Dsl2

.github/workflows/ci.yml

@@ -44,7 +44,7 @@ jobs:
       if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/epitopeprediction') }}
       runs-on: ubuntu-latest
       env:
-        NXF_VER: '20.04.0'
+        NXF_VER: '21.04.0'
         NXF_ANSI_LOG: false
       strategy:
         matrix:
@@ -81,7 +81,7 @@ jobs:
       if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/epitopeprediction') }}
       runs-on: ubuntu-latest
       env:
-        NXF_VER: '20.04.0'
+        NXF_VER: '21.04.0'
         NXF_ANSI_LOG: false
       steps:
         - name: Check out pipeline code

CHANGELOG.md

@@ -8,10 +8,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 - [#73](https://github.com/nf-core/epitopeprediction/pull/73) - Add support for the non-free netmhc tool family including netMHC 4.0, netMHCpan 4.0, netMHCII 2.2, and netMHCIIpan 3.1
+- [#101](https://github.com/nf-core/epitopeprediction/pull/101) - Inclusion of local modules and DSL2 conversion
 
 ### `Changed`
 
 - [#100](https://github.com/nf-core/epitopeprediction/pull/89) - Merge previous template updates up to `v2.1`
+- [#110](https://github.com/nf-core/epitopeprediction/pull/110) - DSL2 conversion
 
 ### `Fixed`
 

assets/multiqc_config.yaml

@@ -1,7 +1,7 @@
 report_comment: >
     This report has been generated by the <a href="https://github.com/nf-core/epitopeprediction" target="_blank">nf-core/epitopeprediction</a>
     analysis pipeline. For information about how to interpret these results, please see the
-    <a href="https://nf-co.re/epitopeprediction" target="_blank">documentation</a>.
+    <a href="https://github.com/nf-core/epitopeprediction" target="_blank">documentation</a>.
 report_section_order:
     software_versions:
         order: -1000

bin/check_requested_models.py

@@ -36,6 +36,7 @@ def read_peptide_input(filename):
 
 def convert_allele_back(allele):
     name = str(allele)
+    print(name)
     if name.startswith("H-2-"):
         # convert internal Fred2 representation back to the nf-core/epitopeprediction input allele format
         return name.replace("H-2-", "H2-")
@@ -49,23 +50,24 @@ def __main__():
     parser = argparse.ArgumentParser("Write out information about supported models by Fred2 for installed predictor tool versions.")
     parser.add_argument('-p', "--peptides", help="File with one peptide per line")
     parser.add_argument('-c', "--mhcclass", default=1, help="MHC class I or II")
-    parser.add_argument('-l', "--max_length", help="Maximum peptide length")
-    parser.add_argument('-ml', "--min_length", help="Minimum peptide length")
-    parser.add_argument('-a', "--alleles", help="<Required> MHC Alleles", required=True)
+    parser.add_argument('-l', "--max_length", help="Maximum peptide length", type=int)
+    parser.add_argument('-ml', "--min_length", help="Minimum peptide length", type=int)
+    parser.add_argument('-a', "--alleles", help="<Required> MHC Alleles", required=True, type=str)
     parser.add_argument('-t', '--tools', help='Tools requested for peptide predictions', required=True, type=str)
     parser.add_argument('-v', '--versions', help='<Required> File with used software versions.', required=True)
     args = parser.parse_args()
 
     selected_methods = [item for item in args.tools.split(',')]
     with open(args.versions, 'r') as versions_file:
-        tool_version = [ (row[0], str(row[1][1:])) for row in csv.reader(versions_file, delimiter = "\t") ]
+        tool_version = [ (row[0].split()[0], str(row[1])) for row in csv.reader(versions_file, delimiter = "\t") ]
         # NOTE this needs to be updated, if a newer version will be available via Fred2 and should be used in the future
         tool_version.append(('syfpeithi', '1.0')) # how to handle this?
         # get for each method the corresponding tool version
         methods = { method:version for tool, version in tool_version for method in selected_methods if tool.lower() in method.lower() }
 
     # get the alleles
-    alleles = FileReader.read_lines(args.alleles, in_type=Allele)
+    # alleles = FileReader.read_lines(args.alleles, in_type=Allele)
+    alleles= [Allele(a) for a in args.alleles.split(";")]
 
     peptide_lengths = []
     if (args.peptides):

bin/check_samplesheet.py

@@ -2,11 +2,12 @@
 
 
 import os
+import re
 import sys
+import errno
 import argparse
 import re
 
-
 def parse_args(args=None):
     Description = "Reformat nf-core/epitopeprediction samplesheet file and check its contents."
     Epilog = "Example usage: python check_samplesheet.py <FILE_IN> <FILE_OUT>"
@@ -30,7 +31,7 @@ def print_error(error, context="Line", context_str=""):
 def check_allele_nomenclature(allele):
     pattern = re.compile("(^[A-Z][\*][0-9][0-9][:][0-9][0-9])$")
     return pattern.match(allele) is not None
-        
+
 
 def make_dir(path):
     if len(path) > 0:
@@ -62,7 +63,7 @@ def check_samplesheet(file_in, file_out):
 
