From f015225fcee1d2743d9bc6e78892dc90a738df70 Mon Sep 17 00:00:00 2001
From: Alexis <71944751+torres-alexis@users.noreply.github.com>
Date: Wed, 23 Oct 2024 13:42:34 -0700
Subject: [PATCH 01/12] remove lib path

---
 .../GL_RefAnnotTable-A/workflow_code/install-org-db.R       | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

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
index f7e6f459..c1ad5613 100644
--- 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
@@ -1,9 +1,5 @@
 # install-org-db.R
 
-# Set R library path to current working directory
-lib_path <- file.path(getwd())
-.libPaths(lib_path)
-
 # Load required libraries
 library(tidyverse)
 library(AnnotationForge)
@@ -116,4 +112,4 @@ if (!interactive()) {
   refTablePath <- if (length(args) > 1) args[2] else NULL
   
   install_annotations(target_organism, refTablePath)
-}
\ No newline at end of file
+}

From fce6a73a7389c12d1115c1b117533d478c3e6d31 Mon Sep 17 00:00:00 2001
From: Alexis <71944751+torres-alexis@users.noreply.github.com>
Date: Wed, 23 Oct 2024 13:42:49 -0700
Subject: [PATCH 02/12] Update GL-DPPD-7110-A_build-genome-annots-tab.R

remove lib path
---
 .../workflow_code/GL-DPPD-7110-A_build-genome-annots-tab.R     | 3 ---
 1 file changed, 3 deletions(-)

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
index f6b043a7..f390d4b0 100644
--- 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
@@ -3,9 +3,6 @@
 # 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"

From 3cc61cffd8096840a89cb6cd44af6fca8bd24942 Mon Sep 17 00:00:00 2001
From: Alexis <71944751+torres-alexis@users.noreply.github.com>
Date: Wed, 23 Oct 2024 14:27:30 -0700
Subject: [PATCH 03/12] Add possible paths to install-org-db execution function

---
 .../GL-DPPD-7110-A_build-genome-annots-tab.R  | 39 ++++++++++++-------
 1 file changed, 26 insertions(+), 13 deletions(-)

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
index f390d4b0..38e6f08c 100644
--- 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
@@ -145,19 +145,41 @@ GTF <- data.frame(GTF)
 
 # Define a function to load the specified org.db package for a given target organism
 install_and_load_org_db <- function(target_organism, target_org_db, ref_tab_path) {
+  # Folder names for the script location: Parent directories or . for executing from parent dir or cd.
+  ## No functionality to pull in the path of an executing R script is available
+  possible_folders <- c("workflow_code", "GL_RefAnnotTable-A_1.1.0", ".")
+  
+  # Get the current working directory and attempt to locate the correct folder
+  script_dir <- getwd()
+  
+  install_script_path <- NULL
+  
+  for (folder in possible_folders) {
+    potential_path <- file.path(script_dir, folder, "install-org-db.R")
+    if (file.exists(potential_path)) {
+      install_script_path <- potential_path
+      break
+    }
+  }
+  
+  # If the install script path was not found, stop with an error
+  if (is.null(install_script_path)) {
+    stop("Cannot find 'install-org-db.R' in the expected folders: 'workflow_code' or 'GL_RefAnnotTable-A_1.1.0'")
+  }
+  
+  # If target_org_db is provided, try to install it from Bioconductor
   if (!is.na(target_org_db) && target_org_db != "") {
-    # Attempt to install the package from Bioconductor
     BiocManager::install(target_org_db, ask = FALSE)
     
     # Check if the package was successfully loaded
     if (!requireNamespace(target_org_db, quietly = TRUE)) {
-      # If not, attempt to create it locally using a helper script
-      source("install-org-db.R")
+      # Source the install script to create the database locally
+      source(install_script_path)
       target_org_db <- install_annotations(target_organism, ref_tab_path)
     }
   } else {
     # If target_org_db is NA or empty, create it locally using the helper script
-    source("install-org-db.R")
+    source(install_script_path)
     target_org_db <- install_annotations(target_organism, ref_tab_path)
   }
   
@@ -165,15 +187,6 @@ install_and_load_org_db <- function(target_organism, target_org_db, ref_tab_path
   library(target_org_db, character.only = TRUE)
 }
 
-# Define list of supported organisms which do not use annotations from an org.db
-no_org_db <- c("Lactobacillus acidophilus", "Mycobacterium marinum", "Oryza sativa", "Pseudomonas aeruginosa",
-              "Serratia liquefaciens", "Staphylococcus aureus", "Streptococcus mutans", "Vibrio fischeri")
-
-# Run the function unless the target_organism is in no_org_db
-if (!(target_organism %in% no_org_db) && (target_organism %in% currently_accepted_orgs)) {
-  install_and_load_org_db(target_organism, target_org_db, ref_tab_path)
-}
-
 
 ############################################
 ######## Build annotation table ############

From 8619121e019a0e12d8894c0847f75151aeaf3711 Mon Sep 17 00:00:00 2001
From: Alexis <71944751+torres-alexis@users.noreply.github.com>
Date: Wed, 23 Oct 2024 14:30:43 -0700
Subject: [PATCH 04/12] Update GL-DPPD-7110-A_build-genome-annots-tab.R

Store workflow version workflow_code folder name as a variable
---
 .../workflow_code/GL-DPPD-7110-A_build-genome-annots-tab.R     | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

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
index 38e6f08c..5c62dab1 100644
--- 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
@@ -6,6 +6,7 @@
 
 # Define variables associated with current pipeline and annotation table versions
 GL_DPPD_ID <- "GL-DPPD-7110-A"
+workflow_version <- "GL_RefAnnotTable-A_1.1.0"
 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"
 readme_path <- "https://github.com/nasa/GeneLab_Data_Processing/tree/master/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md"
 
@@ -147,7 +148,7 @@ GTF <- data.frame(GTF)
 install_and_load_org_db <- function(target_organism, target_org_db, ref_tab_path) {
   # Folder names for the script location: Parent directories or . for executing from parent dir or cd.
   ## No functionality to pull in the path of an executing R script is available
-  possible_folders <- c("workflow_code", "GL_RefAnnotTable-A_1.1.0", ".")
+  possible_folders <- c("workflow_code", workflow_version, ".")
   
