SW_AmpIllumina-B: Rscript execution readme updates

Author: torres-alexis

Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/workflow_code/Snakefile

@@ -635,7 +635,7 @@ if config["data_type"] == "SE":
 rule r_visualizations:
     """ This rule generates R visualizations using trimmed read data and grouping info from the runsheet"""
     conda:
-        "envs/R_visualizations.yaml"
+        "visualizations/R_visualizations.yaml"
     input:
         runsheet = config["runsheet"],
         sample_info = config["sample_info_file"],

Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/workflow_code/visualizations/Illumina-R-visualizations.R

@@ -13,34 +13,18 @@ library(grid)
 ## R visualization script for Illumina paired-end amplicon data                 ##
 ##################################################################################
 # This script is automatically executed as part of the Snakemake workflow when the run_workflow.py --visualizations TRUE argument is used.
-# This script can also be manually executed using processed data from the workflow by using the 'Manual Configuration' section below.
+# This script can also be manually executed using processed data from the workflow 
 
-####### Manual Configuration ########
-# To run the script manually:
-# 1. Uncomment and populate lines 23-30
-# 2. Comment out the Snakemake configuration section (lines 35-42).
-
-# runsheet_file <- "/path/to/SW_AmpIllumina-B/runsheet.csv"
-# sample_info <- "/path/to/SW_AmpIllumina-B/unique-sample-IDs.txt"
-# counts <- "/path/to/SW_AmpIllumina-B/workflow_output/Final_Outputs/counts_GLAmpSeq.tsv"
-# taxonomy <- "/path/to/SW_AmpIllumina-B/workflow_output/Final_Outputs/taxonomy_GLAmpSeq.tsv"
-# final_outputs_dir <- "/path/to/SW_AmpIllumina-B/workflow_output/Final_Outputs/" # Where visualization script outputs will be saved to
-
-# assay_suffix <- "_GLAmpSeq" # Suffix appended to the end of output file names (Default: "_GLAmpSeq")
-# output_prefix <- "" # Prefix appended to the start of output file names (Default: "")
-#####################################
-
-###### Snakemake Configuration ######
-# Assigns arguments to variables based on the snakemake run command 
+# Store command line args as variables #
 args <- commandArgs(trailingOnly = TRUE)
 runsheet_file <- paste0(args[1])
 sample_info <- paste0(args[2])
 counts <- paste0(args[3])
 taxonomy <- paste0(args[4])
 assay_suffix <- paste(args[5])
-final_outputs_dir <- paste0(args[6])
+plots_dir <- paste0(args[6])
 output_prefix <- paste0(args[7])
-#####################################
+########################################
 
 RColorBrewer_Palette <- "Set1"
 
@@ -106,16 +90,16 @@ g_legend <- function(a.gplot){
 ###########################################
 
 # Assign the directory paths to variables
-beta_diversity_out_dir <- paste0(final_outputs_dir, "beta_diversity", .Platform$file.sep)
-alpha_diversity_out_dir <- paste0(final_outputs_dir, "alpha_diversity", .Platform$file.sep)
-taxonomy_out_dir <- paste0(final_outputs_dir, "taxonomy", .Platform$file.sep)
-de_out_dir <- paste0(final_outputs_dir, "da", .Platform$file.sep)
+beta_diversity_out_dir <- paste0(plots_dir, "beta_diversity", .Platform$file.sep)
+alpha_diversity_out_dir <- paste0(plots_dir, "alpha_diversity", .Platform$file.sep)
+taxonomy_out_dir <- paste0(plots_dir, "taxonomy", .Platform$file.sep)
+de_out_dir <- paste0(plots_dir, "da", .Platform$file.sep)
 
 abundance_out_dir <- paste0(de_out_dir, "differential_abundance", .Platform$file.sep)
 volcano_out_dir <- paste0(de_out_dir, "volcano", .Platform$file.sep)
 
 # List of all directory variables
-out_dirs <- list(final_outputs_dir, beta_diversity_out_dir, alpha_diversity_out_dir, taxonomy_out_dir, de_out_dir, abundance_out_dir, volcano_out_dir)
+out_dirs <- list(plots_dir, beta_diversity_out_dir, alpha_diversity_out_dir, taxonomy_out_dir, de_out_dir, abundance_out_dir, volcano_out_dir)
 
 # Loop through each directory path to check and create if necessary
 for (dir_path in out_dirs) {
@@ -471,7 +455,7 @@ ggsave(filename = paste0(alpha_diversity_out_dir, output_prefix, "richness_and_d
 legend <- g_legend(ordination_plot)
 grid.newpage()
 grid.draw(legend)
-legend_filename <- paste0(final_outputs_dir, output_prefix, "color_legend_", assay_suffix, ".png")
+legend_filename <- paste0(plots_dir, output_prefix, "color_legend_", assay_suffix, ".png")
 increment <- ifelse(length(unique(sample_info_tab$groups)) > 9, ceiling((length(unique(sample_info_tab$groups)) - 9) / 3), 0)
 legend_height <- 3 + increment
 ggsave(legend_filename, plot = legend, device = "png", width = 11.1, height = legend_height, dpi = 300)

Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/workflow_code/visualizations/README.md

@@ -21,49 +21,39 @@ ___
 
 ### 1. Set up the execution environment
 
-To ensure that manual execution outputs that are consistent with those of the Snakemake workflow, the script should be executed from a Conda environment created using the [R_visualizations.yaml](/Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/workflow_code/envs/R_visualizations.yaml/) environment file.
+The script should be executed from a Conda environment created using the [R_visualizations.yaml](/Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/workflow_code/visualizations/R_visualizations.yaml) environment file.
 
