Fix pre commit linting

.pre-commit-config.yaml

@@ -4,10 +4,24 @@ repos:
     hooks:
       - id: prettier
         additional_dependencies:
-          - prettier@3.2.5
-
-  - repo: https://github.com/editorconfig-checker/editorconfig-checker.python
-    rev: "3.0.3"
+          - prettier@3.6.2
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
     hooks:
-      - id: editorconfig-checker
-        alias: ec
+      - id: trailing-whitespace
+        args: [--markdown-linebreak-ext=md]
+        exclude: |
+          (?x)^(
+              .*ro-crate-metadata.json$|
+              modules/nf-core/.*|
+              subworkflows/nf-core/.*|
+              .*\.snap$
+          )$
+      - id: end-of-file-fixer
+        exclude: |
+          (?x)^(
+              .*ro-crate-metadata.json$|
+              modules/nf-core/.*|
+              subworkflows/nf-core/.*|
+              .*\.snap$
+          )$

.prettierignore

@@ -10,4 +10,7 @@ testing/
 testing*
 *.pyc
 bin/
+.nf-test/
 ro-crate-metadata.json
+modules/nf-core/
+subworkflows/nf-core/

.prettierrc.yml

@@ -1 +1,6 @@
 printWidth: 120
+tabWidth: 4
+overrides:
+  - files: "*.{md,yml,yaml,html,css,scss,js,cff}"
+    options:
+      tabWidth: 2

docs/output.md

@@ -75,7 +75,6 @@ This directory is created during the second series of steps of the pipeline, fea
 <summary>Output files</summary>
 
 - `library_QC/`
-
   - `counts_heatmap.pdf`: a complete heatmap of absolute mutant counts, stratified by mutant amino acid (Y-axis) per position (X-axis)
     ![Count heatmap](images/library_QC_counts_heatmap.png)
 
@@ -104,7 +103,6 @@ This directory is created during the final series of steps of the pipeline, feat
 <summary>Output files</summary>
 
 - `fitness/`
-
   - `counts_merged.tsv`: summarised gene variant counts across all input and output samples
   - `default_results/fitness_estimation_count_correlation.pdf`: pair-wise replicate variant count scatterplots and correlations between all specified samples
     ![Variant count correlation(s)](images/fitness_estimation_count_correlation.png)

modules/local/dmsanalysis/templates/aa_seq.R

@@ -63,4 +63,3 @@ writeLines(
   f
 )
 close(f)
-

modules/local/dmsanalysis/templates/possible_mutations.R

@@ -2,14 +2,14 @@
 
 # ------------------------------------------------------------------------------
 # Script: Generate Programmed Codon Variants
-# Description: Generates all possible programmed codon mutations for a given 
+# Description: Generates all possible programmed codon mutations for a given
 #              wild-type sequence based on a specified mutagenesis strategy.
-# Input: 
+# Input:
 #   - wt_seq_input: Wild-type sequence (string or path to FASTA file).
 #   - start_stop_pos: Target sequence range format "start-stop".
 #   - mutagenesis_type: Strategy ('nnk', 'nns', 'nnh', 'nnn', 'nnk_nns', 'nnk_nns_nnh', 'custom').
-#   - custom_codon_library_path: Path to custom library. Automatically detects 
-#     if the file is a global list ("AAA, AAC...") or a position-wise CSV 
+#   - custom_codon_library_path: Path to custom library. Automatically detects
+#     if the file is a global list ("AAA, AAC...") or a position-wise CSV
 #     (requires a "Position" header).
 #   - output_file: Desired name/path for the output CSV.
 # Output: A CSV file containing all possible mutated codons per position.
@@ -20,24 +20,24 @@ suppressMessages(library(methods))
 