   # Get the current working directory and attempt to locate the correct folder
   script_dir <- getwd()

From 8bbf66d43a274adf33132e3497289d91a3d140e6 Mon Sep 17 00:00:00 2001
From: Alexis <71944751+torres-alexis@users.noreply.github.com>
Date: Wed, 23 Oct 2024 14:37:08 -0700
Subject: [PATCH 05/12] Update GL-DPPD-7110-A.md

Add workflow version variable (for finding install-org-db path) to pipeline documentation
---
 .../GL-DPPD-7110-A/GL-DPPD-7110-A.md                           | 3 +++
 1 file changed, 3 insertions(+)

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
index bf6ffa64..561fe596 100644
--- 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
@@ -188,6 +188,8 @@ lib_path <- file.path(getwd())
 
 # Define variables associated with current pipeline and annotation table versions
 GL_DPPD_ID <- "GL-DPPD-7110-A"
+workflow_version <- "GL_RefAnnotTable-A_1.1.0"
+
 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"
 readme_path <- "https://github.com/nasa/GeneLab_Data_Processing/tree/master/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md"
 
@@ -213,6 +215,7 @@ library(rtracklayer)
 **Output Data:**
 
 - `GL_DPPD_ID` (variable specifying the GeneLab Data Processing Pipeline Document ID)
+- `workflow_version (variable specifying the current version of the workflow)
 - `ref_tab_path` (variable specifying the path to the reference table CSV file)
 - `readme_path` (variable specifying the path to the README file)
 - `currently_accepted_orgs` (variable specifying the list of currently supported organisms)

From 4bec1931ace9529019f86859f843e3c9a3150a4f Mon Sep 17 00:00:00 2001
From: Alexis <71944751+torres-alexis@users.noreply.github.com>
Date: Wed, 23 Oct 2024 20:13:52 -0700
Subject: [PATCH 06/12] Update GL-DPPD-7110-A_build-genome-annots-tab.R

readd line
---
 .../GL-DPPD-7110-A_build-genome-annots-tab.R              | 8 ++++++++
 1 file changed, 8 insertions(+)

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
index 5c62dab1..afbccce8 100644
--- 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
@@ -188,6 +188,14 @@ install_and_load_org_db <- function(target_organism, target_org_db, ref_tab_path
   library(target_org_db, character.only = TRUE)
 }
 
+# Define list of supported organisms which do not use annotations from an org.db
+no_org_db <- c("Lactobacillus acidophilus", "Mycobacterium marinum", "Oryza sativa", "Pseudomonas aeruginosa",
+               "Serratia liquefaciens", "Staphylococcus aureus", "Streptococcus mutans", "Vibrio fischeri")
+
+# Run the function unless the target_organism is in no_org_db
+if (!(target_organism %in% no_org_db) && (target_organism %in% currently_accepted_orgs)) {
+  install_and_load_org_db(target_organism, target_org_db, ref_tab_path)
+}
 
 ############################################
 ######## Build annotation table ############

From d1ea649bde96b2e317adf3bc4ddbdc88a480227b Mon Sep 17 00:00:00 2001
From: torres-alexis <lextorres46@gmail.com>
Date: Mon, 28 Oct 2024 23:44:04 -0700
Subject: [PATCH 07/12] remove custom org dbs from annotation table

