feat: ONT sample preprocessing

.gitignore

@@ -36,3 +36,4 @@
 !README.md
 !CODE_OF_CONDUCT.md
 !CONTRIBUTING.md
+!barcode-rename.csv

barcode-rename.csv

@@ -0,0 +1 @@
+sample_name,barcode

config/config.yaml

@@ -31,6 +31,11 @@ data-handling:
   # the results from the latest run to
   archive: ../archive/
 
+#path to barcode folders
+barcode_dir: ../barcode_dir/
+#path to store renamed FASTQ files
+output_dir: data/
+
 quality-criteria:
   illumina:
     # minimal length of acceptable reads

docs/installation.md

@@ -82,6 +82,20 @@ The structure can be adjusted via the config file: `config/config.yaml` under
 - **archive**: path to archive data from the results from the analysis to.
   Defaults to `../archive/`.
 
+### ONT sample preprocessing
+Automates the extraction of sequencing reads from sample-specific folders, merges the reads from each
+  barcode into a single FASTQ file, and then renames the files for easy identification and downstream analysis.
+
+- **barcode-rename.csv**: A CSV file containing the barcode sequences and their corresponding sample
+  identifiers.
+- **barcode_dir**: The directory path where the barcode-specific folders are located.
+- **output_dir**: The directory path where the renamed FASTQ files will be saved.
+
+To run the tool, use the following command:
+```sh
+  snakemake --config barcode_dir=path/to/barcode/folders output_dir=data/date/ --cores all --use-conda barcode_rename
+```
+
 ### Sample sheet
 
 The sample sheet contains all samples to be analyzed by UnCoVar. UnCoVar offers

workflow/rules/preprocessing.smk

@@ -13,3 +13,15 @@ rule update_sample:
         "../envs/python.yaml"
     script:
         "../scripts/update-sample-sheet.py"
+
+
+rule barcode_rename:
+    input:
+        barcodes="barcode-rename.csv",
+        barcode_dir=config["barcode_dir"],
+    log:
+        "logs/barcode_rename.txt",
+    conda:
+        "../envs/python.yaml"
+    script:
+        "../scripts/barcode_rename.py"

workflow/scripts/barcode_rename.py

@@ -0,0 +1,82 @@
+import shutil
+import pandas as pd
+import gzip
+import subprocess
+import sys
+import os
+
+
+def get_barcode_dirs(source_directory, barcode_numbers):
+    try:
+        barcode_dirs = []
+        for barcode_number in barcode_numbers:
+            # Construct the source file path
+            source_file = f"barcode{barcode_number}"
+            source_path = os.path.join(source_directory, source_file)
+
+            if os.path.exists(source_path):
+                barcode_dirs.append(source_path)
+            else:
+                print(f"Directory '{source_path}' does not exist.")
+
+        return barcode_dirs
+
+    except Exception as e:
+        print(f"An error occurred: {str(e)}")
+        return []
+
+
+def concatenate_fastq(bc_directory, outfile):
+    input_files = os.path.join(bc_directory, "*.fastq.gz")
+    print(input_files)
+    out_file = f"{os.path.join(outfile, os.path.split(bc_directory)[1])}_all.fastq"
+    print(out_file)
+    subprocess.Popen(f"zcat {input_files} > {out_file}", shell=True).wait()
+
+
+def run_sample_prep(source_directory, barcode_numbers, outfile):
+    bc_folder = get_barcode_dirs(source_directory, barcode_numbers)
+    for item in bc_folder:
+        print(item)
+        concatenate_fastq(item, outfile)
+
+
+def rename_files(final_dir):
+    # rename files
+    renames = pd.read_csv(barcode_csv)
+    renames.reset_index(drop=True, inplace=True)
+
+    rename_dict = dict(zip(renames["barcode"], renames["sample_name"]))
+
+    print(rename_dict)
+
+    files = os.listdir(final_dir)
+    for file in files:
+        num = file.split("_")[0][-2:]
+        print(num)
+        print(
+            final_dir + file + " " + final_dir + str(rename_dict[int(num)]) + ".fastq"
+        )
+        os.rename(final_dir + file, final_dir + str(rename_dict[int(num)]) + ".fastq")
+    print(files)
+
+
+config = snakemake.config
+
+barcode_csv = str(snakemake.input.barcodes)
+source_path = str(snakemake.input.barcode_dir)
+out_dir = str(config["output_dir"])
+
+if not os.path.exists(source_path):
+    print(f"Source directory '{source_path}' not found.")
+
+# Check if the destination directory exists, create it if not
+if not os.path.exists(out_dir):
+    os.makedirs(out_dir)
+
+# getting barcode numbers
+barcode_csv_ = pd.read_csv(barcode_csv, dtype={"barcode": str})
+used_barcodes = barcode_csv_["barcode"]
+
+run_sample_prep(source_path, used_barcodes, out_dir)
+rename_files(out_dir)