formatting

config/config.yaml

@@ -16,22 +16,19 @@ sample-sheet:
   # path to the fastq files of the samples for the sample sheet
   data-path: "/groups/ds/metagenomes/run_folder/"
 
-
 data-handling:
   # path to store input fastq data within the workflow
   data: "data/"
   # path to store databases and reference genomes used within the workflow
   resources: "resources/"
 
-
 ## qualtiy criteria used for filtering
 quality-criteria:
   # minimal length of acceptable reads
   min-length-reads: 15
   # average quality of acceptable reads (PHRED)
   min-PHRED: 20
 
-
 human-ref: "https://ftp.ncbi.nlm.nih.gov/refseq/H_sapiens/annotation/GRCh38_latest/refseq_identifiers/GRCh38_latest_genomic.fna.gz"
 
 kraken:

workflow/Snakefile

@@ -16,9 +16,12 @@ include: "rules/qc.smk"
 include: "rules/species_diversity.smk"
 include: "rules/report.smk"
 
+
 if config["sample-sheet"]["auto-creation"]:
+
     include: "rules/preprocessing.smk"
 
+
 DATE = get_run_date()
 
 
@@ -37,15 +40,10 @@ rule all:
 
 onsuccess:
     print("Workflow finished without an error.")
-    if os.path.exists("results/{date}/report/{date}_report.zip".format(date=DATE)):  
+    if os.path.exists("results/{date}/report/{date}_report.zip".format(date=DATE)):
         shell("tar cpfz results/{DATE}/{DATE}_results.tar.gz results/{DATE}/report/")
-        print(
-            "You can find the results in {date}_results.tar.gz".format(
-                date=DATE
-            )
-        )
+        print("You can find the results in {date}_results.tar.gz".format(date=DATE))
 
 
 onerror:
     print("An error occurred")
-

workflow/rules/preprocessing.smk

@@ -1,6 +1,6 @@
 rule create_sample_sheet:
     input:
-        "config/pep/samples.csv"
+        "config/pep/samples.csv",
     params:
         inpath=config["sample-sheet"]["data-path"],
         renaming=config["sample-sheet"]["rename-sample-files"],

workflow/scripts/create_sample_sheet.py

@@ -5,21 +5,27 @@
 ## write to log file
 sys.stderr = open(snakemake.log[0], "w")
 
-inpath=snakemake.params.inpath 
-renaming=snakemake.params.renaming
-sample_csv=snakemake.input[0]
+inpath = snakemake.params.inpath
+renaming = snakemake.params.renaming
+sample_csv = snakemake.input[0]
 
 
 def rename_fastqs(path):
-    samples=[]
-    #fastqs=os.listdir(path)
-    fastqs=[file for file in os.listdir(path) if file.endswith(".fastq.gz")]
-    if not fastqs:
-        print(f"Error: There are no fastq files in the directory. Have you used the correct path: {path}?")
-        raise Exception(f"There are no fastq files in the directory. Have you used the correct path: {path}?")
+    samples = []
 
+    fastqs = [file for file in os.listdir(path) if file.endswith(".fastq.gz")]
+    if not fastqs:
+        print(
+            f"Error: There are no fastq files in the directory. Have you used the correct path: {path}?"
+        )
+        raise Exception(
+            f"There are no fastq files in the directory. Have you used the correct path: {path}?"
+        )
+
     if renaming:
-        print("Renaming fastq files, e.g. from sampleID_S40_L001_R1_001.fastq.gz to sampleID_R1.fastq.gz")
+        print(
+            "Renaming fastq files, e.g. from sampleID_S40_L001_R1_001.fastq.gz to sampleID_R1.fastq.gz"
+        )
     else:
         print("Fastq files will not be renamed")
 
@@ -33,20 +39,22 @@ def rename_fastqs(path):
             samples.append(sample)
 
         if renaming:
-            os.system(f"mv {path}{fastq} {path}{fastq_new}")
-            
-    return(samples)
+            os.system(f"mv {path} {fastq} {path} {fastq_new}")
+
+    return samples
 
 
 def write_sample_sheet(samples, path, outfile):
-    #os.system(f"touch {outfile}")
+    # os.system(f"touch {outfile}")
 
-    with open(outfile,"w") as sheet:
+    with open(outfile, "w") as sheet:
         sheet.write("sample_name,fq1,fq2\n")
 
         for sample in samples:
-            sheet.write(f"{sample},{path}{sample}_R1.fastq.gz,{path}{sample}_R2.fastq.gz\n")
+            sheet.write(
+                f"{sample},{path} {sample}_R1.fastq.gz,{path} {sample}_R2.fastq.gz\n"
+            )
 
 
-samples=rename_fastqs(inpath)
+samples = rename_fastqs(inpath)
 write_sample_sheet(samples, inpath, sample_csv)