---
 .../GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv      | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv b/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv
index 5ce006d9..12a2c8b8 100644
--- a/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv
+++ b/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv
@@ -1,23 +1,23 @@
 name,species,strain,ensemblVersion,ref_source,fasta,gtf,taxon,annotations,genelab_annots_link,genelab_annots_info_link
 ARABIDOPSIS,Arabidopsis thaliana,,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/arabidopsis_thaliana/dna/Arabidopsis_thaliana.TAIR10.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/arabidopsis_thaliana/Arabidopsis_thaliana.TAIR10.59.gtf.gz,3702,org.At.tair.db,https://figshare.com/ndownloader/files/48354355,https://figshare.com/ndownloader/files/48354352
-BACSU,Bacillus subtilis,subsp. subtilis 168,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/dna/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.59.gtf.gz,224308,org.Bsubtilissubspsubtilis168.eg.db,https://figshare.com/ndownloader/files/48354346,https://figshare.com/ndownloader/files/48354349
-BRADI,Brachypodium distachyon,,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/brachypodium_distachyon/dna/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/brachypodium_distachyon/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.59.gtf.gz,15368,org.Bdistachyon.eg.db,https://figshare.com/ndownloader/files/48354370,https://figshare.com/ndownloader/files/48354361
+BACSU,Bacillus subtilis,subsp. subtilis 168,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/dna/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.59.gtf.gz,224308,,https://figshare.com/ndownloader/files/48354346,https://figshare.com/ndownloader/files/48354349
+BRADI,Brachypodium distachyon,,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/brachypodium_distachyon/dna/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/brachypodium_distachyon/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.59.gtf.gz,15368,,https://figshare.com/ndownloader/files/48354370,https://figshare.com/ndownloader/files/48354361
 BRARP,Brassica rapa,,59,ensembl_plants,http://ftp.ensemblgenomes.org/pub/plants/release-59/fasta/brassica_rapa/dna/Brassica_rapa.Brapa_1.0.dna.toplevel.fa.gz,http://ftp.ensemblgenomes.org/pub/plants/release-59/gtf/brassica_rapa/Brassica_rapa.Brapa_1.0.59.gtf.gz,,,,
 WORM,Caenorhabditis elegans,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/caenorhabditis_elegans/dna/Caenorhabditis_elegans.WBcel235.dna.toplevel.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/caenorhabditis_elegans/Caenorhabditis_elegans.WBcel235.112.gtf.gz,6239,org.Ce.eg.db,https://figshare.com/ndownloader/files/48354373,https://figshare.com/ndownloader/files/48354364
 ZEBRAFISH,Danio rerio,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/danio_rerio/dna/Danio_rerio.GRCz11.dna.primary_assembly.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/danio_rerio/Danio_rerio.GRCz11.112.gtf.gz,7955,org.Dr.eg.db,https://figshare.com/ndownloader/files/48354388,https://figshare.com/ndownloader/files/48354367
 FLY,Drosophila melanogaster,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/drosophila_melanogaster/dna/Drosophila_melanogaster.BDGP6.46.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/drosophila_melanogaster/Drosophila_melanogaster.BDGP6.46.112.gtf.gz,7227,org.Dm.eg.db,https://figshare.com/ndownloader/files/48354382,https://figshare.com/ndownloader/files/48354376
 ERCC,,,,ThermoFisher,https://assets.thermofisher.com/TFS-Assets/LSG/manuals/ERCC92.zip,https://assets.thermofisher.com/TFS-Assets/LSG/manuals/ERCC92.zip,,,,
-ECOLI,Escherichia coli,str. K-12 substr. MG1655,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/dna/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.59.gtf.gz,511145,org.EcolistrK12substrMG1655.eg.db,https://figshare.com/ndownloader/files/48354379,https://figshare.com/ndownloader/files/48354394
+ECOLI,Escherichia coli,str. K-12 substr. MG1655,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/dna/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.59.gtf.gz,511145,,https://figshare.com/ndownloader/files/48354379,https://figshare.com/ndownloader/files/48354394
 HUMAN,Homo sapiens,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/homo_sapiens/Homo_sapiens.GRCh38.112.gtf.gz,9606,org.Hs.eg.db,https://figshare.com/ndownloader/files/48354445,https://figshare.com/ndownloader/files/48354448
 ,Lactobacillus acidophilus,NCFM,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/985/GCF_000011985.1_ASM1198v1/GCF_000011985.1_ASM1198v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/985/GCF_000011985.1_ASM1198v1/GCF_000011985.1_ASM1198v1_genomic.gtf.gz,272621,,https://figshare.com/ndownloader/files/49061254,https://figshare.com/ndownloader/files/49061257
 MOUSE,Mus musculus,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/mus_musculus/dna/Mus_musculus.GRCm39.dna.primary_assembly.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/mus_musculus/Mus_musculus.GRCm39.112.gtf.gz,10090,org.Mm.eg.db,https://figshare.com/ndownloader/files/48354460,https://figshare.com/ndownloader/files/48354457
 ,Mycobacterium marinum,M,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/018/345/GCF_000018345.1_ASM1834v1/GCF_000018345.1_ASM1834v1_genomic.gtf.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/018/345/GCF_000018345.1_ASM1834v1/GCF_000018345.1_ASM1834v1_genomic.gtf.gz,216594,,https://figshare.com/ndownloader/files/49061260,https://figshare.com/ndownloader/files/49061263
 ORYSJ,Oryza sativa,Japonica,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/oryza_sativa/dna/Oryza_sativa.IRGSP-1.0.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/oryza_sativa/Oryza_sativa.IRGSP-1.0.59.gtf.gz,39947,,https://figshare.com/ndownloader/files/48354451,https://figshare.com/ndownloader/files/48354454
-ORYLA,Oryzias latipes,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/oryzias_latipes/dna/Oryzias_latipes.ASM223467v1.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/oryzias_latipes/Oryzias_latipes.ASM223467v1.112.gtf.gz,8090,org.Olatipes.eg.db,https://figshare.com/ndownloader/files/48354463,https://figshare.com/ndownloader/files/48354466
+ORYLA,Oryzias latipes,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/oryzias_latipes/dna/Oryzias_latipes.ASM223467v1.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/oryzias_latipes/Oryzias_latipes.ASM223467v1.112.gtf.gz,8090,,https://figshare.com/ndownloader/files/48354463,https://figshare.com/ndownloader/files/48354466
 ,Pseudomonas aeruginosa,UCBPP-PA14,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/014/625/GCF_000014625.1_ASM1462v1/GCF_000014625.1_ASM1462v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/014/625/GCF_000014625.1_ASM1462v1/GCF_000014625.1_ASM1462v1_genomic.gtf.gz,208963,,https://figshare.com/ndownloader/files/49061266,https://figshare.com/ndownloader/files/49061269
 RAT,Rattus norvegicus,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/rattus_norvegicus/dna/Rattus_norvegicus.mRatBN7.2.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/rattus_norvegicus/Rattus_norvegicus.mRatBN7.2.112.gtf.gz,10116,org.Rn.eg.db,https://figshare.com/ndownloader/files/48354472,https://figshare.com/ndownloader/files/48354475
 YEAST,Saccharomyces cerevisiae,S288C,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/saccharomyces_cerevisiae/dna/Saccharomyces_cerevisiae.R64-1-1.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/saccharomyces_cerevisiae/Saccharomyces_cerevisiae.R64-1-1.112.gtf.gz,559292,org.Sc.sgd.db,https://figshare.com/ndownloader/files/48354469,https://figshare.com/ndownloader/files/48354478
-SALTY,Salmonella enterica,serovar Typhimurium str. LT2,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.gtf.gz,99287,org.SentericaserovarTyphimuriumstrLT2.eg.db,https://figshare.com/ndownloader/files/49061272,https://figshare.com/ndownloader/files/49061275
+SALTY,Salmonella enterica,serovar Typhimurium str. LT2,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.gtf.gz,99287,,https://figshare.com/ndownloader/files/49061272,https://figshare.com/ndownloader/files/49061275
 ,Serratia liquefaciens,ATCC 27592,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/422/085/GCF_000422085.1_ASM42208v1/GCF_000422085.1_ASM42208v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/422/085/GCF_000422085.1_ASM42208v1/GCF_000422085.1_ASM42208v1_genomic.gtf.gz,1346614,,https://figshare.com/ndownloader/files/49061278,https://figshare.com/ndownloader/files/49061281
 ,Staphylococcus aureus,MRSA252,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/505/GCF_000011505.1_ASM1150v1/GCF_000011505.1_ASM1150v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/505/GCF_000011505.1_ASM1150v1/GCF_000011505.1_ASM1150v1_genomic.gtf.gz,282458,,https://figshare.com/ndownloader/files/49061284,https://figshare.com/ndownloader/files/49061287
 ,Streptococcus mutans,UA159,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/007/465/GCF_000007465.2_ASM746v2/GCF_000007465.2_ASM746v2_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/007/465/GCF_000007465.2_ASM746v2/GCF_000007465.2_ASM746v2_genomic.gtf.gz,210007,,https://figshare.com/ndownloader/files/49061290,https://figshare.com/ndownloader/files/49061293

From f06cf149b9048c2eb6935c8398802ef3ef49e52f Mon Sep 17 00:00:00 2001
From: torres-alexis <lextorres46@gmail.com>
Date: Wed, 30 Oct 2024 13:38:21 -0700
Subject: [PATCH 08/12] move timeout to top of scripts, add to readme

---
 .../GL_RefAnnotTable-A/README.md                  |  4 ++++
 .../GL-DPPD-7110-A_build-genome-annots-tab.R      | 15 ++++++---------
 .../workflow_code/install-org-db.R                |  2 +-
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
index e3990af5..2b84e200 100644
--- a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
+++ b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
@@ -54,6 +54,8 @@ The GL_RefAnnotTable-A workflow can be run using one of two approaches:
 
 Please follow the instructions for the approach that best matches your setup and preferences. Each method is explained in detail below. 
 
