Merge pull request #14 from infinity-a11y/version_1.3.1

Version 1.4.0 Pull Request

PhyloTrace.yml

@@ -5,7 +5,9 @@ channels:
   - defaults
 dependencies:
   - r-base=4.3.2
+  - r-remotes=2.5.0
   - kma=1.4.14
+  - parallel=20240522
   - pblat=2.5.1
   - r-bh=1.81.0-1
   - r-biocmanager=1.30.22
@@ -33,11 +35,12 @@ dependencies:
   - r-bit64=4.0.5
   - r-blob=1.2.4
   - r-broom=1.0.5
-  - r-bslib=0.5.1
-  - r-cachem=1.0.8
+  - r-bslib=0.7.0
+  - r-bsicons=0.1.1
+  - r-cachem=1.1.0
   - r-callr=3.7.3
   - r-cellranger=1.1.0
-  - r-cli=3.6.1
+  - r-cli=3.6.2
   - r-clipr=0.8.0
   - r-coda=0.19_4
   - r-colorspace=2.1_0
@@ -49,19 +52,19 @@ dependencies:
   - r-dashboardthemes=1.1.6
   - r-data.table=1.14.8
   - r-dbplyr=2.3.4
-  - r-digest=0.6.33
+  - r-digest=0.6.35
   - r-downloader=0.4
   - r-dplyr=1.1.4
   - r-dtplyr=1.3.1
   - r-ellipsis=0.3.2
-  - r-evaluate=0.22
+  - r-evaluate=0.24
   - r-fansi=1.0.5
   - r-farver=2.1.1
-  - r-fastmap=1.1.1
+  - r-fastmap=1.2.0
   - r-fastmatch=1.1_4
   - r-fontawesome=0.5.2
   - r-forcats=1.0.0
-  - r-fs=1.6.3
+  - r-fs=1.6.4
   - r-gargle=1.5.2
   - r-generics=0.1.3
   - r-ggfun=0.1.3
@@ -70,30 +73,30 @@ dependencies:
   - r-ggplot2=3.4.4
   - r-ggplotify=0.1.2
   - r-ggrepel=0.9.4
-  - r-glue=1.6.2
+  - r-glue=1.7.0
   - r-googledrive=2.1.1
   - r-googlesheets4=1.1.1
   - r-gridGraphics=0.5_1
   - r-gtable=0.3.4
   - r-haven=2.5.3
-  - r-highr=0.10
+  - r-highr=0.11
   - r-hms=1.1.3
-  - r-htmltools=0.5.6.1
-  - r-htmlwidgets=1.6.2
+  - r-htmltools=0.5.8.1
+  - r-htmlwidgets=1.6.4
   - r-httpuv=1.6.11
   - r-httr=1.4.7
   - r-ids=1.0.1
   - r-igraph=1.5.1
   - r-isoband=0.2.7
   - r-jquerylib=0.1.4
-  - r-jsonlite=1.8.7
+  - r-jsonlite=1.8.8
   - r-kableExtra=1.3.4
-  - r-knitr=1.44
+  - r-knitr=1.47
   - r-labeling=0.4.3
   - r-later=1.3.1
   - r-lattice=0.22_5
   - r-lazyeval=0.2.2
-  - r-lifecycle=1.0.3
+  - r-lifecycle=1.0.4
   - r-lubridate=1.9.3
   - r-magrittr=2.0.3
   - r-memoise=2.0.1
@@ -126,11 +129,11 @@ dependencies:
   - r-rematch2=2.1.2
   - r-reprex=2.0.2
   - r-rhandsontable=0.3.8
-  - r-rlang=1.1.1
-  - r-rmarkdown=2.25
+  - r-rlang=1.1.4
+  - r-rmarkdown=2.27
   - r-rstudioapi=0.15.0
   - r-rvest=1.0.3
-  - r-sass=0.4.7
+  - r-sass=0.4.9
   - r-scales=1.2.1
   - r-selectr=0.4_2
   - r-shiny=1.7.5
@@ -153,20 +156,19 @@ dependencies:
   - r-tidytree=0.4.5
   - r-tidyverse=2.0.0
   - r-timechange=0.2.0
-  - r-tinytex=0.48
+  - r-tinytex=0.51
   - r-tzdb=0.4.0
   - r-utf8=1.2.3
   - r-uuid=1.1_1
   - r-vctrs=0.6.4
   - r-viridis=0.6.5
   - r-viridisLite=0.4.2
-  - r-visNetwork=2.1.2
   - r-vroom=1.6.4
   - r-webshot=0.5.5
   - r-withr=2.5.1
-  - r-xfun=0.40
+  - r-xfun=0.45
   - r-xml2=1.3.5
   - r-xtable=1.8_4
-  - r-yaml=2.3.7
+  - r-yaml=2.3.8
   - r-yulab.utils=0.1.0
   - r-zoo=1.8_12

