DSL2: nf-test test_long

.github/workflows/linting_comment.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@ac66b43f0e6a346234dd65d4d0c8fbb31cb316e5 # v11
+        uses: dawidd6/action-download-artifact@4c1e823582f43b179e2cbb49c3eade4e41f992e2 # v10
         with:
           workflow: linting.yml
           workflow_conclusion: completed

bin/collect_genotypes.py

@@ -5,19 +5,22 @@
 import argparse
 import filecmp
 
+
 def file_len(fname):
     with open(fname) as f:
         for i, l in enumerate(f):
             pass
     return i + 1
 
+
 ## A function to return the number of genotypes per line in a .geno file.
 def file_width(fname):
     with open(fname) as f:
         for i in f:
-            return(len(i.strip()))
+            return len(i.strip())
             break
 
+
 ## A function to check that there are no duplicate individual IDs across ind files.
 def check_for_duplicate_ids(indf1, indf2):
     with open(indf1) as f:
@@ -26,13 +29,19 @@ def check_for_duplicate_ids(indf1, indf2):
         inds2 = [x.strip().split()[0] for x in f.readlines()]
     intersection = set(inds1).intersection(inds2)
     if len(intersection) > 0:
-        raise IOError("Input .ind files contain duplicate individual IDs. Duplicates: {}".format(intersection))
+        raise IOError(
+            "Input .ind files contain duplicate individual IDs. Duplicates: {}".format(
+                intersection
+            )
+        )
+
 
 ## Function to check that the snp files are identical
 def check_snp_files(snpf1, snpf2):
     if not filecmp.cmp(snpf1, snpf2):
         raise IOError("Input .snp files are not identical.")
 
+
 ## Function to check the consistency of an eigenstrat database
 def validate_eigenstrat(genof, snpf, indf):
     dimsGeno = [file_len(genof), file_width(genof)]
@@ -41,40 +50,99 @@ def validate_eigenstrat(genof, snpf, indf):
 
     # print(dimsGeno,linesSnp,linesInd)
     ##Check geno and snp compatibility
-    if dimsGeno[0] !=    linesSnp:
+    if dimsGeno[0] != linesSnp:
         raise IOError("Input .snp and .geno files do not match.")
 
     ##Check geno and ind compatibility
-    if dimsGeno[1] !=    linesInd:
+    if dimsGeno[1] != linesInd:
         raise IOError("Input .ind and .geno files do not match.")
 
+
 VERSION = "1.0.0"
 
-parser = argparse.ArgumentParser(usage="%(prog)s [-v] (-g1 <GENO FILE 1 NAME>) (-s1 <SNP FILE 1 NAME>) (-i1 <IND FILE 1 NAME>) (-g2 <GENO FILE 2 NAME>) (-s2 <SNP FILE 2 NAME>) (-i2 <IND FILE 2 NAME>) (-o <OUTPUT FILE PREFIX>)" , description="A tool to put together two EIGENSTRAT datasets of genotyped on the same SNP set into a single dataset.")
+parser = argparse.ArgumentParser(
+    usage="%(prog)s [-v] (-g1 <GENO FILE 1 NAME>) (-s1 <SNP FILE 1 NAME>) (-i1 <IND FILE 1 NAME>) (-g2 <GENO FILE 2 NAME>) (-s2 <SNP FILE 2 NAME>) (-i2 <IND FILE 2 NAME>) (-o <OUTPUT FILE PREFIX>)",
+    description="A tool to put together two EIGENSTRAT datasets of genotyped on the same SNP set into a single dataset.",
+)
 parser._optionals.title = "Available options"
-parser.add_argument("-g1", "--genoFn1", type = str, metavar = "<GENO FILE 1 NAME>",    required = True, help = "The path to the input geno file of the first dataset.")
-parser.add_argument("-s1", "--snpFn1",  type = str, metavar = "<SNP FILE 1 NAME>",     required = True, help = "The path to the input snp file of the first dataset.")
-parser.add_argument("-i1", "--indFn1",  type = str, metavar = "<IND FILE 1 NAME>",     required = True, help = "The path to the input ind file of the first dataset.")
-parser.add_argument("-g2", "--genoFn2", type = str, metavar = "<GENO FILE 2 NAME>",    required = True, help = "The path to the input geno file of the second dataset.")
-parser.add_argument("-s2", "--snpFn2",  type = str, metavar = "<SNP FILE 2 NAME>",     required = True, help = "The path to the input snp file of the second dataset.")
-parser.add_argument("-i2", "--indFn2",  type = str, metavar = "<IND FILE 2 NAME>",     required = True, help = "The path to the input ind file of the second dataset.")
-parser.add_argument("-o", "--output",   type = str, metavar = "<OUTPUT FILES PREFIX>", required = True, help = "The desired output file prefix. Three output files are created, <OUTPUT FILES PREFIX>.geno , <OUTPUT FILES PREFIX>.snp and <OUTPUT FILES PREFIX>.ind .")
-parser.add_argument("-v", "--version", action='version', version="{}".format(VERSION), help="Print the version and exit.")
+parser.add_argument(
+    "-g1",
+    "--genoFn1",
+    type=str,
+    metavar="<GENO FILE 1 NAME>",
+    required=True,
+    help="The path to the input geno file of the first dataset.",
+)
+parser.add_argument(
+    "-s1",
+    "--snpFn1",
+    type=str,
+    metavar="<SNP FILE 1 NAME>",
+    required=True,
+    help="The path to the input snp file of the first dataset.",
+)
+parser.add_argument(
+    "-i1",
+    "--indFn1",
+    type=str,
+    metavar="<IND FILE 1 NAME>",
+    required=True,
+    help="The path to the input ind file of the first dataset.",
+)
+parser.add_argument(
+    "-g2",
+    "--genoFn2",
+    type=str,
+    metavar="<GENO FILE 2 NAME>",
+    required=True,
+    help="The path to the input geno file of the second dataset.",
+)
+parser.add_argument(
+    "-s2",
+    "--snpFn2",
+    type=str,
+    metavar="<SNP FILE 2 NAME>",
+    required=True,
+    help="The path to the input snp file of the second dataset.",
+)
+parser.add_argument(
+    "-i2",
+    "--indFn2",
+    type=str,
+    metavar="<IND FILE 2 NAME>",
+    required=True,
+    help="The path to the input ind file of the second dataset.",
+)
+parser.add_argument(
+    "-o",
+    "--output",
+    type=str,
+    metavar="<OUTPUT FILES PREFIX>",
+    required=True,
+    help="The desired output file prefix. Three output files are created, <OUTPUT FILES PREFIX>.geno , <OUTPUT FILES PREFIX>.snp and <OUTPUT FILES PREFIX>.ind .",
+)
+parser.add_argument(
+    "-v",
+    "--version",
+    action="version",
+    version="{}".format(VERSION),
+    help="Print the version and exit.",
+)
 args = parser.parse_args()
 