 <br>
 
 ___
 
 ### 2. Run the visualization script manually  
 
-To manually execute the script, the following variables: `runsheet_file`, `sample_info`, `counts`, `taxonomy`, `final_outputs_dir`, `assay_suffix`, and `output_prefix`, must be explicitly assigned with appropriate values. For manual execution, the lines within the Snakemake Configuration section should be commented out or removed. These lines are used for capturing variables during execution as part of the Snakemake workflow.
+To run the script, the variables `runsheet_file`, `sample_info`, `counts`, `taxonomy`, `assay_suffix`, `plots_dir`, and `output_prefix` must be specified. The script can be manually executed via the command line by providing  positional arguments.
 
-Additionally, the `RColorBrewer_Palette` variable can be modified.  This variable determines the color palette from the RColorBrewer package that is applied to the plots.
+Additionally, the `RColorBrewer_Palette` variable can be modified in the script.  This variable determines the color palette from the RColorBrewer package that is applied to the plots.
 
 ```R
-####### Manual Configuration ########
-# To run the script manually:
-# 1. Uncomment and populate lines 23-30
-# 2. Comment out the Snakemake configuration section (lines 35-42).
-
-# runsheet_file <- "/path/to/SW_AmpIllumina-B/runsheet.csv"
-# sample_info <- "/path/to/SW_AmpIllumina-B/unique-sample-IDs.txt"
-# counts <- "/path/to/SW_AmpIllumina-B/workflow_output/Final_Outputs/counts_GLAmpSeq.tsv"
-# taxonomy <- "/path/to/SW_AmpIllumina-B/workflow_output/Final_Outputs/taxonomy_GLAmpSeq.tsv"
-# final_outputs_dir <- "/path/to/SW_AmpIllumina-B/workflow_output/Final_Outputs/" # Where visualization script outputs will be saved to
-
-# assay_suffix <- "_GLAmpSeq" # Suffix appended to the end of output file names (Default: "_GLAmpSeq")
-# output_prefix <- "" # Prefix appended to the start of output file names (Default: "")
-#####################################
-
-###### Snakemake Configuration ######
-# Assigns arguments to variables based on the snakemake run command 
+# Store command line args as variables #
 args <- commandArgs(trailingOnly = TRUE)
 runsheet_file <- paste0(args[1])
 sample_info <- paste0(args[2])
 counts <- paste0(args[3])
 taxonomy <- paste0(args[4])
 assay_suffix <- paste(args[5])
-final_outputs_dir <- paste0(args[6])
+plots_dir <- paste0(args[6])
 output_prefix <- paste0(args[7])
-#####################################
+########################################
 
 RColorBrewer_Palette <- "Set1"
 
 ```
+
+Example run command: 
+```bash
+Rscript /path/to/visualizations/Illumina-R-visualizations.R "{runsheet_file}" "{sample_info}" "{counts}" "{taxonomy}" "{assay_suffix}" "{plots_dir}" "{output_prefix}"
+```
+
 <br>
 
 ___
@@ -75,7 +65,7 @@ ___
 * `sample_info` – specifies the text file containing the IDs of each sample used, required for running the SW_AmpIllumina workflow (output from [run_workflow.py](/Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/README.md#5-additional-output-files))
 * `counts` – specifies the ASV counts table (output from [GL-DPPD-7104-B step 5g](/Amplicon/Illumina/Pipeline_GL-DPPD-7104_Versions/GL-DPPD-7104-B.md#5g-generating-and-writing-standard-outputs))
 * `taxonomy` – specifies the taxonomy table (output from [GL-DPPD-7104-B step 5g](/Amplicon/Illumina/Pipeline_GL-DPPD-7104_Versions/GL-DPPD-7104-B.md#5g-generating-and-writing-standard-outputs))
-* `final_outputs_dir` – specifies the path where output files will be saved
+* `plots_dir` – specifies the path where output files will be saved
 * `assay_suffix` – specifies a string that is prepended to the start of the output file names. Default: ""
 * `output_prefix` – specifies a string that is appended to the end of the output file names. Default: "_GLAmpSeq"
 * `RColorBrewer_Palette` – specifies the RColorBrewer palette that will be used for coloring in the plots. Options include "Set1", "Accent", "Dark2", "Paired", "Pastel1", "Pastel2", "Set2", and "Set3". Default: "Set1"