From d9ec49554c16e5fe1b2f18907c01e6ea48cb11ca Mon Sep 17 00:00:00 2001 From: jhudsl-robot Date: Wed, 24 May 2023 15:34:09 +0000 Subject: [PATCH] Render bookdown --- docs/404.html | 12 ++++- docs/About.md | 84 ++++++++++++++++--------------- docs/about-the-authors.html | 96 ++++++++++++++++++++---------------- docs/customize-samples.html | 12 ++++- docs/index.html | 14 +++++- docs/index.md | 3 +- docs/multiple-sra-files.html | 12 ++++- docs/quick-start.html | 12 ++++- docs/references.html | 12 ++++- docs/search_index.json | 2 +- 10 files changed, 167 insertions(+), 92 deletions(-) diff --git a/docs/404.html b/docs/404.html index 89d5662..d8c85a8 100644 --- a/docs/404.html +++ b/docs/404.html @@ -23,7 +23,7 @@ - + @@ -52,6 +52,16 @@ + + + + diff --git a/docs/About.md b/docs/About.md index 1c5abb0..b468899 100644 --- a/docs/About.md +++ b/docs/About.md @@ -47,55 +47,57 @@ These credits are based on our [course contributors table guidelines](https://gi ## ─ Session info ─────────────────────────────────────────────────────────────── ## setting value ## version R version 4.0.2 (2020-06-22) -## os Ubuntu 20.04.3 LTS +## os Ubuntu 20.04.5 LTS ## system x86_64, linux-gnu ## ui X11 ## language (EN) ## collate en_US.UTF-8 ## ctype en_US.UTF-8 ## tz Etc/UTC -## date 2023-03-22 +## date 2023-05-24 ## ## ─ Packages ─────────────────────────────────────────────────────────────────── -## package * version date lib source -## assertthat 0.2.1 2019-03-21 [1] RSPM (R 4.0.3) -## bookdown 0.24 2022-02-15 [1] Github (rstudio/bookdown@88bc4ea) -## callr 3.4.4 2020-09-07 [1] RSPM (R 4.0.2) -## cli 2.0.2 2020-02-28 [1] RSPM (R 4.0.0) -## crayon 1.3.4 2017-09-16 [1] RSPM (R 4.0.0) -## desc 1.2.0 2018-05-01 [1] RSPM (R 4.0.3) -## devtools 2.3.2 2020-09-18 [1] RSPM (R 4.0.3) -## digest 0.6.25 2020-02-23 [1] RSPM (R 4.0.0) -## ellipsis 0.3.1 2020-05-15 [1] RSPM (R 4.0.3) -## evaluate 0.14 2019-05-28 [1] RSPM (R 4.0.3) -## fansi 0.4.1 2020-01-08 [1] RSPM (R 4.0.0) -## fs 1.5.0 2020-07-31 [1] RSPM (R 4.0.3) -## glue 1.6.1 2022-01-22 [1] CRAN (R 4.0.2) -## htmltools 0.5.0 2020-06-16 [1] RSPM (R 4.0.1) -## jquerylib 0.1.4 2021-04-26 [1] CRAN (R 4.0.2) -## knitr 1.33 2022-02-15 [1] Github (yihui/knitr@a1052d1) -## lifecycle 1.0.0 2021-02-15 [1] CRAN (R 4.0.2) -## magrittr 2.0.2 2022-01-26 [1] CRAN (R 4.0.2) -## memoise 1.1.0 2017-04-21 [1] RSPM (R 4.0.0) -## pkgbuild 1.1.0 2020-07-13 [1] RSPM (R 4.0.2) -## pkgload 1.1.0 2020-05-29 [1] RSPM (R 4.0.3) -## prettyunits 1.1.1 2020-01-24 [1] RSPM (R 4.0.3) -## processx 3.4.4 2020-09-03 [1] RSPM (R 4.0.2) -## ps 1.3.4 2020-08-11 [1] RSPM (R 4.0.2) -## purrr 0.3.4 2020-04-17 [1] RSPM (R 4.0.3) -## R6 2.4.1 2019-11-12 [1] RSPM (R 4.0.0) -## remotes 2.2.0 2020-07-21 [1] RSPM (R 4.0.3) -## rlang 0.4.10 2022-02-15 [1] Github (r-lib/rlang@f0c9be5) -## rmarkdown 2.10 2022-02-15 [1] Github (rstudio/rmarkdown@02d3c25) -## rprojroot 2.0.2 2020-11-15 [1] CRAN (R 4.0.2) -## sessioninfo 1.1.1 2018-11-05 [1] RSPM (R 4.0.3) -## stringi 1.5.3 2020-09-09 [1] RSPM (R 4.0.3) -## stringr 1.4.0 2019-02-10 [1] RSPM (R 4.0.3) -## testthat 3.0.1 2022-02-15 [1] Github (R-lib/testthat@e99155a) -## usethis 2.1.5.9000 2022-02-15 [1] Github (r-lib/usethis@57b109a) -## withr 2.3.0 2020-09-22 [1] RSPM (R 4.0.2) -## xfun 0.26 2022-02-15 [1] Github (yihui/xfun@74c2a66) -## yaml 2.2.1 2020-02-01 [1] RSPM (R 4.0.3) +## package * version date lib source +## assertthat 0.2.1 2019-03-21 [1] RSPM (R 4.0.5) +## bookdown 0.24 2023-03-28 [1] Github (rstudio/bookdown@88bc4ea) +## bslib 0.4.2 2022-12-16 [1] CRAN (R 4.0.2) +## cachem 1.0.7 2023-02-24 [1] CRAN (R 4.0.2) +## callr 3.5.0 2020-10-08 [1] RSPM (R 4.0.2) +## cli 3.6.1 2023-03-23 [1] CRAN (R 4.0.2) +## crayon 1.3.4 2017-09-16 [1] RSPM (R 4.0.0) +## desc 1.2.0 2018-05-01 [1] RSPM (R 4.0.3) +## devtools 2.3.2 2020-09-18 [1] RSPM (R 4.0.3) +## digest 0.6.25 2020-02-23 [1] RSPM (R 4.0.0) +## ellipsis 0.3.1 2020-05-15 [1] RSPM (R 4.0.3) +## evaluate 0.20 2023-01-17 [1] CRAN (R 4.0.2) +## fastmap 1.1.1 2023-02-24 [1] CRAN (R 4.0.2) +## fs 1.5.0 2020-07-31 [1] RSPM (R 4.0.3) +## glue 1.4.2 2020-08-27 [1] RSPM (R 4.0.5) +## htmltools 0.5.5 2023-03-23 [1] CRAN (R 4.0.2) +## jquerylib 0.1.4 2021-04-26 [1] CRAN (R 4.0.2) +## jsonlite 1.7.1 2020-09-07 [1] RSPM (R 4.0.2) +## knitr 1.33 2023-03-28 [1] Github (yihui/knitr@a1052d1) +## magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.0.2) +## memoise 2.0.1 2021-11-26 [1] CRAN (R 4.0.2) +## pkgbuild 1.1.0 2020-07-13 [1] RSPM (R 4.0.2) +## pkgload 1.1.0 2020-05-29 [1] RSPM (R 4.0.3) +## prettyunits 1.1.1 2020-01-24 [1] RSPM (R 4.0.3) +## processx 3.4.4 2020-09-03 [1] RSPM (R 4.0.2) +## ps 1.4.0 2020-10-07 [1] RSPM (R 4.0.2) +## R6 2.4.1 2019-11-12 [1] RSPM (R 4.0.0) +## remotes 2.2.0 2020-07-21 [1] RSPM (R 4.0.3) +## rlang 1.1.0 2023-03-14 [1] CRAN (R 4.0.2) +## rmarkdown 2.10 2023-03-28 [1] Github (rstudio/rmarkdown@02d3c25) +## rprojroot 2.0.3 2022-04-02 [1] CRAN (R 4.0.2) +## sass 0.4.5 2023-01-24 [1] CRAN (R 4.0.2) +## sessioninfo 1.1.1 2018-11-05 [1] RSPM (R 4.0.3) +## stringi 1.5.3 2020-09-09 [1] RSPM (R 4.0.3) +## stringr 1.4.0 2019-02-10 [1] RSPM (R 4.0.3) +## testthat 3.0.1 2023-03-28 [1] Github (R-lib/testthat@e99155a) +## usethis 1.6.3 2020-09-17 [1] RSPM (R 4.0.2) +## withr 2.3.0 2020-09-22 [1] RSPM (R 4.0.2) +## xfun 0.26 2023-03-28 [1] Github (yihui/xfun@74c2a66) +## yaml 2.2.1 2020-02-01 [1] RSPM (R 4.0.3) ## ## [1] /usr/local/lib/R/site-library ## [2] /usr/local/lib/R/library diff --git a/docs/about-the-authors.html b/docs/about-the-authors.html index 3779cd7..b96c3ac 100644 --- a/docs/about-the-authors.html +++ b/docs/about-the-authors.html @@ -23,7 +23,7 @@ - + @@ -52,6 +52,16 @@ + + + + @@ -277,55 +287,57 @@

About the Authors

## ─ Session info ───────────────────────────────────────────────────────────────
 ##  setting  value                       
 ##  version  R version 4.0.2 (2020-06-22)
-##  os       Ubuntu 20.04.3 LTS          
+##  os       Ubuntu 20.04.5 LTS          
 ##  system   x86_64, linux-gnu           
 ##  ui       X11                         
 ##  language (EN)                        
 ##  collate  en_US.UTF-8                 
 ##  ctype    en_US.UTF-8                 
 ##  tz       Etc/UTC                     
-##  date     2023-03-22                  
+##  date     2023-05-24                  
 ## 
 ## ─ Packages ───────────────────────────────────────────────────────────────────
-##  package     * version    date       lib source                            
-##  assertthat    0.2.1      2019-03-21 [1] RSPM (R 4.0.3)                    
-##  bookdown      0.24       2022-02-15 [1] Github (rstudio/bookdown@88bc4ea) 
-##  callr         3.4.4      2020-09-07 [1] RSPM (R 4.0.2)                    
-##  cli           2.0.2      2020-02-28 [1] RSPM (R 4.0.0)                    
-##  crayon        1.3.4      2017-09-16 [1] RSPM (R 4.0.0)                    
-##  desc          1.2.0      2018-05-01 [1] RSPM (R 4.0.3)                    
-##  devtools      2.3.2      2020-09-18 [1] RSPM (R 4.0.3)                    
-##  digest        0.6.25     2020-02-23 [1] RSPM (R 4.0.0)                    
-##  ellipsis      0.3.1      2020-05-15 [1] RSPM (R 4.0.3)                    
-##  evaluate      0.14       2019-05-28 [1] RSPM (R 4.0.3)                    
-##  fansi         0.4.1      2020-01-08 [1] RSPM (R 4.0.0)                    
-##  fs            1.5.0      2020-07-31 [1] RSPM (R 4.0.3)                    
-##  glue          1.6.1      2022-01-22 [1] CRAN (R 4.0.2)                    
-##  htmltools     0.5.0      2020-06-16 [1] RSPM (R 4.0.1)                    
-##  jquerylib     0.1.4      2021-04-26 [1] CRAN (R 4.0.2)                    
-##  knitr         1.33       2022-02-15 [1] Github (yihui/knitr@a1052d1)      
-##  lifecycle     1.0.0      2021-02-15 [1] CRAN (R 4.0.2)                    
-##  magrittr      2.0.2      2022-01-26 [1] CRAN (R 4.0.2)                    
-##  memoise       1.1.0      2017-04-21 [1] RSPM (R 4.0.0)                    
-##  pkgbuild      1.1.0      2020-07-13 [1] RSPM (R 4.0.2)                    
-##  pkgload       1.1.0      2020-05-29 [1] RSPM (R 4.0.3)                    
-##  prettyunits   1.1.1      2020-01-24 [1] RSPM (R 4.0.3)                    
-##  processx      3.4.4      2020-09-03 [1] RSPM (R 4.0.2)                    
-##  ps            1.3.4      2020-08-11 [1] RSPM (R 4.0.2)                    
-##  purrr         0.3.4      2020-04-17 [1] RSPM (R 4.0.3)                    
-##  R6            2.4.1      2019-11-12 [1] RSPM (R 4.0.0)                    
-##  remotes       2.2.0      2020-07-21 [1] RSPM (R 4.0.3)                    
-##  rlang         0.4.10     2022-02-15 [1] Github (r-lib/rlang@f0c9be5)      
-##  rmarkdown     2.10       2022-02-15 [1] Github (rstudio/rmarkdown@02d3c25)
-##  rprojroot     2.0.2      2020-11-15 [1] CRAN (R 4.0.2)                    
-##  sessioninfo   1.1.1      2018-11-05 [1] RSPM (R 4.0.3)                    
-##  stringi       1.5.3      2020-09-09 [1] RSPM (R 4.0.3)                    
-##  stringr       1.4.0      2019-02-10 [1] RSPM (R 4.0.3)                    
-##  testthat      3.0.1      2022-02-15 [1] Github (R-lib/testthat@e99155a)   
-##  usethis       2.1.5.9000 2022-02-15 [1] Github (r-lib/usethis@57b109a)    
-##  withr         2.3.0      2020-09-22 [1] RSPM (R 4.0.2)                    
-##  xfun          0.26       2022-02-15 [1] Github (yihui/xfun@74c2a66)       
-##  yaml          2.2.1      2020-02-01 [1] RSPM (R 4.0.3)                    
+##  package     * version date       lib source                            
+##  assertthat    0.2.1   2019-03-21 [1] RSPM (R 4.0.5)                    
+##  bookdown      0.24    2023-03-28 [1] Github (rstudio/bookdown@88bc4ea) 