 ## Open input files
 GenoFile1 = open(args.genoFn1, "r")
-SnpFile1  = open(args.snpFn1,  "r")
-IndFile1  = open(args.indFn1,  "r")
+SnpFile1 = open(args.snpFn1, "r")
+IndFile1 = open(args.indFn1, "r")
 
 GenoFile2 = open(args.genoFn2, "r")
 # SnpFile2  = open(args.snpFn2,  "r") ## Never actually read in line by line
-IndFile2  = open(args.indFn2,  "r")
+IndFile2 = open(args.indFn2, "r")
 
 ## open output files
 GenoFileOut = open(args.output + ".geno", "w")
-SnpFileOut  = open(args.output + ".snp",  "w")
-IndFileOut  = open(args.output + ".ind",  "w")
+SnpFileOut = open(args.output + ".snp", "w")
+IndFileOut = open(args.output + ".ind", "w")
 
 ## Perform basic validation on inputs
 validate_eigenstrat(args.genoFn1, args.snpFn1, args.indFn1)
@@ -85,7 +153,7 @@ def validate_eigenstrat(genof, snpf, indf):
 ## Now actually merge the data
 ## Geno
 for line1, line2 in zip(GenoFile1, GenoFile2):
-    geno_line="{}{}".format(line1.strip(),line2.strip())
+    geno_line = "{}{}".format(line1.strip(), line2.strip())
     print(geno_line, file=GenoFileOut)
 
 ## Snp

bin/extract_map_reads.py

@@ -27,16 +27,24 @@ def _get_args():
         action="store_true",
         help="specify if bam file was created from merged fastq files",
     )
-    parser.add_argument("-rev", dest="rev", default=None, help="path to reverse fastq file")
-    parser.add_argument("-of", dest="out_fwd", default=None, help="path to forward output fastq file")
-    parser.add_argument("-or", dest="out_rev", default=None, help="path to forward output fastq file")
+    parser.add_argument(
+        "-rev", dest="rev", default=None, help="path to reverse fastq file"
+    )
+    parser.add_argument(
+        "-of", dest="out_fwd", default=None, help="path to forward output fastq file"
+    )
+    parser.add_argument(
+        "-or", dest="out_rev", default=None, help="path to forward output fastq file"
+    )
     parser.add_argument(
         "-m",
         dest="mode",
         default="remove",
         help="Read removal mode: remove reads (remove) or replace sequence by N (replace). Default = remove",
     )
-    parser.add_argument("-t", dest="threads", default=4, help="Number of parallel threads")
+    parser.add_argument(
+        "-t", dest="threads", default=4, help="Number of parallel threads"
+    )
 
     args = parser.parse_args()
 

bin/filter_bam_fragment_length.py

@@ -9,7 +9,9 @@
 
 def get_args():
     """This function parses and return arguments passed in"""
-    parser = argparse.ArgumentParser(prog="bam_filter", description="Filter bam on fragment length")
+    parser = argparse.ArgumentParser(
+        prog="bam_filter", description="Filter bam on fragment length"
+    )
     parser.add_argument("bam", help="Bam aligment file")
     parser.add_argument(
         "-l",

bin/print_x_contamination.py

@@ -86,7 +86,20 @@ def make_float(x):
             "Method2_ML_estimate": ml2,
             "Method2_ML_SE": err_ml2,
         }
-        print(Ind, nSNPs, mom1, err_mom1, ml1, err_ml1, mom2, err_mom2, ml2, err_ml2, sep="\t", file=output)
+        print(
+            Ind,
+            nSNPs,
+            mom1,
+            err_mom1,
+            ml1,
+            err_ml1,
+            mom2,
+            err_mom2,
+            ml2,
+            err_ml2,
+            sep="\t",
+            file=output,
+        )
 
 
 jsonOut = {

conf/test_long.config

@@ -16,8 +16,14 @@ process {
         memory: '15.GB',
         time: '3.h',
     ]
+
+    withName: MAPDAMAGE2 {
+        time   = { 3.h   * task.attempt }
+        memory = { 15.GB * task.attempt }
+    }
 }
 
+
 includeConfig 'test_minimal.config'
 
 params {

modules.json

@@ -212,7 +212,7 @@
                     },
                     "mapdamage2": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
                         "installed_by": ["modules"]
                     },
                     "megan/rma2info": {