README.md

@@ -139,10 +139,11 @@ bash install_phylotrace.sh
 
 ### 2.4 Uninstall
 To uninstall PhyloTrace from your system, remove the application directory and run the following command to remove the
-desktop launcher:
+desktop launcher and the PhyloTrace conda environment:
 ```bash
 rm $HOME/.local/share/applications/PhyloTrace.desktop
 rm $HOME/.local/share/icons/hicolor/scalable/apps/PhyloTrace.png
+conda remove -n PhyloTrace --all -y
 ```
 
 ### 2.5 Troubleshooting

execute/automatic_typing.R

@@ -1,7 +1,8 @@
 meta_info <- readRDS("meta_info.rds")
 db_path <- readRDS("multi_typing_df.rds")[, "db_path"]
 assembly_folder <- dir(paste0(getwd(), "/selected_genomes"), full.names = TRUE)
-assembly <- assembly_folder[grep(tail(dir(paste0(getwd(), "/kma_multi/results")), n = 1), assembly_folder)]
+assembly <- assembly_folder[which(commandArgs(trailingOnly = TRUE)[1] == basename(assembly_folder))]
+results_folder <- dir(paste0(meta_info$db_directory, "/execute/blat_multi/results"), full.names = TRUE)
 
 source("variant_validation.R")
 
@@ -20,6 +21,11 @@ column_classes <- function(df) {
   })
 }
 
+# Function to log messages to the file
+log_message <- function(log_file, message) {
+  cat(format(Sys.time(), "%Y-%m-%d %H:%M:%S"), "-", message, "\n", file = log_file, append = TRUE)
+}
+
 # Define start and stop codons
 start_codons <- c("ATG", "GTG", "TTG")
 stop_codons <- c("TAA", "TAG", "TGA")
@@ -31,7 +37,7 @@ allele_folder <- list.files(paste0(db_path, "/", gsub(" ", "_", meta_info$cgmlst
 template <- readLines(assembly)
 
 # List all .psl result files from alignment with BLAT
-psl_files <- list.files(tail(dir(paste0(meta_info$db_directory, "/execute/kma_multi/results"), full.names = TRUE), n = 1), pattern = "\\.psl$", full.names = TRUE)
+psl_files <- list.files(results_folder[which(sub("\\.(fasta|fna|fa)$", "", basename(assembly)) == basename(results_folder))], pattern = "\\.psl$", full.names = TRUE)
 
 # Initialize an empty vector to store the results
 allele_vector <- integer(length(psl_files))
@@ -299,54 +305,14 @@ if(sum(unname(base::sapply(psl_files, file.size)) <= 427) / length(psl_files) <=
   # Save new Entry in Typing Database
   saveRDS(Database, paste0(db_path, "/", gsub(" ", "_", meta_info$cgmlst_typing), "/Typing.rds"))
 
-  multi_user_fb <- paste0(
-    "#!/bin/bash\n",
-    'log_file=', shQuote(paste0(getwd(), "/execute/script_log.txt")), '\n',
-    '# Function to log messages to the file', '\n',
-    'log_message() {', '\n',
-    '    echo "$(date +"%Y-%m-%d %H:%M:%S") - $1" >> "$log_file"', '\n',
-    '}', '\n',
-    'log_message "Successful typing of "', shQuote(sub("\\.(fasta|fna|fa)$", "", basename(assembly)))
-  )
-
-  # Specify the path to save the script
-  multi_user_fb_path <- paste0(getwd(), "/execute/multi_user_fb.sh")
-
-  # Write the script to a file
-  cat(multi_user_fb, file = multi_user_fb_path)
-
-  # Make the script executable
-  system(paste("chmod +x", multi_user_fb_path))
-
-  # Execute the script
-  system(paste(multi_user_fb_path), wait = FALSE)
+  # Logging successes
+  log_message(log_file = paste0(getwd(), "/execute/script_log.txt"), 
+              message = paste0("Successful typing of ", sub("\\.(fasta|fna|fa)$", "", basename(assembly))))
 