+##  bslib         0.4.2   2022-12-16 [1] CRAN (R 4.0.2)                    
+##  cachem        1.0.7   2023-02-24 [1] CRAN (R 4.0.2)                    
+##  callr         3.5.0   2020-10-08 [1] RSPM (R 4.0.2)                    
+##  cli           3.6.1   2023-03-23 [1] CRAN (R 4.0.2)                    
+##  crayon        1.3.4   2017-09-16 [1] RSPM (R 4.0.0)                    
+##  desc          1.2.0   2018-05-01 [1] RSPM (R 4.0.3)                    
+##  devtools      2.3.2   2020-09-18 [1] RSPM (R 4.0.3)                    
+##  digest        0.6.25  2020-02-23 [1] RSPM (R 4.0.0)                    
+##  ellipsis      0.3.1   2020-05-15 [1] RSPM (R 4.0.3)                    
+##  evaluate      0.20    2023-01-17 [1] CRAN (R 4.0.2)                    
+##  fastmap       1.1.1   2023-02-24 [1] CRAN (R 4.0.2)                    
+##  fs            1.5.0   2020-07-31 [1] RSPM (R 4.0.3)                    
+##  glue          1.4.2   2020-08-27 [1] RSPM (R 4.0.5)                    
+##  htmltools     0.5.5   2023-03-23 [1] CRAN (R 4.0.2)                    
+##  jquerylib     0.1.4   2021-04-26 [1] CRAN (R 4.0.2)                    
+##  jsonlite      1.7.1   2020-09-07 [1] RSPM (R 4.0.2)                    
+##  knitr         1.33    2023-03-28 [1] Github (yihui/knitr@a1052d1)      
+##  magrittr      2.0.3   2022-03-30 [1] CRAN (R 4.0.2)                    
+##  memoise       2.0.1   2021-11-26 [1] CRAN (R 4.0.2)                    
+##  pkgbuild      1.1.0   2020-07-13 [1] RSPM (R 4.0.2)                    
+##  pkgload       1.1.0   2020-05-29 [1] RSPM (R 4.0.3)                    
+##  prettyunits   1.1.1   2020-01-24 [1] RSPM (R 4.0.3)                    
+##  processx      3.4.4   2020-09-03 [1] RSPM (R 4.0.2)                    
+##  ps            1.4.0   2020-10-07 [1] RSPM (R 4.0.2)                    
+##  R6            2.4.1   2019-11-12 [1] RSPM (R 4.0.0)                    
+##  remotes       2.2.0   2020-07-21 [1] RSPM (R 4.0.3)                    
+##  rlang         1.1.0   2023-03-14 [1] CRAN (R 4.0.2)                    
+##  rmarkdown     2.10    2023-03-28 [1] Github (rstudio/rmarkdown@02d3c25)
+##  rprojroot     2.0.3   2022-04-02 [1] CRAN (R 4.0.2)                    
+##  sass          0.4.5   2023-01-24 [1] CRAN (R 4.0.2)                    
+##  sessioninfo   1.1.1   2018-11-05 [1] RSPM (R 4.0.3)                    
+##  stringi       1.5.3   2020-09-09 [1] RSPM (R 4.0.3)                    
+##  stringr       1.4.0   2019-02-10 [1] RSPM (R 4.0.3)                    
+##  testthat      3.0.1   2023-03-28 [1] Github (R-lib/testthat@e99155a)   
+##  usethis       1.6.3   2020-09-17 [1] RSPM (R 4.0.2)                    
+##  withr         2.3.0   2020-09-22 [1] RSPM (R 4.0.2)                    
+##  xfun          0.26    2023-03-28 [1] Github (yihui/xfun@74c2a66)       
+##  yaml          2.2.1   2020-02-01 [1] RSPM (R 4.0.3)                    
 ## 
 ## [1] /usr/local/lib/R/site-library
 ## [2] /usr/local/lib/R/library
diff --git a/docs/customize-samples.html b/docs/customize-samples.html index 3c62b8d..bb91720 100644 --- a/docs/customize-samples.html +++ b/docs/customize-samples.html @@ -23,7 +23,7 @@ - + @@ -52,6 +52,16 @@ + + + + diff --git a/docs/index.html b/docs/index.html index b76738d..fff43ff 100644 --- a/docs/index.html +++ b/docs/index.html @@ -23,7 +23,7 @@ - + @@ -52,6 +52,16 @@ + + + + @@ -143,7 +153,7 @@

About this Module

diff --git a/docs/index.md b/docs/index.md index 9378f90..05c3e30 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,6 +1,6 @@ --- title: "AnVIL: SRA Data" -date: "March 22, 2023" +date: "May 24, 2023" site: bookdown::bookdown_site documentclass: book bibliography: book.bib @@ -53,3 +53,4 @@ _Programming skills_ ## AnVIL Collection {-} Please check out our full collection of AnVIL and related resources: https://hutchdatascience.org/AnVIL_Collection/ + diff --git a/docs/multiple-sra-files.html b/docs/multiple-sra-files.html index 58f8c29..014fd5e 100644 --- a/docs/multiple-sra-files.html +++ b/docs/multiple-sra-files.html @@ -23,7 +23,7 @@ - + @@ -52,6 +52,16 @@ + + + + diff --git a/docs/quick-start.html b/docs/quick-start.html index 350a427..96efb8a 100644 --- a/docs/quick-start.html +++ b/docs/quick-start.html @@ -23,7 +23,7 @@ - + @@ -52,6 +52,16 @@ + + + + diff --git a/docs/references.html b/docs/references.html index 6b1d708..c2c2ffb 100644 --- a/docs/references.html +++ b/docs/references.html @@ -23,7 +23,7 @@ - + @@ -52,6 +52,16 @@ + + + + diff --git a/docs/search_index.json b/docs/search_index.json index b6c46a4..fdb89f1 100644 --- a/docs/search_index.json +++ b/docs/search_index.json @@ -1 +1 @@ -[["index.html", "AnVIL: SRA Data About this Module About SRA Skills Level Learning Objectives AnVIL Collection", " AnVIL: SRA Data March 22, 2023 About this Module This module is part of a series of