+> **Note**: If you encounter timeout errors, you can increase the default timeout (3600 seconds) by modifying the `options(timeout=3600)` line at the top of the `GL-DPPD-7110-A_build-genome-annots-tab.R` script.
+
 <br> 
 
 ---
@@ -198,6 +200,8 @@ The input and output data are the same for both [Approach 1: Using Singularity](
 
 If the reference table does not specify an annotations database for the target organism in the 'annotations' column of the [GL-DPPD-7110-A_annotations.csv](../../Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv) file, the `install_annotations` function (defined in `install-org-db.R`) will be executed by default. This function can also be run as a stand-alone script:
 
+> **Note**: If you encounter timeout errors, you can increase the default timeout (3600 seconds) by modifying the `options(timeout=3600)` line at the top of the `install-org-db.R` script.
+
 <br>
 
 #### Using Singularity 
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
index afbccce8..1254920a 100644
--- 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
@@ -2,7 +2,7 @@
 # Written by Mike Lee
 # GeneLab script for generating organism-specific gene annotation tables
 # Example usage: Rscript GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
-
+options(timeout = 3600)
 
 # Define variables associated with current pipeline and annotation table versions
 GL_DPPD_ID <- "GL-DPPD-7110-A"
@@ -80,9 +80,6 @@ library(rtracklayer)
 ############## Define variables and output file names ###################
 #########################################################################
 
-# Set timeout time to ensure annotation file downloads will complete
-options(timeout = 600)
-
 ref_table <- tryCatch(
   read.csv(ref_tab_path),
   error = function(e) {
@@ -133,9 +130,6 @@ if ( file.exists(out_table_filename) ) {
 ######## Load annotation databases  #########
 #############################################
 
-# Set timeout time to ensure annotation file downloads will complete
-options(timeout = 600)
-
 ####### GTF ##########
 
 # Create the GTF dataframe from its path, unique gene identities in the reference assembly are under 'gene_id'
@@ -186,15 +180,18 @@ install_and_load_org_db <- function(target_organism, target_org_db, ref_tab_path
   
   # Load the package into the R session
   library(target_org_db, character.only = TRUE)
+  
+  # Return the target_org_db name
+  return(target_org_db)
 }
 
 # Define list of supported organisms which do not use annotations from an org.db
 no_org_db <- c("Lactobacillus acidophilus", "Mycobacterium marinum", "Oryza sativa", "Pseudomonas aeruginosa",
                "Serratia liquefaciens", "Staphylococcus aureus", "Streptococcus mutans", "Vibrio fischeri")
 
-# Run the function unless the target_organism is in no_org_db
+# Run the function unless the target_organism is in no_org_db and update target_org_db with the result
 if (!(target_organism %in% no_org_db) && (target_organism %in% currently_accepted_orgs)) {
-  install_and_load_org_db(target_organism, target_org_db, ref_tab_path)
+  target_org_db <- install_and_load_org_db(target_organism, target_org_db, ref_tab_path)
 }
 
 ############################################
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
index c1ad5613..fb8fe1a2 100644
--- 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
@@ -1,5 +1,5 @@
 # install-org-db.R
-
+options(timeout=3600)
 # Load required libraries
 library(tidyverse)
 library(AnnotationForge)

From 5088539f028bfe75a466474b488ef86e56e83e2c Mon Sep 17 00:00:00 2001
From: torres-alexis <lextorres46@gmail.com>
Date: Wed, 30 Oct 2024 13:41:59 -0700
Subject: [PATCH 09/12] add no-home + bind local path to same container path

---
 .../Workflow_Documentation/GL_RefAnnotTable-A/README.md   | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
index 2b84e200..fdbe9f11 100644
--- a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
+++ b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
@@ -106,9 +106,9 @@ While in the directory containing the `GL_RefAnnotTable-A_1.1.0` folder that was
  
 
 ```bash
-singularity exec -B $(pwd)/GL_RefAnnotTable-A_1.1.0:/work \
+singularity exec --no-home -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
 $SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
-Rscript /work/GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
+Rscript GL_RefAnnotTable-A_1.1.0/GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
 ```
 
 <br> 
@@ -207,9 +207,9 @@ If the reference table does not specify an annotations database for the target o
 #### Using Singularity 
 
 ```bash
-singularity exec -B $(pwd)/GL_RefAnnotTable-A_1.1.0:/work \
+singularity exec --no-home -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
 $SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
-Rscript /work/install-org-db.R 'Bacillus subtilis'
+Rscript GL_RefAnnotTable-A_1.1.0/install-org-db.R 'Bacillus subtilis'
 ```
  
 <br>

From 63683814c083e4ac7fab50e5735f6165a6b2ddbf Mon Sep 17 00:00:00 2001
From: torres-alexis <lextorres46@gmail.com>
Date: Wed, 30 Oct 2024 19:08:22 -0700
Subject: [PATCH 10/12] add cols bioconductor_annotations, custom_annotations,
 change dppd var workflow_version

---
 .../GL-DPPD-7110-A/GL-DPPD-7110-A.md          |  8 ++--
 .../GL-DPPD-7110-A_annotations.csv            | 48 +++++++++----------
 .../GL-DPPD-7110-A_build-genome-annots-tab.R  |  2 +-
 .../workflow_code/install-org-db.R            |  2 +-
 4 files changed, 30 insertions(+), 30 deletions(-)

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
index 561fe596..0fba4029 100644
--- 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
@@ -188,7 +188,7 @@ lib_path <- file.path(getwd())
 
 # Define variables associated with current pipeline and annotation table versions
 GL_DPPD_ID <- "GL-DPPD-7110-A"
-workflow_version <- "GL_RefAnnotTable-A_1.1.0"
+workflow_version <- ""
 
 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"
 readme_path <- "https://github.com/nasa/GeneLab_Data_Processing/tree/master/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md"
@@ -215,7 +215,7 @@ library(rtracklayer)
 **Output Data:**
 
 - `GL_DPPD_ID` (variable specifying the GeneLab Data Processing Pipeline Document ID)
-- `workflow_version (variable specifying the current version of the workflow)
+- `workflow_version` (variable specifying the [current version of the workflow](https://github.com/nasa/GeneLab_Data_Processing/tree/DEV_GeneLab_Reference_Annotations_vGL-DPPD-7110-A/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A))
 - `ref_tab_path` (variable specifying the path to the reference table CSV file)
 - `readme_path` (variable specifying the path to the README file)
 - `currently_accepted_orgs` (variable specifying the list of currently supported organisms)
@@ -244,7 +244,7 @@ target_info <- ref_table %>%
 
 # Extract the relevant columns from the reference table
 target_taxid <- target_info$taxon # Taxonomic identifier
-target_org_db <- target_info$annotations # org.eg.db R package
+target_org_db <- target_info$bioconductor_annotations # org.eg.db R package
 gtf_link <- target_info$gtf # Path to reference assembly GTF
 target_short_name <- target_info$name # PANTHER / UNIPROT short name; blank if not available
 ref_source <- target_info$ref_source # Reference files source  
@@ -284,7 +284,7 @@ if ( file.exists(out_table_filename) ) {
 **Output Data:**
 
