dengue_typing now retrieves the sequence of the closest reference

Author: cimendes

flowcraft/bin/parse_fasta.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+
+import argparse
+from itertools import groupby
+import os
+
+def getSequence(ref, fasta):
+
+    entry = (x[1] for x in groupby(fasta, lambda line: line[0] == ">"))
+
+    for header in entry:
+        headerStr = header.__next__()[1:].strip()
+        seq = "".join(s.strip() for s in entry.__next__())
+
+        if ref == headerStr.replace('>',''):
+            filename = os.path.join(os.getcwd(), ref.replace('/','_').split('|')[0])
+            output_file = open(filename + '.fa', "w+")
+            output_file.write(">" + headerStr + "\\n" + seq + "\\n")
+            output_file.close()
+
+def main():
+
+    parser = argparse.ArgumentParser(prog='parse_fasta.py', description="Parse FASTA files for a specific header", formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+    parser.add_argument('--version', help='Version information', action='version', version=str('%(prog)s v0.1'))
+
+    parser_required = parser.add_argument_group('Required options')
+    parser_required.add_argument('-t', type=str, metavar='header of sequence to be retrieved',
+                             help='Uncompressed fastq file containing mate 1 reads', required=True)
+    parser_required.add_argument('-f', type=argparse.FileType('r'), metavar='/path/to/input/file.fasta',
+                             help='Fasta with the sequences', required=True)
+
+    args = parser.parse_args()
+
+    getSequence(args.t, args.f)
+
+
+
+if __name__ == "__main__":
+    main()

flowcraft/generator/templates/dengue_typing.nf

@@ -12,6 +12,7 @@ process dengue_typing_{{ pid }} {
 
     output:
     file "seq_typing*"
+    file "*.fa"
     {% with task_name="dengue_typing" %}
     {%- include "compiler_channels.txt" ignore missing -%}
     {% endwith %}
@@ -26,6 +27,9 @@ process dengue_typing_{{ pid }} {
 
         seq_typing.py assembly --org Dengue Virus -f ${assembly} -o ./ -j $task.cpus -t nucl
 
+        awk 'NR == 2 { print \$4 }' seq_typing.report_types.tab > reference
+        parse_fasta.py -t \$(cat reference)  -f /NGStools/seq_typing/reference_sequences/dengue_virus/1_GenotypesDENV_14-05-18.fasta
+
         # Add information to dotfiles
         json_str="{'tableRow':[{'sample':'${sample_id}','data':[{'header':'seqtyping','value':'\$(cat seq_typing.report.txt)','table':'typing'}]}],'metadata':[{'sample':'${sample_id}','treeData':'\$(cat seq_typing.report.txt)','column':'typing'}]}"
         echo \$json_str > .report.json