books for the Genomic Data Science Analysis, Visualization, and Informatics Lab-space (AnVIL) of the National Human Genome Research Institute (NHGRI). Learn more about AnVIL by visiting https://anvilproject.org or reading the article in Cell Genomics. About SRA This module will go over how to bring Sequence Read Archive (SRA) data into AnVIL. You can check out the SRA website to learn more: Sequence Read Archive (SRA) data, available through multiple cloud providers and NCBI servers, is the largest publicly available repository of high throughput sequencing data. The archive accepts data from all branches of life as well as metagenomic and environmental surveys. SRA stores raw sequencing data and alignment information to enhance reproducibility and facilitate new discoveries through data analysis. It can be very exciting to learn how much data is at your fingertips! Once you have settled on some data to use, you’ll want to bring it into AnVIL if it’s not already there. Navigate to the menu on the left to get started! Skills Level Genetics Novice: no genetics knowledge needed Programming skills Novice: no programming experience needed Learning Objectives AnVIL Collection Please check out our full collection of AnVIL and related resources: https://hutchdatascience.org/AnVIL_Collection/ "],["quick-start.html", "Chapter 1 Quick Start 1.1 Clone Workspace 1.2 Set Up Samples 1.3 Launch Workflow 1.4 Check Workflow 1.5 Locate Data 1.6 Summary", " Chapter 1 Quick Start In this module, we’ll bring some metagenomic data into AnVIL. This data comes from this BioProject, which collected soil samples to study bacterial communities in tallgrass prairie. Bacteria play an important role in this ecosystem, but can be changed by disturbance, management, and the presence of herbivores. The SRA Data corresponding to this project is located here. You might hear new terms for moving data around in the cloud. Ingress is when data comes to you, similar to downloading a file or receiving an email with an attachment. Egress is sending the data to another resource, similar to uploading or sending an attached file via email. There is no fee for ingressing data to AnVIL from SRA. 1.1 Clone Workspace Clone the Workspace https://anvil.terra.bio/#workspaces/anvil-outreach/SRA-data-on-AnVIL. For this demo, we have given the cloned Workspace the name SRA-data-on-AnVIL-example. 1.2 Set Up Samples Navigate to the WORKFLOWS Tab and select the SRA_Fetch Workflow. Select “Run workflow(s) with inputs defined by data table”. Set the “Select root entity type” to “sample” and click SELECT DATA. On the Select Data popup, select only the first sample, SRR22375322, and click OK. 1.3 Launch Workflow Click on the space underneath “Attribute” and select this.sample_id. Click SAVE. You are ready to launch the Workflow! Click RUN ANALYSIS. Voilà! Your Workflow is running. Because the Workflow is happening in the cloud, you can close your browser or shut down your computer without interrupting the transfer. 1.4 Check Workflow Click on the JOB HISTORY tab. You should see that the job status is “Done”. This might take a few minutes. 1.5 Locate Data Click on the DATA tab and click on the “sample” table on the left. You should now see the file associated with the first sample! 1.6 Summary Clone Workspace Go to the WORKFLOWS tab Select sample via data table (“Run workflow(s) with inputs defined by data table”) Set the Attribute to this.sample_id SAVE and RUN ANALYSIS Go to DATA tab and click “sample” table to see file populated "],["multiple-sra-files.html", "Chapter 2 Multiple SRA files 2.1 Select Workflow Data 2.2 Check Workflow 2.3 Locate Data 2.4 Summary", " Chapter 2 Multiple SRA files More than likely, you will be importing multiple files from SRA. Luckily, this is quite easy in AnVIL! In contrast to how your local computer works, The SRA Fetch Workflow imports files in parallel, so it does not take a substantially longer time. 2.1 Select Workflow Data Navigate to the WORKFLOWS Tab and select the SRA_Fetch Workflow. Select “Run workflow(s) with inputs defined by data table”. Set the “Select root entity type” to “sample” and click SELECT DATA. Select the second through fifth samples and click OK on the bottom right. Ensure the “Attribute” is set to this.sample_id and click RUN ANALYSIS. Click LAUNCH. You can close your browser or shut down your computer without interrupting the transfer. The Workflow knows that you probably want to parallelize the import of your SRA files. This means that each import is happening at the same time. Notice how this workflow with multiple samples actually launched 4 different jobs/analyses! This means that AnVIL can help you process lots of files much faster than working with them one by one. 2.2 Check Workflow Click on the JOB HISTORY tab. Different submissions are arranged by newest on the top. You should see that the job status is “Done”. 