added params to decide if dengue_typing retrieves the sequence of the closest reference

Author: cimendes

flowcraft/bin/parse_fasta.py

@@ -5,6 +5,12 @@
 from itertools import groupby
 import os
 
+
+def replace_char(text):
+    for ch in ['/', '`', '*', '{', '}', '[', ']', '(', ')', '#', '+', '-', '.', '!', '$', ':']:
+        text = text.replace(ch, "_")
+    return text
+
 def getSequence(ref, fasta):
 
     entry = (x[1] for x in groupby(fasta, lambda line: line[0] == ">"))
@@ -15,8 +21,9 @@ def getSequence(ref, fasta):
 
         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")
+            fasta_header = replace_char(headerStr)
+            output_file = open(filename + '.fa', "w")
+            output_file.write(">" + fasta_header + "\n" + seq.upper() + "\n")
             output_file.close()
 
 def main():

flowcraft/generator/components/typing.py

@@ -130,6 +130,14 @@ def __init__(self, **kwargs):
 
         self.link_start = None
 
+        self.params = {
+            "reference": {
+                "default": "false",
+                "description":
+                    "Retrieves the sequence of the closest reference."
+            }
+        }
+
         self.directives = {"dengue_typing": {
             "cpus": 4,
             "memory": "'4GB'",

flowcraft/generator/templates/dengue_typing.nf

@@ -1,3 +1,7 @@
+
+getRef = params.reference ? "true" : "false"
+getRef_{{ pid }} = Channel.value(getRef)
+
 process dengue_typing_{{ pid }} {
 
     // Send POST request to platform
@@ -9,10 +13,11 @@ process dengue_typing_{{ pid }} {
 
     input:
     set sample_id, file(assembly) from {{ input_channel }}
+    val ref from getRef_{{ pid }}
 
     output:
     file "seq_typing*"
-    file "*.fa"
+    file "*.fa" into _ref_seqTyping, optional True
     {% with task_name="dengue_typing" %}
     {%- include "compiler_channels.txt" ignore missing -%}
     {% endwith %}
@@ -27,8 +32,12 @@ 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
+
+        if [ $ref = "cool" ]
+        then
+            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
+        fi
 
         # 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'}]}"

flowcraft/generator/templates/mafft.nf

@@ -8,6 +8,7 @@ process mafft_{{ pid }} {
 
     input:
     file(assembly) from {{ input_channel }}.map{ it[1] }.collect()
+    file(refs) from _ref_seqTyping.collect().unique()
 
     output:
     file ("*.align") into {{ output_channel }}
@@ -18,7 +19,9 @@ process mafft_{{ pid }} {
     script:
     """
 
-    cat ${assembly} > all_assemblies.fasta
+
+
+    cat ${assembly} ${refs} > all_assemblies.fasta
 
     mafft --adjustdirection --thread $task.cpus --auto all_assemblies.fasta > ${workflow.scriptName}.align
     """