 } else {
 
-  failures <- sum(unname(base::sapply(psl_files, file.size)) <= 427) / length(psl_files) * 100
-
-  multi_user_fb <- paste0(
-    "#!/bin/bash\n",
-    'log_file=', shQuote(paste0(getwd(), "/execute/script_log.txt")), '\n',
-    '# Function to log messages to the file', '\n',
-    'log_message() {', '\n',
-    '    echo "$(date +"%Y-%m-%d %H:%M:%S") - $1" >> "$log_file"', '\n',
-    '}', '\n',
-    'log_message ', shQuote(paste0("Assembly typing failed for ", sub("\\.(fasta|fna|fa)$", "", basename(assembly)))), '\n',
-    shQuote(paste0(failures, "% of loci not typed."))
-  )
-
-  # Specify the path to save the script
-  multi_user_fb_path <- paste0(getwd(), "/execute/multi_user_fb.sh")
-
-  # Write the script to a file
-  cat(multi_user_fb, file = multi_user_fb_path)
-
-  # Make the script executable
-  system(paste("chmod +x", multi_user_fb_path))
-
-  # Execute the script
-  system(paste(multi_user_fb_path), wait = FALSE)
+  # Logging failures
+  log_message(log_file = paste0(getwd(), "/execute/script_log.txt"), 
+              message = paste0("Assembly typing failed for ", 
+                               sub("\\.(fasta|fna|fa)$", "", basename(assembly))))
 }
-
-

execute/kma_multi.sh → execute/blat_multi.sh

@@ -12,16 +12,17 @@ genome_folder=$(Rscript -e "cat(readRDS('multi_typing_df.rds')[,'genome_folder']
 genome_names=$(Rscript -e "cat(readRDS('multi_typing_df.rds')[,'genome_names'])")
 alleles=$(Rscript -e "cat(readRDS('multi_typing_df.rds')[,'alleles'])")
 
-# Directory name
-mkdir $base_path/execute/kma_multi
-results="$base_path/execute/kma_multi/results"
+# Remove the existing multi directory
+if [ -d "$base_path/execute/blat_multi" ]; then
+    rm -r "$base_path/execute/blat_multi"
+fi
+mkdir "$base_path/execute/blat_multi"
 
-# Remove the existing directory (if it exists)
+# Remove the existing results directory
+results="$base_path/execute/blat_multi/results"
 if [ -d "$results" ]; then
     rm -r "$results"
 fi
-
-# Create a new directory
 mkdir "$results"
 
 selected_genomes="$base_path/execute/selected_genomes"
@@ -54,9 +55,9 @@ for file in "${file_names[@]}"; do
 done
 
 #INDEXING GENOME AS DATABASE
-kma_database="$base_path/execute/kma_multi/$scheme"
+blat_database="$base_path/execute/blat_multi/$scheme"
 
-#RUNNING KMA Loop
+#RUNNING blat Loop
 genome_filename_noext=""
 
 #Indexing Loop
@@ -69,21 +70,15 @@ for genome in "$selected_genomes"/*; do
     genome_filename=$(basename "$genome")
     genome_filename_noext="${genome_filename%.*}"
     log_message "Processing $genome_filename"
-    kma index -i "$genome" -o "$kma_database"
     fi
     mkdir "$results/$genome_filename_noext"
-
-    #Running Loop
-    for query_file in "$alleles"/*.{fasta,fa,fna}; do
-        if [ -f "$query_file" ]; then
-        query_filename=$(basename "$query_file")
-        query_filename_noext="${query_filename%.*}"
-        output_file="$results/$genome_filename_noext/$query_filename_noext"
-        #kma -i "$query_file" -o "$output_file" -t_db "$kma_database" -nc -status
-        pblat $genome "$query_file" "$output_file.psl"
-        fi
-    done
+
+    result_folder="$results/$genome_filename_noext"
+
+    # Run parallelized BLAT
+    find "$alleles" -type f \( -name "*.fasta" -o -name "*.fa" -o -name "*.fna" \) | parallel pblat $genome {} "$result_folder/{/.}.psl"
+
     log_message "Attaching $genome_filename"
-    Rscript "$base_path/execute/automatic_typing.R"
+    Rscript "$base_path/execute/automatic_typing.R" "$genome_filename"
 done
 log_message "Multi Typing finalized."

