[GL_RefAnnotTable] Fix R packages, add docker instructions

Author: torres-alexis

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) |
@@ -294,42 +294,58 @@ 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]]
+    # Define genus and species regardless of 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_organism)
+      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)
+      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)
 }
 ```
 

GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md

@@ -26,20 +26,20 @@ 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 +102,37 @@ 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
+
+Rather than running the workflow in your local environment, you can use a Docker image. This method ensures that all dependencies are correctly installed.
+
+1. **Pull the Docker image:**
+
+   ```bash
+   docker pull quay.io/torres-alexis/gl_images:GL_RefAnnotTable_v1.1.0-rc.1
+   ```
+
+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 using Docker:**
+
+   ```bash
+   docker run -it -v $(pwd)/GL_RefAnnotTable-A_1.1.0:/home/rstudio/work quay.io/torres-alexis/gl_images:GL_RefAnnotTable_v1.1.0-rc.1 bash -c "cd /home/rstudio/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)

GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/workflow_code/install-org-db.R

@@ -1,8 +1,3 @@
-# install-org-db.R
-
-# Function: Get annotations db from ref table. If no annotations db is defined, create the package name from genus, species, (and strain for microbes), 
-# Try to Bioconductor install annotations db. If fail then build the package using AnnotationForge, install it into the current directory.
-# Requires ~80GB for NCBIFilesDir file caching
 install_annotations <- function(target_organism, refTablePath) {
     if (!file.exists(refTablePath)) {
         stop("Reference table file does not exist at the specified path: ", refTablePath)
@@ -13,35 +8,36 @@ install_annotations <- function(target_organism, refTablePath) {
         filter(species == target_organism) %>%
         pull(taxon)
 
+    # Define genus and species regardless of 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 +52,25 @@ 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 +79,4 @@ 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)
-}
+}