Merge pull request #21 from infinity-a11y/version_1.5.0

Merge Version 1.5.0 into Master

PhyloTrace.yml

@@ -7,6 +7,7 @@ dependencies:
   - r-base=4.3.2
   - r-remotes=2.5.0
   - kma=1.4.14
+  - ncbi-amrfinderplus=3.12.8
   - parallel=20240522
   - pblat=2.5.1
   - r-bh=1.81.0-1
@@ -92,7 +93,7 @@ dependencies:
   - r-jquerylib=0.1.4
   - r-jsonlite=1.8.8
   - r-kableExtra=1.3.4
-  - r-knitr=1.47
+  - r-knitr=1.48
   - r-labeling=0.4.3
   - r-later=1.3.1
   - r-lattice=0.22_5
@@ -159,7 +160,7 @@ dependencies:
   - r-tidytree=0.4.5
   - r-tidyverse=2.0.0
   - r-timechange=0.2.0
-  - r-tinytex=0.51
+  - r-tinytex=0.52
   - r-tzdb=0.4.0
   - r-utf8=1.2.3
   - r-uuid=1.1_1
@@ -169,9 +170,9 @@ dependencies:
   - r-vroom=1.6.4
   - r-webshot=0.5.5
   - r-withr=2.5.1
-  - r-xfun=0.45
+  - r-xfun=0.46
   - r-xml2=1.3.5
   - r-xtable=1.8_4
-  - r-yaml=2.3.8
+  - r-yaml=2.3.10
   - r-yulab.utils=0.1.0
   - r-zoo=1.8_12

README.md

@@ -25,7 +25,7 @@ development. To get a stable version download the newest release.
 ![PartnerLogos](www/partners_logo_round.svg)
 
 <sup><sup> Developed in collaboration with Hochschule Furtwangen University (HFU) and Medical
-University of Graz (MUG). Featured on ShinyConf 2024. </sup> </sup>
+University of Graz (MUG). Featured on ShinyConf 2024 and R/Medicine 2024. </sup> </sup>
 
 [![DOI](https://img.shields.io/badge/DOI-10.5281%2Fzenodo.10996423-00e896?labelColor=gray&color=2500ba&logoColor=black)](https://doi.org/10.5281/zenodo.10996423)
 [![License: GPL

execute/check_duplicate_multi.R

@@ -1,35 +1,33 @@
 library(logr)
-# Get the command line arguments
-args <- commandArgs(trailingOnly = TRUE)
-
-# Access the first argument
-base_path <- args[1]
-
-# Get selected assembly file names
-file_names <- list.files(paste0(getwd(), "/selected_genomes"), full.names = T)
-
-# Function to log messages 
-log.message <- function(log_file, message) {
-  cat(format(Sys.time(), "%Y-%m-%d %H:%M:%S"), "-", message, "\n", file = log_file, append = TRUE)
-}
 
-logfile <- file.path(paste0(base_path, "/logs/check_duplicate_multi.log"))
-
-log <- log_open(logfile, logdir = FALSE)
-
-log_print("Initiated multi typing fasta name duplicates check")
-
-# 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 <- stringr::str_extract(assemblies[[i]][seq(1, length(assemblies[[i]]), by = 3)], "^[^\\s]+")
+process_fasta <- function(fasta_path) {
+  # Read the FASTA file into a data.table
+  dt <- data.table::fread(fasta_path, header = FALSE, sep = "\n", col.names = "line", data.table = TRUE)
+
+  # Identify headers and sequence lines
+  dt[, is_header := grepl("^>", line)]
+
+  # Create a group identifier for each sequence based on headers
+  dt[, group := cumsum(is_header)]
+
+  # Process each group to concatenate sequences, keeping headers as is
+  result <- dt[, .(header = line[1], 
+                   sequence = paste(line[!is_header], collapse = "")), 
+               by = group]
+
+  # Prepare the final output as a character vector
+  # Ensure exactly one empty line between sequence end and next header
+  output <- unlist(result[, .(output = c(header, sequence, "")), by = group]$output)
+
+  # Remove the last empty line to avoid trailing empty line in the file
+  output <- output[-length(output)]
+
+  names <- stringr::str_extract(output[seq(1, length(output), by = 3)], "^[^\\s]+")
 
   # Test if there are duplicates
   if(length(names) != length(unique(names))){
 
-    log_print(paste0("Duplicate(s) present in ", basename(file_names[i])))
+    log_print(paste0("Duplicate(s) present in ", basename(fasta_path)))
 
     # add a number to the duplicates
     for(j in 1:length(names)){
@@ -41,12 +39,46 @@ for(i in 1:length(assemblies)){
 
     # substitute the respective lines in the file with the new names 
     for(k in 1:length(names)){
-      assemblies[[i]][3*k - 2] <- paste0(names[k])
+      output[3*k - 2] <- paste0(names[k])
     }
 