     Furhter Examples:
     - Class2 allele format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/alleles/alleles.DRB1_01_01.txt
-    - Mouse allele format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/alleles/alleles.H2.txt 
+    - Mouse allele format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/alleles/alleles.H2.txt
     - pep.tsv => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/peptides/peptides.tsv
     - annotated_variants.tsv => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/variants/variants.tsv
     - annotated_variants.vcf => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/variants/variants.vcf
@@ -97,33 +98,27 @@ def check_samplesheet(file_in, file_out):
                     "Line",
                     line,
                 )
-
-            sample, alleles, filename = lspl[: len(HEADER)]
-
 
-            ## Check if the alleles given in the text file are in the right format
-            if alleles.endswith(".txt"):
-                with open(alleles, "r") as af:
-                    alleles = ';'.join([al.strip('\n') if check_allele_nomenclature(al) else \
-                    print_error("Allele format is not matching the nomenclature", "Line", line) for al in af.readlines()])
-
+            ## Check sample name entries
+            sample, alleles, filename = lspl[: len(HEADER)]
 
+            file_extension = os.path.splitext(filename)[1][1::]
             ## Get annotation of filename column
-            if filename.endswith(".vcf"):
+            if filename.endswith(".vcf") | filename.endswith(".vcf.gz"):
                 anno = "variant"
-            elif filename.endswith(".tsv"):
+            elif filename.endswith(".tsv") | filename.endswith(".GSvar"):
                 ## Check if it is a variant annotation file or a peptide file
                 with open(filename, "r") as tsv:
                     first_header_col = [col.lower() for col in tsv.readlines()[0].split('\t')][0]
                     if first_header_col == "id":
                         anno = "pep"
-                    elif first_header_col == "#chr": 
-                        anno = "variant"   
+                    elif first_header_col == "#chr":
+                        anno = "variant"
             else:
                 anno = "prot"
 
-            sample_info = [sample, alleles, filename, anno]
-            ## Create sample mapping dictionary 
+            sample_info = [sample, alleles, filename, anno, file_extension]
+            ## Create sample mapping dictionary
             if sample not in sample_run_dict:
                 sample_run_dict[sample] = [sample_info]
             else:
@@ -137,10 +132,10 @@ def check_samplesheet(file_in, file_out):
         out_dir = os.path.dirname(file_out)
         make_dir(out_dir)
         with open(file_out, "w") as fout:
-            fout.write(",".join(["sample", "alleles", "filename", "anno"]) + "\n")
+            fout.write(",".join(["sample", "alleles", "filename", "anno", "ext"]) + "\n")
 
             for sample in sorted(sample_run_dict.keys()):
-                for idx, val in enumerate(sample_run_dict[sample]):
+                for val in sample_run_dict[sample]:
                     fout.write(",".join(val) + "\n")
 
 
@@ -150,4 +145,4 @@ def main(args=None):
 
 
 if __name__ == "__main__":
-    sys.exit(main())
+    sys.exit(main())

bin/check_supported_models.py

@@ -25,7 +25,7 @@ def __main__():
     # NOTE this needs to be updated manually, if other methods should be used in the future
     available_methods = ['syfpeithi', 'mhcflurry', 'mhcnuggets-class-1', 'mhcnuggets-class-2']
     with open(args.versions, 'r') as versions_file:
-        tool_version = [ (row[0], str(row[1][1:])) for row in csv.reader(versions_file, delimiter = "\t") ]
+        tool_version = [ (row[0].split()[0], str(row[1])) for row in csv.reader(versions_file, delimiter = "\t") ]
         # NOTE this needs to be updated, if a newer version will be available via Fred2 and should be used in the future
         tool_version.append(('syfpeithi', '1.0'))
         # get for each method the corresponding tool version

bin/decrypt

@@ -2,9 +2,9 @@
 # Decrypts stdin -> stdout reading the passphrase from the environment variable
 # DECRYPT_PASSPHRASE.
 gpg \
-	--quiet \
-	--batch \
-	--yes \
-	--decrypt \
-	--passphrase="$DECRYPT_PASSPHRASE" \
-	--output -
+    --quiet \
+    --batch \
+    --yes \
+    --decrypt \
+    --passphrase="$DECRYPT_PASSPHRASE" \
+    --output -