2.3 Locate Data Click on the DATA tab and click on the “sample” table on the left. You should now see the files associated with the second through fifth sample! 2.4 Summary Go to the WORKFLOWS tab Select multiple samples via data table (“Run workflow(s) with inputs defined by data table”) Set the Attribute to this.sample_id SAVE and RUN ANALYSIS Go to DATA tab and click “sample” table to see files populated "],["customize-samples.html", "Chapter 3 Customize Samples 3.1 Import Data 3.2 The samples.tsv File 3.3 Upload the TSV 3.4 Summary", " Chapter 3 Customize Samples You will probably need to select different samples than the ones in this demo. We’ve created another workspace, SRA-data-on-AnVIL-example2, to demonstrate how to upload your own sample IDs. If you go to the DATA tab, you’ll notice the same samples (ending in 22-26). These are here because data tables are copied when you clone a workspace. However, let’s add a second set of samples ending in 27-31. 3.1 Import Data Click on IMPORT DATA and select “Upload TSV”. This opens a popup that looks like this: However, let’s take a moment to get acquainted with the new file we’ll be uploading. 3.2 The samples.tsv File First, download the samples file here. You might have to right-click and “Save as”. Download samples.tsv Next, open the file on your local machine. This is what it might look like in Microsoft Excel: The column header entity:sample_id is important. entity: is required. samples becomes the name of the data table. So for example, if our header was entity:reference_id, a data table called “reference” would be created in AnVIL. If you didn’t want to overwrite anything in the original “samples” table, you could change the column header. As long as none of the IDs are the same, no data will be overwritten. 3.3 Upload the TSV Back on AnVIL, Click to select a TSV file. This file should be the one you just downloaded above called samples.tsv. You will see a warning about potentially overwriting the existing entries. We know that none of the IDs in the new samples file overlap, so click START IMPORT JOB. New samples have been added! You can now proceed with running the Workflow as you did in the Quick Start and Multiple Files sections. 3.4 Summary Go to the DATA tab Select IMPORT DATA and “Upload TSV” Add your custom file and click START IMPORT JOB "],["about-the-authors.html", "About the Authors", " About the Authors These credits are based on our course contributors table guidelines.     Credits Names Pedagogy Lead Content Instructor(s) FirstName LastName Lecturer(s) (include chapter name/link in parentheses if only for specific chapters) - make new line if more than one chapter involved Delivered the course in some way - video or audio Content Author(s) (include chapter name/link in parentheses if only for specific chapters) - make new line if more than one chapter involved If any other authors besides lead instructor Content Contributor(s) (include section name/link in parentheses) - make new line if more than one section involved Wrote less than a chapter AnVIL instructions: Katherine Cox, Ava Hoffman, Elizabeth Humphries Content Editor(s)/Reviewer(s) Checked your content Content Director(s) Helped guide the content direction Content Consultants (include chapter name/link in parentheses or word “General”) - make new line if more than one chapter involved Gave high level advice on content AnVIL instructions: Allie Cliffe Acknowledgments Gave small assistance to content but not to the level of consulting Production Content Publisher(s) Helped with publishing platform Content Publishing Reviewer(s) Reviewed overall content and aesthetics on publishing platform Technical Course Publishing Engineer(s) Helped with the code for the technical aspects related to the specific course generation Template Publishing Engineers Candace Savonen, Carrie Wright Publishing Maintenance Engineer Candace Savonen Technical Publishing Stylists Carrie Wright, Candace Savonen Package Developers (ottrpal) John Muschelli, Candace Savonen, Carrie Wright Art and Design Illustrator(s) Created graphics for the course Figure Artist(s) Created figures/plots for course Videographer(s) Filmed videos Videography Editor(s) Edited film Audiographer(s) Recorded audio Audiography Editor(s) Edited audio recordings Funding Funder(s) Institution/individual who funded course including grant number Funding Staff Staff members who help with funding   ## ─ Session info ─────────────────────────────────────────────────────────────── ## setting value ## version R version 4.0.2 (2020-06-22) ## os Ubuntu 20.04.3 LTS ## system x86_64, linux-gnu ## ui X11 ## language (EN) ## collate en_US.UTF-8 ## ctype en_US.UTF-8 ## tz Etc/UTC ## date 2023-03-22 ## ## ─ Packages ─────────────────────────────────────────────────────────────────── ## package * version date lib source ## assertthat 0.2.1 2019-03-21 [1] RSPM (R 4.0.3) ## bookdown 0.24 2022-02-15 [1] Github (rstudio/bookdown@88bc4ea) ## callr 3.4.4 2020-09-07 [1] RSPM (R 4.0.2) ## cli 2.0.2 2020-02-28 [1] RSPM (R 4.0.0) ## crayon 1.3.4 2017-09-16 [1] RSPM (R 4.0.0) ## desc 1.2.0 2018-05-01 [1] RSPM (R 4.0.3) ## devtools 2.3.2 2020-09-18 [1] RSPM (R 4.0.3) ## digest 0.6.25 2020-02-23 [1] RSPM (R 4.0.0) ## ellipsis 0.3.1 2020-05-15 [1] RSPM (R 4.0.3) ## evaluate 0.14 2019-05-28 [1] RSPM (R 4.0.3) ## fansi 0.4.1 2020-01-08 [1] RSPM (R 4.0.0) ## fs 1.5.0 2020-07-31 [1] RSPM (R 4.0.3) ## glue 1.6.1 2022-01-22 [1] CRAN (R 4.0.2) ## htmltools 0.5.0 2020-06-16 [1] RSPM (R 4.0.1) ## jquerylib 0.1.4 2021-04-26 [1] CRAN (R 4.0.2) ## knitr 1.33 2022-02-15 [1] Github (yihui/knitr@a1052d1) ## lifecycle 1.0.0 2021-02-15 [1] CRAN (R 4.0.2) ## magrittr 2.0.2 2022-01-26 [1] CRAN (R 4.0.2) ## memoise 1.1.0 2017-04-21 [1] RSPM (R 4.0.0) ## pkgbuild 1.1.0 2020-07-13 [1] RSPM (R 4.0.2) ## pkgload 1.1.0 2020-05-29 [1] RSPM (R 4.0.3) ## prettyunits 1.1.1 2020-01-24 [1] RSPM (R 4.0.3) ## processx 3.4.4 2020-09-03 [1] RSPM (R 4.0.2) ## ps 1.3.4 2020-08-11 [1] RSPM (R 4.0.2) ## purrr 0.3.4 2020-04-17 [1] RSPM (R 4.0.3) ## R6 2.4.1 2019-11-12 [1] RSPM (R 4.0.0) ## remotes 2.2.0 2020-07-21 [1] RSPM (R 4.0.3) ## rlang 0.4.10 2022-02-15 [1] Github (r-lib/rlang@f0c9be5) ## rmarkdown 2.10 2022-02-15 [1] Github (rstudio/rmarkdown@02d3c25) ## rprojroot 2.0.2 2020-11-15 [1] CRAN (R 4.0.2) ## sessioninfo 1.1.1 2018-11-05 [1] RSPM (R 4.0.3) ## stringi 1.5.3 2020-09-09 [1] RSPM (R 4.0.3) ## stringr 1.4.0 2019-02-10 [1] RSPM (R 4.0.3) ## testthat 3.0.1 2022-02-15 [1] Github (R-lib/testthat@e99155a) ## usethis 2.1.5.9000 2022-02-15 [1] Github (r-lib/usethis@57b109a) ## withr 2.3.0 2020-09-22 [1] RSPM (R 4.0.2) ## xfun 0.26 2022-02-15 [1] Github (yihui/xfun@74c2a66) ## yaml 2.2.1 2020-02-01 [1] RSPM (R 4.0.3) ## ## [1] /usr/local/lib/R/site-library ## [2] /usr/local/lib/R/library "],["references.html", "References", " References "],["404.html", "Page not found", " Page not found The page you requested cannot be found (perhaps it was moved or renamed). You may want to try searching to find the page's new location, or use the table of contents to find the page you are looking for. "]] +[["index.html", "AnVIL: SRA Data About this Module About SRA Skills Level Learning Objectives AnVIL Collection", " AnVIL: SRA Data May 24, 2023 About this Module This module is part of a series of books for the Genomic Data Science Analysis, Visualization, and Informatics Lab-space (AnVIL) of the National Human Genome Research Institute (NHGRI). Learn more about AnVIL by visiting https://anvilproject.org or reading the article in Cell Genomics. About SRA This module will go over how to bring Sequence Read Archive (SRA) data into AnVIL. You can check out the SRA website to learn more: Sequence Read Archive (SRA) data, available through multiple cloud providers and NCBI servers, is the largest publicly available repository of high throughput sequencing data. The archive accepts data from all branches of life as well as metagenomic and environmental surveys. SRA stores raw sequencing data and alignment information to enhance reproducibility and facilitate new discoveries through data analysis. It can be very exciting to learn how much data is at your fingertips! Once you have settled on some data to use, you’ll want to bring it into AnVIL if it’s not already there. Navigate to the menu on the left to get started! Skills Level Genetics Novice: no genetics knowledge needed Programming skills Novice: no programming experience needed Learning Objectives AnVIL Collection Please check out our full collection of AnVIL and related resources: https://hutchdatascience.org/AnVIL_Collection/ "],["quick-start.html", "Chapter 1 Quick Start 1.1 Clone Workspace 1.2 Set Up Samples 1.3 Launch Workflow 1.4 Check Workflow 1.5 Locate Data 1.6 Summary", " Chapter 1 Quick Start In this module, we’ll bring some metagenomic data into AnVIL. This data comes from this BioProject, which collected soil samples to study bacterial communities in tallgrass prairie. Bacteria play an important role in this ecosystem, but can be changed by disturbance, management, and the presence of herbivores. The SRA Data corresponding to this project is located here. You might hear new terms for moving data around in the cloud. Ingress is when data comes to you, similar to downloading a file or receiving an email with an attachment. Egress is sending the data to another resource, similar to uploading or sending an attached file via email. There is no fee for ingressing data to AnVIL from SRA. 1.1 Clone Workspace Clone the Workspace https://anvil.terra.bio/#workspaces/anvil-outreach/SRA-data-on-AnVIL. For this demo, we have given the cloned Workspace the name SRA-data-on-AnVIL-example. 