 generate_possible_variants <- function(wt_seq_input, start_stop_pos, mutagenesis_type,
                                        custom_codon_library_path, output_file) {
-  
+
   # Parse the start and stop positions from the input format "start-stop"
   positions <- unlist(strsplit(start_stop_pos, "-"))
   start_pos <- as.numeric(positions[1])
   stop_pos <- as.numeric(positions[2])
-  
+
   # Load sequence from file or process as a direct string
   if (file.exists(wt_seq_input)) {
     seq_data <- Biostrings::readDNAStringSet(filepath = wt_seq_input)
     wt_seq <- seq_data[[1]]
   } else {
     wt_seq <- Biostrings::DNAString(wt_seq_input)
   }
-  
+
   # Extract the target coding sequence
   coding_seq <- Biostrings::subseq(wt_seq, start = start_pos, end = stop_pos)
   coding_seq <- as.character(coding_seq)
-  
+
   # Predefined codon dictionaries
   nnk_codons <- c('AAG', 'AAT', 'ATG', 'ATT', 'AGG', 'AGT', 'ACG', 'ACT', 'TAG', 'TAT', 'TTG', 'TTT', 'TGG', 'TGT', 'TCG', 'TCT', 'GAG', 'GAT', 'GTG', 'GTT', 'GGG', 'GGT', 'GCG', 'GCT', 'CAG', 'CAT', 'CTG', 'CTT', 'CGG', 'CGT', 'CCG', 'CCT')
   nns_codons <- c('AAG', 'AAC', 'ATG', 'ATC', 'AGG', 'AGC', 'ACG', 'ACC', 'TAG', 'TAC', 'TTG', 'TTC', 'TGG', 'TGC', 'TCG', 'TCC', 'GAG', 'GAC', 'GTG', 'GTC', 'GGG', 'GGC', 'GCG', 'GCC', 'CAG', 'CAC', 'CTG', 'CTC', 'CGG', 'CGC', 'CCG', 'CCC')
@@ -50,37 +50,37 @@ generate_possible_variants <- function(wt_seq_input, start_stop_pos, mutagenesis
   is_position_wise <- FALSE
   position_lookup <- list()
   custom_codons <- NULL
-  
+
   if (mutagenesis_type == "custom") {
     if (!file.exists(custom_codon_library_path) || is.null(custom_codon_library_path)) {
       stop("Custom codons file must be provided and valid when using 'custom' mutagenesis_type.")
     }
-    
+
     # Auto-detect format by inspecting the first line
     first_line <- readLines(custom_codon_library_path, n = 1)
-    
+
     if (grepl("Position", first_line, ignore.case = TRUE)) {
       # Format 1: Position-wise CSV file
       is_position_wise <- TRUE
-      
+
       # Read line-by-line instead of read.csv to avoid strict column matching errors
       lines <- readLines(custom_codon_library_path)
-      
+
       # Loop through lines, skipping the header (index 1)
       for (line in lines[-1]) {
         # Skip empty lines
-        if (trimws(line) == "") next 
-        
+        if (trimws(line) == "") next
+
         # Split the line by commas
         parts <- trimws(unlist(strsplit(line, ",")))
-        
+
         # The first part is the position, everything else are the codons
         pos_idx <- parts[1]
         codon_vec <- parts[-1]
-        
+
         # Remove any accidental empty strings (e.g., from trailing commas)
         codon_vec <- codon_vec[codon_vec != ""]
-        
+
         position_lookup[[pos_idx]] <- codon_vec
       }
     } else {
@@ -89,19 +89,19 @@ generate_possible_variants <- function(wt_seq_input, start_stop_pos, mutagenesis
       custom_codons <- trimws(custom_codons)
     }
   }
-  
+
   # Helper function to split a DNA sequence into nucleotide triplets
   split_into_codons <- function(seq) {
     # Note: Double escaping is required for Perl regular expressions here
     return(strsplit(seq, "(?<=.{3})", perl = TRUE)[[1]])
   }
-  
+
   wt_codons <- split_into_codons(coding_seq)
-  
+
   # Initialize dataframe to store final variant results
   # Note: \$ escaping is maintained for Nextflow compatibility
   result <- data.frame(Codon_Number = integer(), wt_codon = character(), Variant = character(), stringsAsFactors = FALSE)
-  
+
   # Helper function to determine the target codon list per position
   get_codon_list <- function(wt_codon, codon_index) {
     if (mutagenesis_type == "nnk") {
@@ -137,32 +137,32 @@ generate_possible_variants <- function(wt_seq_input, start_stop_pos, mutagenesis
       stop("Invalid mutagenesis_type. Choose from 'nnk', 'nns', 'nnh', 'nnn', 'nnk_nns', 'nnk_nns_nnh', or 'custom'.")
     }
   }
-  
+
   # Iterate over each wild-type codon to assign programmed variants
   for (i in seq_along(wt_codons)) {
     wt_codon <- wt_codons[i]
     codon_list <- get_codon_list(wt_codon, i)
-    
+
     # Skip iteration if no custom codons were assigned to this specific position
-    if (is.null(codon_list)) next 
-    
+    if (is.null(codon_list)) next
+
     # Filter out the wild-type codon from the mutation list
     possible_variants <- codon_list[codon_list != wt_codon]
-    
+
     for (variant in possible_variants) {
       # Note: \$ escaping is maintained for Nextflow compatibility
       result <- rbind(result, data.frame(Codon_Number = i, wt_codon = wt_codon, Variant = variant, stringsAsFactors = FALSE))
     }
   }
-  
+
   write.csv(result, output_file, row.names = FALSE)
 }
 