 - `target_taxid` (variable specifying the taxonomic identifier for the target organism)
-- `target_org_db` (variable specifying the name of the org.db R package for the target organism)
+- `target_org_db` (variable specifying the name of the org.eg.db R package for the target organism if it is hosted by Bioconductor)
 - `gtf_link` (variable specifying the URL to the GTF file for the target organism)
 - `target_short_name` (variable specifying the PANTHER/UNIPROT short name for the target organism)
 - `ref_source` (variable specifying the source of the reference files, e.g., "ensembl", "ensembl_plants", "ensembl_bacteria", "ncbi")
diff --git a/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv b/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv
index 12a2c8b8..c2a881e2 100644
--- a/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv
+++ b/GeneLab_Reference_Annotations/Pipeline_GL-DPPD-7110_Versions/GL-DPPD-7110-A/GL-DPPD-7110-A_annotations.csv
@@ -1,24 +1,24 @@
-name,species,strain,ensemblVersion,ref_source,fasta,gtf,taxon,annotations,genelab_annots_link,genelab_annots_info_link
-ARABIDOPSIS,Arabidopsis thaliana,,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/arabidopsis_thaliana/dna/Arabidopsis_thaliana.TAIR10.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/arabidopsis_thaliana/Arabidopsis_thaliana.TAIR10.59.gtf.gz,3702,org.At.tair.db,https://figshare.com/ndownloader/files/48354355,https://figshare.com/ndownloader/files/48354352
-BACSU,Bacillus subtilis,subsp. subtilis 168,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/dna/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.59.gtf.gz,224308,,https://figshare.com/ndownloader/files/48354346,https://figshare.com/ndownloader/files/48354349
-BRADI,Brachypodium distachyon,,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/brachypodium_distachyon/dna/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/brachypodium_distachyon/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.59.gtf.gz,15368,,https://figshare.com/ndownloader/files/48354370,https://figshare.com/ndownloader/files/48354361
-BRARP,Brassica rapa,,59,ensembl_plants,http://ftp.ensemblgenomes.org/pub/plants/release-59/fasta/brassica_rapa/dna/Brassica_rapa.Brapa_1.0.dna.toplevel.fa.gz,http://ftp.ensemblgenomes.org/pub/plants/release-59/gtf/brassica_rapa/Brassica_rapa.Brapa_1.0.59.gtf.gz,,,,
-WORM,Caenorhabditis elegans,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/caenorhabditis_elegans/dna/Caenorhabditis_elegans.WBcel235.dna.toplevel.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/caenorhabditis_elegans/Caenorhabditis_elegans.WBcel235.112.gtf.gz,6239,org.Ce.eg.db,https://figshare.com/ndownloader/files/48354373,https://figshare.com/ndownloader/files/48354364
-ZEBRAFISH,Danio rerio,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/danio_rerio/dna/Danio_rerio.GRCz11.dna.primary_assembly.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/danio_rerio/Danio_rerio.GRCz11.112.gtf.gz,7955,org.Dr.eg.db,https://figshare.com/ndownloader/files/48354388,https://figshare.com/ndownloader/files/48354367
-FLY,Drosophila melanogaster,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/drosophila_melanogaster/dna/Drosophila_melanogaster.BDGP6.46.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/drosophila_melanogaster/Drosophila_melanogaster.BDGP6.46.112.gtf.gz,7227,org.Dm.eg.db,https://figshare.com/ndownloader/files/48354382,https://figshare.com/ndownloader/files/48354376
-ERCC,,,,ThermoFisher,https://assets.thermofisher.com/TFS-Assets/LSG/manuals/ERCC92.zip,https://assets.thermofisher.com/TFS-Assets/LSG/manuals/ERCC92.zip,,,,
-ECOLI,Escherichia coli,str. K-12 substr. MG1655,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/dna/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.59.gtf.gz,511145,,https://figshare.com/ndownloader/files/48354379,https://figshare.com/ndownloader/files/48354394
-HUMAN,Homo sapiens,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/homo_sapiens/Homo_sapiens.GRCh38.112.gtf.gz,9606,org.Hs.eg.db,https://figshare.com/ndownloader/files/48354445,https://figshare.com/ndownloader/files/48354448
-,Lactobacillus acidophilus,NCFM,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/985/GCF_000011985.1_ASM1198v1/GCF_000011985.1_ASM1198v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/985/GCF_000011985.1_ASM1198v1/GCF_000011985.1_ASM1198v1_genomic.gtf.gz,272621,,https://figshare.com/ndownloader/files/49061254,https://figshare.com/ndownloader/files/49061257
-MOUSE,Mus musculus,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/mus_musculus/dna/Mus_musculus.GRCm39.dna.primary_assembly.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/mus_musculus/Mus_musculus.GRCm39.112.gtf.gz,10090,org.Mm.eg.db,https://figshare.com/ndownloader/files/48354460,https://figshare.com/ndownloader/files/48354457
-,Mycobacterium marinum,M,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/018/345/GCF_000018345.1_ASM1834v1/GCF_000018345.1_ASM1834v1_genomic.gtf.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/018/345/GCF_000018345.1_ASM1834v1/GCF_000018345.1_ASM1834v1_genomic.gtf.gz,216594,,https://figshare.com/ndownloader/files/49061260,https://figshare.com/ndownloader/files/49061263
-ORYSJ,Oryza sativa,Japonica,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/oryza_sativa/dna/Oryza_sativa.IRGSP-1.0.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/oryza_sativa/Oryza_sativa.IRGSP-1.0.59.gtf.gz,39947,,https://figshare.com/ndownloader/files/48354451,https://figshare.com/ndownloader/files/48354454
-ORYLA,Oryzias latipes,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/oryzias_latipes/dna/Oryzias_latipes.ASM223467v1.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/oryzias_latipes/Oryzias_latipes.ASM223467v1.112.gtf.gz,8090,,https://figshare.com/ndownloader/files/48354463,https://figshare.com/ndownloader/files/48354466
-,Pseudomonas aeruginosa,UCBPP-PA14,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/014/625/GCF_000014625.1_ASM1462v1/GCF_000014625.1_ASM1462v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/014/625/GCF_000014625.1_ASM1462v1/GCF_000014625.1_ASM1462v1_genomic.gtf.gz,208963,,https://figshare.com/ndownloader/files/49061266,https://figshare.com/ndownloader/files/49061269
-RAT,Rattus norvegicus,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/rattus_norvegicus/dna/Rattus_norvegicus.mRatBN7.2.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/rattus_norvegicus/Rattus_norvegicus.mRatBN7.2.112.gtf.gz,10116,org.Rn.eg.db,https://figshare.com/ndownloader/files/48354472,https://figshare.com/ndownloader/files/48354475
-YEAST,Saccharomyces cerevisiae,S288C,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/saccharomyces_cerevisiae/dna/Saccharomyces_cerevisiae.R64-1-1.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/saccharomyces_cerevisiae/Saccharomyces_cerevisiae.R64-1-1.112.gtf.gz,559292,org.Sc.sgd.db,https://figshare.com/ndownloader/files/48354469,https://figshare.com/ndownloader/files/48354478
-SALTY,Salmonella enterica,serovar Typhimurium str. LT2,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.gtf.gz,99287,,https://figshare.com/ndownloader/files/49061272,https://figshare.com/ndownloader/files/49061275
-,Serratia liquefaciens,ATCC 27592,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/422/085/GCF_000422085.1_ASM42208v1/GCF_000422085.1_ASM42208v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/422/085/GCF_000422085.1_ASM42208v1/GCF_000422085.1_ASM42208v1_genomic.gtf.gz,1346614,,https://figshare.com/ndownloader/files/49061278,https://figshare.com/ndownloader/files/49061281
-,Staphylococcus aureus,MRSA252,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/505/GCF_000011505.1_ASM1150v1/GCF_000011505.1_ASM1150v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/505/GCF_000011505.1_ASM1150v1/GCF_000011505.1_ASM1150v1_genomic.gtf.gz,282458,,https://figshare.com/ndownloader/files/49061284,https://figshare.com/ndownloader/files/49061287
-,Streptococcus mutans,UA159,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/007/465/GCF_000007465.2_ASM746v2/GCF_000007465.2_ASM746v2_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/007/465/GCF_000007465.2_ASM746v2/GCF_000007465.2_ASM746v2_genomic.gtf.gz,210007,,https://figshare.com/ndownloader/files/49061290,https://figshare.com/ndownloader/files/49061293
-,Vibrio fischeri,ES114,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/805/GCF_000011805.1_ASM1180v1/GCF_000011805.1_ASM1180v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/805/GCF_000011805.1_ASM1180v1/GCF_000011805.1_ASM1180v1_genomic.gtf.gz,312309,,https://figshare.com/ndownloader/files/49061296,https://figshare.com/ndownloader/files/49061299
