Merge pull request #123 from torres-alexis/DEV_GeneLab_Reference_Annotations_vGL-DPPD-7110-A

asaravia-butler · web-flow · commit 40e3652b355b · 2024-10-01T08:20:06.000-07:00
[GL_RefAnnotTable] Add Docker/Singularity
diff --git a/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A.md b/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A.md
@@ -136,9 +136,9 @@ The default columns in the annotation table are:
 | Program         | Version | Relevant Links |
 |:----------------|:-------:|:---------------|
 | R               |  4.4.0  | [https://www.r-project.org/](https://www.r-project.org/) |
-| Bioconductor    | 3.19.1  | [https://bioconductor.org](https://bioconductor.org) |
+| Bioconductor    |  3.19    | [https://bioconductor.org](https://bioconductor.org) |
 | tidyverse       |  2.0.0  | [https://www.tidyverse.org](https://www.tidyverse.org) |
-| STRINGdb        | 2.16.0  | [https://www.bioconductor.org/packages/release/bioc/html/STRINGdb.html](https://www.bioconductor.org/packages/release/bioc/html/STRINGdb.html) |
+| STRINGdb        | 2.16.4  | [https://www.bioconductor.org/packages/release/bioc/html/STRINGdb.html](https://www.bioconductor.org/packages/release/bioc/html/STRINGdb.html) |
 | PANTHER.db      | 1.0.12  | [https://bioconductor.org/packages/release/data/annotation/html/PANTHER.db.html](https://www.bioconductor.org/packages/release/data/annotation/html/PANTHER.db.html) |
 | rtracklayer     | 1.64.0  | [https://bioconductor.org/packages/release/bioc/html/rtracklayer.html](https://www.bioconductor.org/packages/release/bioc/html/rtracklayer.html) |
 | org.At.tair.db  | 3.19.1  | [https://bioconductor.org/packages/release/data/annotation/html/org.At.tair.db.html](https://www.bioconductor.org/packages/release/data/annotation/html/org.At.tair.db.html) |
@@ -182,6 +182,10 @@ Current GeneLab annotation tables are available on [figshare](https://figshare.c
 ## 0. Set Up Environment
 
 ```R
+# Set R library path to current working directory
+lib_path <- file.path(getwd())
+.libPaths(lib_path)
+
 # Define variables associated with current pipeline and annotation table versions
 GL_DPPD_ID <- "GL-DPPD-7110-A"
 ref_tab_path <- "https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/master/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv"
@@ -253,7 +257,7 @@ base_output_name <- str_replace(base_gtf_filename, ".gtf.gz", "")
 
 # Add the species name to base_output_name if the reference source is not ENSEMBL
 if (!(ref_source %in% c("ensembl_plants", "ensembl_bacteria", "ensembl"))) {
-  base_output_name <- paste(str_replace(target_species_designation, " ", "_"), base_output_name, sep = "_")
+  base_output_name <- paste(str_replace(target_organism, " ", "_"), base_output_name, sep = "_")
 }
 
 out_table_filename <- paste0(base_output_name, "-GL-annotations.tsv")
@@ -294,42 +298,52 @@ if ( file.exists(out_table_filename) ) {
 # Use AnnotationForge's makeOrgPackageFromNCBI function with default settings to create the organism-specific org.db R package from available NCBI annotations
 
 # Try to download the org.db from Bioconductor, build it locally if installation fails
-BiocManager::install(target_org_db, ask = FALSE) 
-if (!requireNamespace(target_org_db, quietly = TRUE)) { 
+BiocManager::install(target_org_db, ask = FALSE)
+if (!requireNamespace(target_org_db, quietly = TRUE)) {
   tryCatch({
     # Parse organism's name in the reference table to create the org.db name (target_org_db)
     genus_species <- strsplit(target_organism, " ")[[1]]
     if (length(genus_species) < 1) {
-        stop("Species designation is not correctly formatted: ", target_organism)
+      stop("Species designation is not correctly formatted: ", target_organism)
     }
+    
     genus <- genus_species[1]
     species <- ifelse(length(genus_species) > 1, genus_species[2], "")
     strain <- ref_table %>%
       filter(species == target_organism) %>%
       pull(strain) %>%
       gsub("[^A-Za-z0-9]", "", .)
+    
     if (!is.na(strain) && strain != "") {
-        species <- paste0(species, strain)
+      species <- paste0(species, strain)
+    }
+    
+    # Get package name or build it if not provided
+    target_org_db <- ref_table %>%
+      filter(species == target_organism) %>%
+      pull(annotations)
+    
+    if (is.na(target_org_db) || target_org_db == "") {
+      cat("\nNo annotation database specified. Constructing package name...\n")
+      target_org_db <- paste0("org.", substr(genus, 1, 1), species, ".eg.db")
     }
-    target_org_db <- paste0("org.", substr(genus, 1, 1), species, ".eg.db")
     
-    BiocManager::install(c("AnnotationForge", "biomaRt", "GO.db"), ask = FALSE) 
+    BiocManager::install(c("AnnotationForge", "biomaRt", "GO.db"), ask = FALSE)
     library(AnnotationForge)
-    makeOrgPackageFromNCBI( 
-        version = "0.1",
-        author = "Your Name <your.email@example.com>",
-        maintainer = "Your Name <your.email@example.com>",
-        outputDir = "./",
-        tax_id = target_taxid,
-        genus = genus,
-        species = species
+    makeOrgPackageFromNCBI(
+      version = "0.1",
+      author = "Your Name <your.email@example.com>",
+      maintainer = "Your Name <your.email@example.com>",
+      outputDir = "./",
+      tax_id = target_taxid,
+      genus = genus,
+      species = species
     )
     install.packages(file.path("./", target_org_db), repos = NULL, type = "source", quiet = TRUE)
     cat(paste0("'", target_org_db, "' has been successfully built and installed.\n"))
   }, error = function(e) {
-      stop("Failed to build and load the package: ", target_org_db, "\nError: ", e$message)
+    stop("Failed to build and load the package: ", target_org_db, "\nError: ", e$message)
   })
-  target_org_db <- install_annotations(target_organism, ref_tab_path)
 }
 ```
 
diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/CHANGELOG.md b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/CHANGELOG.md
@@ -49,10 +49,10 @@ Bioconductor. Used for:
     - Bacteria: Ensembl bacteria release 59
 - Updated software:
     - tidyverse version updated from 1.3.2 to 2.0.0  
-    - STRINGdb version updated from 2.8.4 to 2.16.0   
+    - STRINGdb version updated from 2.8.4 to 2.16.4   
     - PANTHER.db version updated from 1.0.11 to 1.0.12 
     - rtracklayer version updated from 1.56.1 to 1.64.0
-    - Bioconductor version updated from 3.15.1 to 3.19.1  
+    - Bioconductor version updated from 3.15.1 to 3.19  
 - Removed org.EcK12.eg.db and replaced it with a locally created annotations 
 database, as it is no longer available on Bioconductor
 - Changed the first argument of GL-DPPD-7110-A_build-genome-annots-tab.R from 
diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
@@ -10,6 +10,7 @@ The current GeneLab Reference Annotation Table (GL_RefAnnotTable-A) pipeline is
 3. [Setup Execution Permission for Workflow Scripts](#3-setup-execution-permission-for-workflow-scripts)
 4. [Run the workflow](#4-run-the-workflow)  
 5. [Run the annotations database creation function as a stand-alone script](#5-run-the-annotations-database-creation-function-as-a-stand-alone-script)
+6. [Run the Workflow Using Docker or Singularity](#6-run-the-workflow-using-docker-or-singularity)
 <br>
 
 ### 1. Install R and R packages
@@ -26,20 +27,20 @@ Once R is installed, open a CLI terminal and run the following command to activa
 ```bash
 R
 ```
-
+`
 Within an active R environment, run the following commands to install the required R packages:
 
 ```R
-install.packages("tidyverse", version = 2.0.0, repos = "http://cran.us.r-project.org")
+install.packages("tidyverse")
 
-install.packages("BiocManager", version = 3.19.1, repos = "http://cran.us.r-project.org")
+install.packages("BiocManager")
 
-BiocManager::install("STRINGdb", version = 3.19.1)
-BiocManager::install("PANTHER.db", version = 3.19.1)
-BiocManager::install("rtracklayer", version = 3.19.1)
-BiocManager::install("AnnotationForge", version = 1.46.0)
-BiocManager::install("biomaRt", version = 2.60.1)
-BiocManager::install("GO.db", version = 3.19.1)
+BiocManager::install("STRINGdb")
+BiocManager::install("PANTHER.db")
+BiocManager::install("rtracklayer")
+BiocManager::install("AnnotationForge")
+BiocManager::install("biomaRt")
+BiocManager::install("GO.db")
 ```
 