1.2 Set Up Samples Navigate to the WORKFLOWS Tab and select the SRA_Fetch Workflow. Select “Run workflow(s) with inputs defined by data table”. Set the “Select root entity type” to “sample” and click SELECT DATA. On the Select Data popup, select only the first sample, SRR22375322, and click OK. 1.3 Launch Workflow Click on the space underneath “Attribute” and select this.sample_id. Click SAVE. You are ready to launch the Workflow! Click RUN ANALYSIS. Voilà! Your Workflow is running. Because the Workflow is happening in the cloud, you can close your browser or shut down your computer without interrupting the transfer. 1.4 Check Workflow Click on the JOB HISTORY tab. You should see that the job status is “Done”. This might take a few minutes. 1.5 Locate Data Click on the DATA tab and click on the “sample” table on the left. You should now see the file associated with the first sample! 1.6 Summary Clone Workspace Go to the WORKFLOWS tab Select sample via data table (“Run workflow(s) with inputs defined by data table”) Set the Attribute to this.sample_id SAVE and RUN ANALYSIS Go to DATA tab and click “sample” table to see file populated "],["multiple-sra-files.html", "Chapter 2 Multiple SRA files 2.1 Select Workflow Data 2.2 Check Workflow 2.3 Locate Data 2.4 Summary", " Chapter 2 Multiple SRA files More than likely, you will be importing multiple files from SRA. Luckily, this is quite easy in AnVIL! In contrast to how your local computer works, The SRA Fetch Workflow imports files in parallel, so it does not take a substantially longer time. 2.1 Select Workflow Data Navigate to the WORKFLOWS Tab and select the SRA_Fetch Workflow. Select “Run workflow(s) with inputs defined by data table”. Set the “Select root entity type” to “sample” and click SELECT DATA. Select the second through fifth samples and click OK on the bottom right. Ensure the “Attribute” is set to this.sample_id and click RUN ANALYSIS. Click LAUNCH. You can close your browser or shut down your computer without interrupting the transfer. The Workflow knows that you probably want to parallelize the import of your SRA files. This means that each import is happening at the same time. Notice how this workflow with multiple samples actually launched 4 different jobs/analyses! This means that AnVIL can help you process lots of files much faster than working with them one by one. 2.2 Check Workflow Click on the JOB HISTORY tab. Different submissions are arranged by newest on the top. You should see that the job status is “Done”. 2.3 Locate Data Click on the DATA tab and click on the “sample” table on the left. You should now see the files associated with the second through fifth sample! 2.4 Summary Go to the WORKFLOWS tab Select multiple samples via data table (“Run workflow(s) with inputs defined by data table”) Set the Attribute to this.sample_id SAVE and RUN ANALYSIS Go to DATA tab and click “sample” table to see files populated "],["customize-samples.html", "Chapter 3 Customize Samples 3.1 Import Data 3.2 The samples.tsv File 3.3 Upload the TSV 3.4 Summary", " Chapter 3 Customize Samples You will probably need to select different samples than the ones in this demo. We’ve created another workspace, SRA-data-on-AnVIL-example2, to demonstrate how to upload your own sample IDs. If you go to the DATA tab, you’ll notice the same samples (ending in 22-26). These are here because data tables are copied when you clone a workspace. However, let’s add a second set of samples ending in 27-31. 3.1 Import Data Click on IMPORT DATA and select “Upload TSV”. This opens a popup that looks like this: However, let’s take a moment to get acquainted with the new file we’ll be uploading. 3.2 The samples.tsv File First, download the samples file here. You might have to right-click and “Save as”. Download samples.tsv Next, open the file on your local machine. This is what it might look like in Microsoft Excel: The column header entity:sample_id is important. entity: is required. samples becomes the name of the data table. So for example, if our header was entity:reference_id, a data table called “reference” would be created in AnVIL. If you didn’t want to overwrite anything in the original “samples” table, you could change the column header. As long as none of the IDs are the same, no data will be overwritten. 3.3 Upload the TSV Back on AnVIL, Click to select a TSV file. This file should be the one you just downloaded above called samples.tsv. You will see a warning about potentially overwriting the existing entries. We know that none of the IDs in the new samples file overlap, so click START IMPORT JOB. New samples have been added! You can now proceed with running the Workflow as you did in the Quick Start and Multiple Files sections. 