\ No newline at end of file
+name,species,strain,ensemblVersion,ref_source,fasta,gtf,taxon,bioconductor_annotations,custom_annotations,genelab_annots_link,genelab_annots_info_link
+ARABIDOPSIS,Arabidopsis thaliana,,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/arabidopsis_thaliana/dna/Arabidopsis_thaliana.TAIR10.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/arabidopsis_thaliana/Arabidopsis_thaliana.TAIR10.59.gtf.gz,3702,org.At.tair.db,,https://figshare.com/ndownloader/files/48354355,https://figshare.com/ndownloader/files/48354352
+BACSU,Bacillus subtilis,subsp. subtilis 168,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/dna/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/bacillus_subtilis_subsp_subtilis_str_168_gca_000009045/Bacillus_subtilis_subsp_subtilis_str_168_gca_000009045.ASM904v1.59.gtf.gz,224308,,org.Bsubtilissubspsubtilis168.eg.db,https://figshare.com/ndownloader/files/48354346,https://figshare.com/ndownloader/files/48354349
+BRADI,Brachypodium distachyon,,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/brachypodium_distachyon/dna/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/brachypodium_distachyon/Brachypodium_distachyon.Brachypodium_distachyon_v3.0.59.gtf.gz,15368,,org.Bdistachyon.eg.db,https://figshare.com/ndownloader/files/48354370,https://figshare.com/ndownloader/files/48354361
+BRARP,Brassica rapa,,59,ensembl_plants,http://ftp.ensemblgenomes.org/pub/plants/release-59/fasta/brassica_rapa/dna/Brassica_rapa.Brapa_1.0.dna.toplevel.fa.gz,http://ftp.ensemblgenomes.org/pub/plants/release-59/gtf/brassica_rapa/Brassica_rapa.Brapa_1.0.59.gtf.gz,,,,,
+WORM,Caenorhabditis elegans,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/caenorhabditis_elegans/dna/Caenorhabditis_elegans.WBcel235.dna.toplevel.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/caenorhabditis_elegans/Caenorhabditis_elegans.WBcel235.112.gtf.gz,6239,org.Ce.eg.db,,https://figshare.com/ndownloader/files/48354373,https://figshare.com/ndownloader/files/48354364
+ZEBRAFISH,Danio rerio,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/danio_rerio/dna/Danio_rerio.GRCz11.dna.primary_assembly.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/danio_rerio/Danio_rerio.GRCz11.112.gtf.gz,7955,org.Dr.eg.db,,https://figshare.com/ndownloader/files/48354388,https://figshare.com/ndownloader/files/48354367
+FLY,Drosophila melanogaster,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/drosophila_melanogaster/dna/Drosophila_melanogaster.BDGP6.46.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/drosophila_melanogaster/Drosophila_melanogaster.BDGP6.46.112.gtf.gz,7227,org.Dm.eg.db,,https://figshare.com/ndownloader/files/48354382,https://figshare.com/ndownloader/files/48354376
+ERCC,,,,ThermoFisher,https://assets.thermofisher.com/TFS-Assets/LSG/manuals/ERCC92.zip,https://assets.thermofisher.com/TFS-Assets/LSG/manuals/ERCC92.zip,,,,,
+ECOLI,Escherichia coli,str. K-12 substr. MG1655,59,ensembl_bacteria,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/fasta/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/dna/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/bacteria/release-59/gtf/bacteria_0_collection/escherichia_coli_str_k_12_substr_mg1655_gca_000005845/Escherichia_coli_str_k_12_substr_mg1655_gca_000005845.ASM584v2.59.gtf.gz,511145,,org.EcolistrK12substrMG1655.eg.db,https://figshare.com/ndownloader/files/48354379,https://figshare.com/ndownloader/files/48354394
+HUMAN,Homo sapiens,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/homo_sapiens/Homo_sapiens.GRCh38.112.gtf.gz,9606,org.Hs.eg.db,,https://figshare.com/ndownloader/files/48354445,https://figshare.com/ndownloader/files/48354448
+,Lactobacillus acidophilus,NCFM,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/985/GCF_000011985.1_ASM1198v1/GCF_000011985.1_ASM1198v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/985/GCF_000011985.1_ASM1198v1/GCF_000011985.1_ASM1198v1_genomic.gtf.gz,272621,,,https://figshare.com/ndownloader/files/49061254,https://figshare.com/ndownloader/files/49061257
+MOUSE,Mus musculus,,112,ensembl,https://ftp.ensembl.org/pub/release-112/fasta/mus_musculus/dna/Mus_musculus.GRCm39.dna.primary_assembly.fa.gz,https://ftp.ensembl.org/pub/release-112/gtf/mus_musculus/Mus_musculus.GRCm39.112.gtf.gz,10090,org.Mm.eg.db,,https://figshare.com/ndownloader/files/48354460,https://figshare.com/ndownloader/files/48354457
+,Mycobacterium marinum,M,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/018/345/GCF_000018345.1_ASM1834v1/GCF_000018345.1_ASM1834v1_genomic.gtf.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/018/345/GCF_000018345.1_ASM1834v1/GCF_000018345.1_ASM1834v1_genomic.gtf.gz,216594,,,https://figshare.com/ndownloader/files/49061260,https://figshare.com/ndownloader/files/49061263
+ORYSJ,Oryza sativa,Japonica,59,ensembl_plants,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/fasta/oryza_sativa/dna/Oryza_sativa.IRGSP-1.0.dna.toplevel.fa.gz,https://ftp.ensemblgenomes.ebi.ac.uk/pub/plants/release-59/gtf/oryza_sativa/Oryza_sativa.IRGSP-1.0.59.gtf.gz,39947,,,https://figshare.com/ndownloader/files/48354451,https://figshare.com/ndownloader/files/48354454
+ORYLA,Oryzias latipes,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/oryzias_latipes/dna/Oryzias_latipes.ASM223467v1.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/oryzias_latipes/Oryzias_latipes.ASM223467v1.112.gtf.gz,8090,,org.Olatipes.eg.db,https://figshare.com/ndownloader/files/48354463,https://figshare.com/ndownloader/files/48354466
+,Pseudomonas aeruginosa,UCBPP-PA14,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/014/625/GCF_000014625.1_ASM1462v1/GCF_000014625.1_ASM1462v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/014/625/GCF_000014625.1_ASM1462v1/GCF_000014625.1_ASM1462v1_genomic.gtf.gz,208963,,,https://figshare.com/ndownloader/files/49061266,https://figshare.com/ndownloader/files/49061269
+RAT,Rattus norvegicus,,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/rattus_norvegicus/dna/Rattus_norvegicus.mRatBN7.2.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/rattus_norvegicus/Rattus_norvegicus.mRatBN7.2.112.gtf.gz,10116,org.Rn.eg.db,,https://figshare.com/ndownloader/files/48354472,https://figshare.com/ndownloader/files/48354475
+YEAST,Saccharomyces cerevisiae,S288C,112,ensembl,http://ftp.ensembl.org/pub/release-112/fasta/saccharomyces_cerevisiae/dna/Saccharomyces_cerevisiae.R64-1-1.dna.toplevel.fa.gz,http://ftp.ensembl.org/pub/release-112/gtf/saccharomyces_cerevisiae/Saccharomyces_cerevisiae.R64-1-1.112.gtf.gz,559292,org.Sc.sgd.db,,https://figshare.com/ndownloader/files/48354469,https://figshare.com/ndownloader/files/48354478
+SALTY,Salmonella enterica,serovar Typhimurium str. LT2,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2/GCF_000006945.2_ASM694v2_genomic.gtf.gz,99287,,org.SentericaserovarTyphimuriumstrLT2.eg.db,https://figshare.com/ndownloader/files/49061272,https://figshare.com/ndownloader/files/49061275
+,Serratia liquefaciens,ATCC 27592,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/422/085/GCF_000422085.1_ASM42208v1/GCF_000422085.1_ASM42208v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/422/085/GCF_000422085.1_ASM42208v1/GCF_000422085.1_ASM42208v1_genomic.gtf.gz,1346614,,,https://figshare.com/ndownloader/files/49061278,https://figshare.com/ndownloader/files/49061281
+,Staphylococcus aureus,MRSA252,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/505/GCF_000011505.1_ASM1150v1/GCF_000011505.1_ASM1150v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/505/GCF_000011505.1_ASM1150v1/GCF_000011505.1_ASM1150v1_genomic.gtf.gz,282458,,,https://figshare.com/ndownloader/files/49061284,https://figshare.com/ndownloader/files/49061287
+,Streptococcus mutans,UA159,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/007/465/GCF_000007465.2_ASM746v2/GCF_000007465.2_ASM746v2_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/007/465/GCF_000007465.2_ASM746v2/GCF_000007465.2_ASM746v2_genomic.gtf.gz,210007,,,https://figshare.com/ndownloader/files/49061290,https://figshare.com/ndownloader/files/49061293
+,Vibrio fischeri,ES114,,ncbi,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/805/GCF_000011805.1_ASM1180v1/GCF_000011805.1_ASM1180v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/011/805/GCF_000011805.1_ASM1180v1/GCF_000011805.1_ASM1180v1_genomic.gtf.gz,312309,,,https://figshare.com/ndownloader/files/49061296,https://figshare.com/ndownloader/files/49061299
\ No newline at end of file
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
index 1254920a..058aea71 100644
--- 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
@@ -94,7 +94,7 @@ target_info <- ref_table %>%
 
