA, Nothaft FA, et al. (2017) Toil enables reproducible, open source, big biomedical data analyses. Nature biotechnology.
Collado-Torres L, Nellore A, et al (2017) Reproducible RNA-seq analysis using recount2. Nature biotechnology.
Q. Wang, J Armenia, C. Zhang, A.V. Penson, E. Reznik, L. Zhang, T. Minet, A. Ochoa, B.E. Gross, C. A. Iacobuzio-Donahue, D. Betel, B.S. Taylor, J. Gao, N. Schultz. Unifying cancer and normal RNA sequencing data from different sources. Scientific Data 5:180061, 2018.
Rahman M, et al. (2015) Alternative preprocessing of RNA-Sequencing data in TCGA leads to improved analysis results. Bioinformatics.
The GTEx Consortium. The Genotype-Tissue Expression (GTEx) project. (2013) Nature genetics.
Robert, C. & Watson, M. Errors in RNA-Seq quantification affect genes of relevance to human disease. Genome Biol 16, 177 (2015)
R Core Team (2018). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/.

5.
Tools used for analysis

All our analysis is done in R. We found the following  R/Biocondcutor packages extremely useful in our analysis.
 SummarizedExperiment for creating and storing TCGA and GTEX data as SE objects.
 GenomicRanges for manipulating genomic ranges.
 rtracklayer for reading in GTF files quickly as GenomicRanges objects
 ggplot2 for making most of the plots in our paper.
 pheatmap for making heatmaps
We also used RColorBrewer, UpSetR and eulerr 
To ensure smooth execution of code in this repository, please install the following packages

if (!requireNamespace("BiocManager", quietly = TRUE))
    install.packages("BiocManager")

BiocManager::install(c("SummarizedExperiment",
                       "GenomicRanges", 
                       "rtracklayer", 
                       "ggplot2", 
                       "pheatmap", 
                       "RColorBrewer", 
                       "UpSetR", 
                       "eulerr", 
                       "gridExtra"))

Shift+Enter to run

Language:R

Uncertainty in RNA

1. Introduction

1.1. Additional Figures

2. Downloading Data

2.1. Data folder Organization

2.2. Amazon S3 Bucket Data

2.2.1. Download Processed Data

2.2.2. Download complete data in chunks

2.2.3. Complete Data Download

2.3. Clone this github repository

2.4. MD5SUM for downloaded files

3. Vignette Overview

3.1. Acquiring TCGA data

3.2. Acquiring GTEX data

3.3. Creating TPM Normalized SE objects for TCGA data.

3.4. Creating TPM Normalized SE objects for GTEx data

3.5. PCA using RPKM normalized data

3.6. PCA using TPM normalized data

3.7. Discordant Genes

3.8. 7(b) Differences in absolute log2 fold change of discordant samples within a data source

3.9. 7(c) Discordant Genes

3.10. Supplemental Tables

3.11. Supplemental Figures

3.12. Batches in TCGA Data

3.13. Batches in GTEx Data

3.14. Combining GTEx and TCGA Data

3.15. Figure 1 of submitted paper

3.16. Figure 2 of submitted paper

4. References

5. Tools used for analysis

1.
Introduction

1.1.
Additional Figures

2.
Downloading Data

2.1.
Data folder Organization

2.2.
Amazon S3 Bucket Data

2.2.1.
Download Processed Data

2.2.2.
Download complete data in chunks

2.2.3.
Complete Data Download

2.3.
Clone this github repository

2.4.
MD5SUM for downloaded files

3.
Vignette Overview

3.1.
Acquiring TCGA data

3.2.
Acquiring GTEX data

3.3.
Creating TPM Normalized SE objects for TCGA data.

3.4.
Creating TPM Normalized SE objects for GTEx data

3.5.
PCA using RPKM normalized data

3.6.
PCA using TPM normalized data

3.7.
Discordant Genes

3.8.
7(b) Differences in absolute log2 fold change of discordant samples within a data source

3.9.
7(c) Discordant Genes

3.10.
Supplemental Tables

3.11.
Supplemental Figures

3.12.
Batches in TCGA Data

3.13.
Batches in GTEx Data

3.14.
Combining GTEx and TCGA Data

3.15.
Figure 1 of submitted paper

3.16.
Figure 2 of submitted paper

4.
References

5.
Tools used for analysis