 <br>
@@ -102,3 +103,53 @@ Rscript install-org-db.R 'Bacillus subtilis' /path/to/GL-DPPD-7110-A_annotations
 **Output data:**
 
 - org.*.eg.db/ (species-specific annotation database, as a local R package)
+
+### 6. Run the Workflow Using Docker or Singularity
+
+Rather than running the workflow in your local environment, you can use a Docker or Singularity container. This method ensures that all dependencies are correctly installed.
+
+1. **Pull the container image:**
+
+   Docker:
+   ```bash
+   docker pull quay.io/nasa_genelab/gl-refannottable:v1.0.0
+   ```
+
+   Singularity:
+   ```bash
+   singularity pull docker://quay.io/nasa_genelab/gl-refannottable:v1.0.0
+   ```
+
+2. **Download the workflow files:**
+
+   ```bash
+   curl -LO https://github.com/nasa/GeneLab_Data_Processing/releases/download/GL_RefAnnotTable-A_1.1.0/GL_RefAnnotTable-A_1.1.0.zip
+   unzip GL_RefAnnotTable-A_1.1.0.zip
+   ```
+
+3. **Run the workflow:**
+
+   Docker:
+   ```bash
+   docker run -it -v $(pwd)/GL_RefAnnotTable-A_1.1.0:/work \
+     quay.io/nasa_genelab/gl-refannottable:v1.0.0 \
+     bash -c "cd /work && Rscript GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'"
+   ```
+
+   Singularity:
+   ```bash
+   singularity exec -B $(pwd)/GL_RefAnnotTable-A_1.1.0:/work \
+     gl-refannottable_v1.0.0.sif \
+     bash -c "cd /work && Rscript GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'"
+   ```
+
+**Input data:**
+
+- No input files are required. Specify the target organism using a positional command line argument. `Mus musculus` is used in the example above. To see a list of all available organisms, run `Rscript GL-DPPD-7110-A_build-genome-annots-tab.R` without positional arguments. The correct argument for each organism can also be found in the 'species' column of the [GL-DPPD-7110-A_annotations.csv](../../Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv)
+
+- Optional: a reference table CSV can be supplied as a second positional argument instead of using the default [GL-DPPD-7110-A_annotations.csv](../../Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv)
+
+**Output data:**
+
+- *-GL-annotations.tsv (Tab delineated table of gene annotations)
+- *-GL-build-info.txt (Text file containing information used to create the annotation table, including tool and tool versions and date of creation)
diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/workflow_code/GL-DPPD-7110-A_build-genome-annots-tab.R b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/workflow_code/GL-DPPD-7110-A_build-genome-annots-tab.R
@@ -3,6 +3,10 @@
 # GeneLab script for generating organism-specific gene annotation tables
 # Example usage: Rscript GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
 
+# Set R library path to current working directory
+lib_path <- file.path(getwd())
+.libPaths(lib_path)
+
 # Define variables associated with current pipeline and annotation table versions
 GL_DPPD_ID <- "GL-DPPD-7110-A"
 ref_tab_path <- "https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/master/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv"
diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/workflow_code/install-org-db.R b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/workflow_code/install-org-db.R
@@ -13,35 +13,36 @@ install_annotations <- function(target_organism, refTablePath) {
         filter(species == target_organism) %>%
         pull(taxon)
     