 # Extract the relevant columns from the reference table
 target_taxid <- target_info$taxon # Taxonomic identifier
-target_org_db <- target_info$annotations # org.eg.db R package
+target_org_db <- target_info$bioconductor_annotations # org.eg.db R package
 gtf_link <- target_info$gtf # Path to reference assembly GTF
 target_short_name <- target_info$name # PANTHER / UNIPROT short name; blank if not available
 ref_source <- target_info$ref_source # Reference files source  
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
index fb8fe1a2..72421811 100644
--- 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
@@ -52,7 +52,7 @@ install_annotations <- function(target_organism, refTablePath = NULL) {
     # Get package name or build it if not provided
     target_org_db <- ref_table %>%
         filter(species == target_organism) %>%
-        pull(annotations)
+        pull(bioconductor_annotations)
     
     if (is.na(target_org_db) || target_org_db == "") {
         cat("\nNo annotation database specified. Constructing package name...\n")

From b39c63c147cb5ef30f7d255d2a4f65c8a4cdd8d4 Mon Sep 17 00:00:00 2001
From: torres-alexis <lextorres46@gmail.com>
Date: Wed, 30 Oct 2024 21:05:53 -0700
Subject: [PATCH 11/12] remove --no-home from readme

---
 .../Workflow_Documentation/GL_RefAnnotTable-A/README.md       | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
index fdbe9f11..92ff4dbd 100644
--- a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
+++ b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
@@ -106,7 +106,7 @@ While in the directory containing the `GL_RefAnnotTable-A_1.1.0` folder that was
  