-    # save the new assembly 
-    writeLines(assemblies[[i]], file_names[i])
-  } 
+    # save formatted fasta
+    writeLines(output, fasta_path) 
+
+    # Return invisible NULL to suppress output
+    invisible(NULL)
+
+  } else {
+
+    # save formatted fasta
+    writeLines(output, fasta_path) 
+
+    # Return invisible NULL to suppress output
+    invisible(NULL)
+  }
 }
 
+# Get the command line arguments
+args <- commandArgs(trailingOnly = TRUE)
+
+# Access the first argument
+base_path <- args[1]
+
+# Get selected assembly file names
+assemblies <- list.files(paste0(getwd(), "/selected_genomes"), full.names = T)
+
+# Function to log messages 
+log.message <- function(log_file, message) {
+  cat(format(Sys.time(), "%Y-%m-%d %H:%M:%S"), "-", message, "\n", file = log_file, append = TRUE)
+}
+
+logfile <- file.path(paste0(base_path, "/logs/check_duplicate_multi.log"))
+
+log <- log_open(logfile, logdir = FALSE)
+
+log_print("Initiated multi typing fasta check and formatting")
+
+# Check and format fasta of assemblies
+invisible(lapply(assemblies, process_fasta))
+
 log_close()

execute/check_duplicate_single.R

@@ -1,4 +1,63 @@
 library(logr)
+
+process_fasta <- function(fasta_path) {
+  # Read the FASTA file into a data.table
+  dt <- data.table::fread(fasta_path, header = FALSE, sep = "\n", col.names = "line", data.table = TRUE)
+
+  # Identify headers and sequence lines
+  dt[, is_header := grepl("^>", line)]
+
+  # Create a group identifier for each sequence based on headers
+  dt[, group := cumsum(is_header)]
+
+  # Process each group to concatenate sequences, keeping headers as is
+  result <- dt[, .(header = line[1], 
+                   sequence = paste(line[!is_header], collapse = "")), 
+               by = group]
+
+  # Prepare the final output as a character vector
+  # Ensure exactly one empty line between sequence end and next header
+  output <- unlist(result[, .(output = c(header, sequence, "")), by = group]$output)
+
+  # Remove the last empty line to avoid trailing empty line in the file
+  output <- output[-length(output)]
+
+  names <- stringr::str_extract(output[seq(1, length(output), by = 3)], "^[^\\s]+")
+
+  # Test if there are duplicates
+  if(length(names) != length(unique(names))){
+
+    log_print(paste0("Duplicate(s) present in ", basename(fasta_path)))
+
+    # add a number to the duplicates
+    for(j in 1:length(names)){
+      if(sum(names == names[j]) > 1){
+        indices <- which(names == names[j])
+        names[j] <- paste0(names[j], "_", which(names == names[j]))
+      }
+    }
+
+    # substitute the respective lines in the file with the new names 
+    for(k in 1:length(names)){
+      output[3*k - 2] <- paste0(names[k])
+    }
+
+    # save formatted fasta
+    writeLines(output, paste0(getwd(), "/blat_single/", basename(fasta_path))) 
+
+    # Return invisible NULL to suppress output
+    invisible(NULL)
+
+  } else {
+
+    # save formatted fasta
+    writeLines(output, paste0(getwd(), "/blat_single/", basename(fasta_path)))
+
+    # Return invisible NULL to suppress output
+    invisible(NULL)
+  }
+}
+
 typing_meta <- readRDS(paste0(getwd(), "/single_typing_df.rds"))
 
 # Function to log messages 
@@ -14,32 +73,7 @@ log_print("Initiated single typing fasta name duplicates check")
 
 assembly <- typing_meta$genome
 
-lines <- readLines(assembly)
-
-names <- stringr::str_extract(lines[seq(1, length(lines), by = 3)], "^[^\\s]+")
-
-# Test if there are duplicates
-if(length(names) != length(unique(names))) {
-
-  log_print(paste0("Duplicate(s) present in ", basename(assembly)))
-
-  # add a number to the duplicates
-  for(i in 1:length(names)) {
-    if(sum(names == names[i]) > 1) {
-      indices <- which(names == names[i])
-      names[i] <- paste0(names[i], "_", indices[which(indices == i)])
-    }
-  }
-
-  # substitute the respective lines in the file with the new names 
-  for(i in 1:length(names)) {
-    lines[3*i - 2] <- paste0(names[i])
-  }
-
-  # save the new assembly to working directory
-  writeLines(lines, paste0(getwd(), "/blat_single/assembly.fasta"))
-} else {
-  writeLines(lines, paste0(getwd(), "/blat_single/assembly.fasta"))
-}
+# Check and format fasta of assemblies
+invisible(lapply(assembly, process_fasta))
 
 log_close()

execute/kill_multi.sh

@@ -33,4 +33,4 @@ else
   kill "$PID"
 fi
 
-echo 0 > $log_file
+echo 0 > $log_file