execute/blat_run.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+
+cd execute
+source ~/miniconda3/etc/profile.d/conda.sh
+conda activate PhyloTrace
+unset R_HOME
+
+# Set base path
+base_path=$(Rscript -e "cat(readRDS('single_typing_df.rds')[,'wd'])")
+
+# reset progress
+echo 0 > "$base_path/execute/progress.txt"
+
+# Get variables
+scheme=$(Rscript -e "cat(readRDS('single_typing_df.rds')[,'scheme'])")
+alleles=$(Rscript -e "cat(readRDS('single_typing_df.rds')[,'alleles'])")
+
+# Remove the existing directory (if it exists)
+if [ -d "$base_path/execute/blat_single" ]; then
+    rm -r "$base_path/execute/blat_single"
+fi
+
+mkdir "$base_path/execute/blat_single"
+
+# Directory name
+results="$base_path/execute/blat_single/results"
+
+# Remove the existing directory (if it exists)
+if [ -d "$results" ]; then
+    rm -r "$results"
+fi
+
+# Create a new directory
+mkdir "$results"
+
+# Check assembly file and save in the execute folder
+Rscript "$base_path/execute/check_duplicate.R"
+wait
+genome="$base_path/execute/blat_single/assembly.fasta"
+
+# Run parallelized BLAT
+parallel --citation
+find "$alleles" -type f \( -name "*.fasta" -o -name "*.fa" -o -name "*.fna" \) | parallel pblat $genome {} "$results/{/.}.psl"
+
+# Start appending results
+echo 888888 >> "$base_path/execute/progress.txt"
+Rscript "$base_path/execute/single_typing.R"
+
+# Single typing finalized
+echo 999999 >> "$base_path/execute/progress.txt"

execute/check_duplicate.R

@@ -1,12 +1,10 @@
-library(stringr)
-
 typing_meta <- readRDS(paste0(getwd(), "/single_typing_df.rds"))
 
 assembly <- typing_meta$genome
 
 lines <- readLines(assembly)
 
-names <- str_extract(lines[seq(1, length(lines), by = 3)], "^[^\\s]+")
+names <- stringr::str_extract(lines[seq(1, length(lines), by = 3)], "^[^\\s]+")
 
 # Test if there are duplicates
 if(length(names) != length(unique(names))){
@@ -23,7 +21,7 @@ if(length(names) != length(unique(names))){
   }
 
   # save the new assembly to working directory
-  writeLines(lines, paste0(getwd(), "/kma_single/assembly.fasta"))
+  writeLines(lines, paste0(getwd(), "/blat_single/assembly.fasta"))
 } else {
-  writeLines(lines, paste0(getwd(), "/kma_single/assembly.fasta"))
+  writeLines(lines, paste0(getwd(), "/blat_single/assembly.fasta"))
 }

execute/check_duplicate_multi.R

@@ -1,13 +1,11 @@
-library(stringr)
-
 file_names <- list.files(paste0(getwd(), "/selected_genomes"), full.names = T)
 
 # load selected assemblies
 assemblies <- lapply(list.files(paste0(getwd(), "/selected_genomes"), full.names = T), readLines)
 
 # loop through every assembly
 for(i in 1:length(assemblies)){
-  names <- str_extract(assemblies[[i]][seq(1, length(assemblies[[i]]), by = 3)], "^[^\\s]+")
+  names <- stringr::str_extract(assemblies[[i]][seq(1, length(assemblies[[i]]), by = 3)], "^[^\\s]+")
 
   # Test if there are duplicates
   if(length(names) != length(unique(names))){