3.4 Summary Go to the DATA tab Select IMPORT DATA and “Upload TSV” Add your custom file and click START IMPORT JOB "],["about-the-authors.html", "About the Authors", " About the Authors These credits are based on our course contributors table guidelines.     Credits Names Pedagogy Lead Content Instructor(s) FirstName LastName Lecturer(s) (include chapter name/link in parentheses if only for specific chapters) - make new line if more than one chapter involved Delivered the course in some way - video or audio Content Author(s) (include chapter name/link in parentheses if only for specific chapters) - make new line if more than one chapter involved If any other authors besides lead instructor Content Contributor(s) (include section name/link in parentheses) - make new line if more than one section involved Wrote less than a chapter AnVIL instructions: Katherine Cox, Ava Hoffman, Elizabeth Humphries Content Editor(s)/Reviewer(s) Checked your content Content Director(s) Helped guide the content direction Content Consultants (include chapter name/link in parentheses or word “General”) - make new line if more than one chapter involved Gave high level advice on content AnVIL instructions: Allie Cliffe Acknowledgments Gave small assistance to content but not to the level of consulting Production Content Publisher(s) Helped with publishing platform Content Publishing Reviewer(s) Reviewed overall content and aesthetics on publishing platform Technical Course Publishing Engineer(s) Helped with the code for the technical aspects related to the specific course generation Template Publishing Engineers Candace Savonen, Carrie Wright Publishing Maintenance Engineer Candace Savonen Technical Publishing Stylists Carrie Wright, Candace Savonen Package Developers (ottrpal) John Muschelli, Candace Savonen, Carrie Wright Art and Design Illustrator(s) Created graphics for the course Figure Artist(s) Created figures/plots for course Videographer(s) Filmed videos Videography Editor(s) Edited film Audiographer(s) Recorded audio Audiography Editor(s) Edited audio recordings Funding Funder(s) Institution/individual who funded course including grant number Funding Staff Staff members who help with funding   ## ─ Session info ─────────────────────────────────────────────────────────────── ## setting value ## version R version 4.0.2 (2020-06-22) ## os Ubuntu 20.04.5 LTS ## system x86_64, linux-gnu ## ui X11 ## language (EN) ## collate en_US.UTF-8 ## ctype en_US.UTF-8 ## tz Etc/UTC ## date 2023-05-24 ## ## ─ Packages ─────────────────────────────────────────────────────────────────── ## package * version date lib source ## assertthat 0.2.1 2019-03-21 [1] RSPM (R 4.0.5) ## bookdown 0.24 2023-03-28 [1] Github (rstudio/bookdown@88bc4ea) ## bslib 0.4.2 2022-12-16 [1] CRAN (R 4.0.2) ## cachem 1.0.7 2023-02-24 [1] CRAN (R 4.0.2) ## callr 3.5.0 2020-10-08 [1] RSPM (R 4.0.2) ## cli 3.6.1 2023-03-23 [1] CRAN (R 4.0.2) ## crayon 1.3.4 2017-09-16 [1] RSPM (R 4.0.0) ## desc 1.2.0 2018-05-01 [1] RSPM (R 4.0.3) ## devtools 2.3.2 2020-09-18 [1] RSPM (R 4.0.3) ## digest 0.6.25 2020-02-23 [1] RSPM (R 4.0.0) ## ellipsis 0.3.1 2020-05-15 [1] RSPM (R 4.0.3) ## evaluate 0.20 2023-01-17 [1] CRAN (R 4.0.2) ## fastmap 1.1.1 2023-02-24 [1] CRAN (R 4.0.2) ## fs 1.5.0 2020-07-31 [1] RSPM (R 4.0.3) ## glue 1.4.2 2020-08-27 [1] RSPM (R 4.0.5) ## htmltools 0.5.5 2023-03-23 [1] CRAN (R 4.0.2) ## jquerylib 0.1.4 2021-04-26 [1] CRAN (R 4.0.2) ## jsonlite 1.7.1 2020-09-07 [1] RSPM (R 4.0.2) ## knitr 1.33 2023-03-28 [1] Github (yihui/knitr@a1052d1) ## magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.0.2) ## memoise 2.0.1 2021-11-26 [1] CRAN (R 4.0.2) ## pkgbuild 1.1.0 2020-07-13 [1] RSPM (R 4.0.2) ## pkgload 1.1.0 2020-05-29 [1] RSPM (R 4.0.3) ## prettyunits 1.1.1 2020-01-24 [1] RSPM (R 4.0.3) ## processx 3.4.4 2020-09-03 [1] RSPM (R 4.0.2) ## ps 1.4.0 2020-10-07 [1] RSPM (R 4.0.2) ## R6 2.4.1 2019-11-12 [1] RSPM (R 4.0.0) ## remotes 2.2.0 2020-07-21 [1] RSPM (R 4.0.3) ## rlang 1.1.0 2023-03-14 [1] CRAN (R 4.0.2) ## rmarkdown 2.10 2023-03-28 [1] Github (rstudio/rmarkdown@02d3c25) ## rprojroot 2.0.3 2022-04-02 [1] CRAN (R 4.0.2) ## sass 0.4.5 2023-01-24 [1] CRAN (R 4.0.2) ## sessioninfo 1.1.1 2018-11-05 [1] RSPM (R 4.0.3) ## stringi 1.5.3 2020-09-09 [1] RSPM (R 4.0.3) ## stringr 1.4.0 2019-02-10 [1] RSPM (R 4.0.3) ## testthat 3.0.1 2023-03-28 [1] Github (R-lib/testthat@e99155a) ## usethis 1.6.3 2020-09-17 [1] RSPM (R 4.0.2) ## withr 2.3.0 2020-09-22 [1] RSPM (R 4.0.2) ## xfun 0.26 2023-03-28 [1] Github (yihui/xfun@74c2a66) ## yaml 2.2.1 2020-02-01 [1] RSPM (R 4.0.3) ## ## [1] /usr/local/lib/R/site-library ## [2] /usr/local/lib/R/library "],["references.html", "References", " References "],["404.html", "Page not found", " Page not found The page you requested cannot be found (perhaps it was moved or renamed). You may want to try searching to find the page's new location, or use the table of contents to find the page you are looking for. "]]