 # ------------------------------------------------------------------------------
 # Main Execution Block (Nextflow variable substitution)
 # ------------------------------------------------------------------------------
 
-# Replaces bash if/else logic. If Nextflow omits the optional file, 
+# Replaces bash if/else logic. If Nextflow omits the optional file,
 # it passes "/NULL", which R translates to an actual NULL object.
 custom_lib_arg <- if ("$custom_codon_library" == "/NULL") {
   NULL

modules/local/dmsanalysis/templates/process_gatk.R

@@ -362,4 +362,3 @@ writeLines(
   f
 )
 close(f)
-

modules/local/fitness/fitness_experimental_design.nf

@@ -16,4 +16,4 @@ process EXPDESIGN_FITNESS {
 
   script:
   template 'dimsum_experimentalDesign.R'
-}
+}

modules/local/fitness/templates/dimsum_experimentalDesign.R

@@ -11,14 +11,14 @@ make_dimsum_experimental_design <- function(samplesheet_csv, out_path = "experim
 
   # tolerate missing file2 column (single-end)
   if (!"file2" %in% names(ss)) ss\$file2 <- ""
-  
+
   required <- c("sample", "type", "replicate", "file1", "file2")
   missing  <- setdiff(required, names(ss))
   if (length(missing) > 0) stop("Samplesheet missing columns: ", paste(missing, collapse = ", "))
 
   # coerce types
   ss\$replicate <- as.integer(ss\$replicate)
-  
+
   # ---- derive sample_name strategy ----
   # If only one biological sample present (e.g. one protein), use "input1", "output2", ...
   # If multiple biological samples present, prefix with 'sample' to avoid collisions:
@@ -38,11 +38,11 @@ make_dimsum_experimental_design <- function(samplesheet_csv, out_path = "experim
   selection_replicate <- ifelse(ss\$type == "output", 1L, NA_integer_)
   # assume one technical batch
   technical_replicate <- rep(1L, nrow(ss))
-  
+
   pair1 <- basename(ss\$file1)
   # keep empty string for single-end / missing file2
   pair2 <- ifelse(is.na(ss\$file2) | ss\$file2 == "", "", basename(ss\$file2))
-  
+
   ed <- data.frame(
     sample_name          = sample_name,
     experiment_replicate = experiment_replicate,
@@ -93,4 +93,3 @@ writeLines(
   f
 )
 close(f)
-

modules/local/fitness/templates/find_syn_mutation.R

@@ -38,7 +38,7 @@ pick_synonymous_wt_from_range <- function(wt_fasta, counts_merged_tsv, pos_range
   df <- utils::read.delim(counts_merged_tsv, sep = "\\t", header = TRUE,
                           stringsAsFactors = FALSE, check.names = FALSE)
   if (!"nt_seq" %in% names(df)) stop("counts_merged_tsv must have a 'nt_seq' column.")
-  
+
   df\$nt_seq <- toupper(df\$nt_seq)
   keep_len <- nchar(df\$nt_seq) == wt_len
   if (!any(keep_len)) stop("No sequences match WT window length (", wt_len, ").")