 
 ```bash
-singularity exec --no-home -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
+singularity exec -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
 $SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
 Rscript GL_RefAnnotTable-A_1.1.0/GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
 ```
@@ -207,7 +207,7 @@ If the reference table does not specify an annotations database for the target o
 #### Using Singularity 
 
 ```bash
-singularity exec --no-home -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
+singularity exec -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
 $SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
 Rscript GL_RefAnnotTable-A_1.1.0/install-org-db.R 'Bacillus subtilis'
 ```

From dcdf589d00ed4e417c88a2392684d69590cb34c0 Mon Sep 17 00:00:00 2001
From: Alexis Torres <lextorres46@gmail.com>
Date: Thu, 31 Oct 2024 14:32:42 -0700
Subject: [PATCH 12/12] Add r_libs to scrips, readme, standardize notes

---
 .../GL_RefAnnotTable-A/README.md              | 40 ++++++++++++-------
 .../GL-DPPD-7110-A_build-genome-annots-tab.R  |  2 +-
 .../workflow_code/install-org-db.R            |  1 +
 3 files changed, 27 insertions(+), 16 deletions(-)

diff --git a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
index 92ff4dbd..aefe1a3b 100644
--- a/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
+++ b/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/README.md
@@ -70,13 +70,13 @@ This approach allows you to run the workflow within a containerized environment,
 
 Singularity is a containerization platform for running applications portably and reproducibly. We use container images hosted on Quay.io to encapsulate all the necessary software and dependencies required by the GL_RefAnnotTable-A workflow. This setup allows you to run the workflow without installing any software directly on your system. 
   
-> ***Note**: Other containerization tools like Docker or Apptainer can also be used to pull and run these images.*
+> **Note**: Other containerization tools like Docker or Apptainer can also be used to pull and run these images.
    
 
 We recommend installing Singularity system-wide as per the official [Singularity installation documentation](https://docs.sylabs.io/guides/3.10/admin-guide/admin_quickstart.html).  
  
 
-> ***Note**: While Singularity is also available through [Anaconda](https://anaconda.org/conda-forge/singularity), we recommend installing Singularity system-wide following the official installation documentation.*
+> **Note**: While Singularity is also available through [Anaconda](https://anaconda.org/conda-forge/singularity), we recommend installing Singularity system-wide following the official installation documentation.
 
 <br> 
 
@@ -84,17 +84,19 @@ We recommend installing Singularity system-wide as per the official [Singularity
 
 To pull the Singularity image needed for the workflow, you can use the provided script as directed below or pull the image directly.  
 
-> ***Note**: This command should be run in the location containing the `GL_RefAnnotTable-A_1.1.0` directory that was downloaded in [step 1](#1-download-the-workflow-files). Depending on your network speed, fetching the images will take approximately 20 minutes.*  
- 
+> **Note**: This command should be run in the location containing the `GL_RefAnnotTable-A_1.1.0` directory that was downloaded in [step 1](#1-download-the-workflow-files). Depending on your network speed, fetching the images will take approximately 20 minutes.
 
 ```bash
 bash GL_RefAnnotTable-A_1.1.0/bin/prepull_singularity.sh GL_RefAnnotTable-A_1.1.0/config/software/by_docker_image.config
 ```
  
-Once complete, a `singularity` folder containing the Singularity images will be created. Run the following command to export this folder as an environment variable:  
- 
+Once complete, a `singularity` folder containing the Singularity images will be created. Next, set up the required environment variables:
 
 ```bash
+# Set R library path to current working directory
+export R_LIBS_USER=$(pwd)/R_libs
+
+# Set Singularity cache directory 
 export SINGULARITY_CACHEDIR=$(pwd)/singularity
 ```
 
@@ -102,13 +104,15 @@ export SINGULARITY_CACHEDIR=$(pwd)/singularity
 
 #### Step 3: Run the Workflow
 
-While in the directory containing the `GL_RefAnnotTable-A_1.1.0` folder that was downloaded in [step 1](#1-download-the-workflow-files), you can now run the workflow. Below is an example for generating the annotation table for *Mus musculus* (mouse): 
- 
+> **Note**: The annotation database creation process requires FTP access through port 21. If you encounter connection issues, please verify that port 21 is not blocked by your network/firewall settings or try running the workflow on a system with unrestricted FTP access.
+
+While in the directory containing the `GL_RefAnnotTable-A_1.1.0` folder that was downloaded in [step 1](#1-download-the-workflow-files), you can now run the workflow. Below is an example for generating the annotation table for *Mus musculus* (mouse):
 
 ```bash
-singularity exec -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
-$SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
-Rscript GL_RefAnnotTable-A_1.1.0/GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
+singularity exec \
+    --bind $(pwd):$(pwd) \
+    $SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
+    Rscript GL_RefAnnotTable-A_1.1.0/GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
 ```
 
 <br> 
@@ -206,12 +210,18 @@ If the reference table does not specify an annotations database for the target o
 
 #### Using Singularity 
 
+> **Note**: The annotation database creation process requires FTP access through port 21. If you encounter connection issues, please verify that port 21 is not blocked by your network/firewall settings.
+
 ```bash
-singularity exec -B $(pwd)/GL_RefAnnotTable-A_1.1.0:$(pwd)/GL_RefAnnotTable-A_1.1.0 \
-$SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
-Rscript GL_RefAnnotTable-A_1.1.0/install-org-db.R 'Bacillus subtilis'
+# Set R library path if not already set
+export R_LIBS_USER=$(pwd)/R_libs
+
+singularity exec \
+    --bind $(pwd):$(pwd) \
+    $SINGULARITY_CACHEDIR/quay.io-nasa_genelab-gl-refannottable-a-1.1.0.img \
+    Rscript GL_RefAnnotTable-A_1.1.0/install-org-db.R 'Bacillus subtilis'
 ```
- 
+
 <br>
 
 #### Using a Local R Environment
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
index 058aea71..46923217 100644
--- 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
@@ -3,7 +3,7 @@
 # GeneLab script for generating organism-specific gene annotation tables
 # Example usage: Rscript GL-DPPD-7110-A_build-genome-annots-tab.R 'Mus musculus'
 options(timeout = 3600)
-
+.libPaths(Sys.getenv("R_LIBS_USER"))
 # Define variables associated with current pipeline and annotation table versions
 GL_DPPD_ID <- "GL-DPPD-7110-A"
 workflow_version <- "GL_RefAnnotTable-A_1.1.0"
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
index 72421811..00f03548 100644
--- 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
@@ -1,5 +1,6 @@
 # install-org-db.R
 options(timeout=3600)
+.libPaths(Sys.getenv("R_LIBS_USER"))
 # Load required libraries
 library(tidyverse)
 library(AnnotationForge)