Include fasta header conversion and restoration steps in ghostx module scripts.

scripts/convert_ghostx.py

 #!/usr/bin/python3
+
 import sys
 import json
 import argparse
+from os import path
+import subprocess
 
 parser = argparse.ArgumentParser(description='Convert ghostx results to json documents')
 parser.add_argument('--result', '-r', required=True, help='The ghostx result directory')
@@ -55,3 +58,6 @@ with open(result_filename) as f:
 output_filename = args.output
 with open(output_filename, 'w') as o:
     json.dump(documents, o)
+
+restore_seq_ids_tool = path.dirname(__file__) + '/restore_seq_id_from_enumeration.py'
+subprocess.run([restore_seq_ids_tool, '-j', output_filename, '-e', args.result + '/enum_headers.tsv'])

scripts/reduce_fasta_headers_to_enumeration.py

@@ -2,9 +2,11 @@
 
 import argparse
 import fileinput
+import os
 
-parser = argparse.ArgumentParser(description='Replaces fasta headers with unique numbers and stores original headers in tsv file')
+parser = argparse.ArgumentParser(description='Replaces fasta headers with unique numbers and saves both in tsv format')
 parser.add_argument('--fasta', '-f', required=True, help='The fasta file')
+parser.add_argument('--enum-headers-dir', '-d', default='.', help='Target directory for headers file enum_headers.tsv')
 args = parser.parse_args()
 
 fasta = args.fasta
@@ -21,8 +23,7 @@ with fileinput.FileInput(fasta, inplace=True) as f:
         else:
             print(line, end='')
 
-headers_dict_file = 'enum_header_dict.tsv'
-
-with open(headers_dict_file, 'w') as o:
+enum_headers_file = args.enum_headers_dir + '/enum_headers.tsv'
+with open(enum_headers_file, 'w') as o:
     for key in headers_dict:
         o.write("{}\t{}\n".format(key, headers_dict[key]))

scripts/restore_seq_id_from_enumeration.py

@@ -8,18 +8,24 @@ parser.add_argument('--json', '-j', required=True, help='The results json file')
 parser.add_argument('--enum-headers', '-e', required=True, help='The enumerated original headers in tsv format')
 args = parser.parse_args()
 
-header_dict = {}
-documents = {}
+seq_id_dict = {}
+docs_enumerated = {}
 
 with open(args.json) as j:
-    documents = json.load(j)
+    docs_enumerated = json.load(j)
 
 with open(args.enum_headers) as h:
     for line in h:
         num, header = line.strip().split('\t')
-        header_dict[num] = header
+        seq_id_dict[num] = header.split()[0]
 
-documents["id"] = header_dict[documents["id"]].split()[0]
+documents_restored = {}
+
+for num in docs_enumerated:
+    seq_id = seq_id_dict[num]
+    doc = docs_enumerated[num]
+    doc["id"] = seq_id
+    documents_restored[seq_id] = doc
 
 with open(args.json, 'w') as o:
-    json.dump(documents, o)
+    json.dump(documents_restored, o)

scripts/run_ghostx.py

 #!/usr/bin/env python3
+
 import env
 import argparse
 import re
-from os import system,makedirs
+from os import system,makedirs,path
 from psot import config
 import subprocess
 import json
@@ -15,6 +16,11 @@ parser.add_argument('--database', '-d', required=True, help='Database to search
 parser.add_argument('--output', '-o', required=True, help='The result directory. Will contain info.json and results.tsv.')
 args = parser.parse_args()
 
+makedirs(args.output, exist_ok=True)
+
+reduce_headers_tool = path.dirname(__file__) + '/reduce_fasta_headers_to_enumeration.py'
+subprocess.run([reduce_headers_tool, "-f", args.fasta, "-d", args.output])
+
 # Aproach:
 #  directory for output
 #    info.json -> Tool info
@@ -26,11 +32,10 @@ toolconfig = {
 }
 # find version
 output = subprocess.run([ghostx_tool], stderr=subprocess.PIPE)
-text =output.stderr.decode('ascii') 
+text = output.stderr.decode('ascii') 
 result = re.search('version (.*)', text)
 toolconfig['version'] = result.group(1)
 
-makedirs(args.output, exist_ok=True)
 with open(args.output + '/info.json', 'w') as f:
     json.dump(toolconfig, f)
 system(ghostx_tool + " aln -d " + args.database + " -o " + args.output + "/results.tsv -i " + args.fasta)