+    # Parse organism's name in the reference table to create the org.db name (target_org_db)
+    target_species_designation <- ref_table %>%
+        filter(species == target_organism) %>%
+        pull(species) %>%
+        gsub("\\s+", " ", .) %>%
+        gsub("[^A-Za-z0-9 ]", "", .)
+    
+    genus_species <- strsplit(target_species_designation, " ")[[1]]
+    if (length(genus_species) < 1) {
+        stop("Species designation is not correctly formatted: ", target_species_designation)
+    }
+    
+    genus <- genus_species[1]
+    species <- ifelse(length(genus_species) > 1, genus_species[2], "")
+    strain <- ref_table %>%
+        filter(species == target_organism) %>%
+        pull(strain) %>%
+        gsub("[^A-Za-z0-9]", "", .)
+    
+    if (!is.na(strain) && strain != "") {
+        species <- paste0(species, strain)
+    }
+    
     # Get package name or build it if not provided
     target_org_db <- ref_table %>%
         filter(species == target_organism) %>%
         pull(annotations)
     
     if (is.na(target_org_db) || target_org_db == "") {
         cat("\nNo annotation database specified. Constructing package name...\n")
-        target_species_designation <- ref_table %>%
-            filter(species == target_organism) %>%
-            pull(species) %>%
-            gsub("\\s+", " ", .) %>%
-            gsub("[^A-Za-z0-9 ]", "", .)
-        
-        genus_species <- strsplit(target_species_designation, " ")[[1]]
-        if (length(genus_species) < 1) {
-            stop("Species designation is not correctly formatted: ", target_species_designation)
-        }
-        
-        genus <- genus_species[1]
-        species <- ifelse(length(genus_species) > 1, genus_species[2], "")
-        strain <- ref_table %>%
-            filter(species == target_organism) %>%
-            pull(strain) %>%
-            gsub("[^A-Za-z0-9]", "", .)
-
-        if (!is.na(strain) && strain != "") {
-            species <- paste0(species, strain)
-        }
-        
         target_org_db <- paste0("org.", substr(genus, 1, 1), species, ".eg.db")
     }
     
@@ -56,25 +57,25 @@ install_annotations <- function(target_organism, refTablePath) {
         } else {
             cat(paste0("\nInstallation from Bioconductor failed, attempting to build '", target_org_db, "'...\n"))
             if (!dir.exists(target_org_db)) {
-            tryCatch({
-                BiocManager::install(c("AnnotationForge", "biomaRt", "GO.db"), ask = FALSE)
-                library(AnnotationForge)
-                makeOrgPackageFromNCBI(
-                    version = "0.1",
-                    author = "Your Name <your.email@example.com>",
-                    maintainer = "Your Name <your.email@example.com>",
-                    outputDir = "./",
-                    tax_id = target_taxid,
-                    genus = genus,
-                    species = species
-                )
-                install.packages(file.path("./", target_org_db), repos = NULL, type = "source", quiet = TRUE)
-                cat(paste0("'", target_org_db, "' has been successfully built and installed.\n"))
-            }, error = function(e) {
-                stop("Failed to build and load the package: ", target_org_db, "\nError: ", e$message)
-            })
+                tryCatch({
+                    BiocManager::install(c("AnnotationForge", "biomaRt", "GO.db"), ask = FALSE)
+                    library(AnnotationForge)
+                    makeOrgPackageFromNCBI(
+                        version = "0.1",
+                        author = "Your Name <your.email@example.com>",
+                        maintainer = "Your Name <your.email@example.com>",
+                        outputDir = "./",
+                        tax_id = target_taxid,
+                        genus = genus,
+                        species = species
+                    )
+                    install.packages(file.path("./", target_org_db), repos = NULL, type = "source", quiet = TRUE)
+                    cat(paste0("'", target_org_db, "' has been successfully built and installed.\n"))
+                }, error = function(e) {
+                    stop("Failed to build and load the package: ", target_org_db, "\nError: ", e$message)
+                })
             } else {
-                cat(paste0("Local annotation package ", target_org_db, " already exists. This local package will be installed."))
+                cat(paste0("Local annotation package ", target_org_db, " already exists. This local package will be installed.\n"))
                 install.packages(file.path("./", target_org_db), repos = NULL, type = "source", quiet = TRUE)
             }
         }
@@ -83,4 +84,4 @@ install_annotations <- function(target_organism, refTablePath) {
     library(target_org_db, character.only = TRUE)
     cat(paste0("Using Annotation Database '", target_org_db, "'.\n"))
     return(target_org_db)
-}
+}
