Deleted trailing Ns scripts and reformatted the VecScreen Python scri…

…pts with black

bin/VSlistTo1HitPerLine.py

@@ -16,6 +16,7 @@
 import re
 import argparse
 
+
 def main(args):
     hits_to_report = ""
     ID = ""
@@ -27,14 +28,14 @@ def main(args):
             line = line.strip()
             Fld = line.split(" ")
 
-            if not re.match(r'^[0-9 \t]+$', line):
+            if not re.match(r"^[0-9 \t]+$", line):
                 hits_to_report = ""
 
             if hits_to_report:
                 print(f"VecScreen_{hits_to_report.ljust(8)}\t{ID}\t{line}")
                 hits += 1
                 continue
-            
+
             if line.startswith(">Vector "):
                 if ID != "":
                     if error_found:
@@ -75,13 +76,20 @@ def main(args):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Reformatting VecScreen's output")
-    parser.add_argument("vecscreen_output_file", type=str, help="Path to a raw output file from NCBI VecScreen (from a run with the -f3 flag)", default=None)
+    parser.add_argument(
+        "vecscreen_output_file",
+        type=str,
+        help="Path to a raw output file from NCBI VecScreen (from a run with the -f3 flag)",
+        default=None,
+    )
     parser.add_argument("--skip_reporting_strong_hits", action="store_true", help="Skip reporting strong hits")
     parser.add_argument("--skip_reporting_moderate_hits", action="store_true", help="Skip reporting moderate hits")
     parser.add_argument("--skip_reporting_weak_hits", action="store_true", help="Skip reporting weak hits")
-    parser.add_argument("--skip_reporting_suspect_hits", action="store_true", help="Skip reporting hits of suspect origin")
+    parser.add_argument(
+        "--skip_reporting_suspect_hits", action="store_true", help="Skip reporting hits of suspect origin"
+    )
     parser.add_argument("--skip_reporting_no_hits", action="store_true", help="Skip reporting no-hits")
     parser.add_argument("--skip_reporting_errors", action="store_true", help="Skip reporting errors")
     parser.add_argument("-v", "--version", action="version", version="1.0")
     args = parser.parse_args()
-    main(args)
+    main(args)

bin/chunk_assembly_for_vecscreen.py

@@ -7,42 +7,44 @@
 import argparse
 import os
 
-def main(fasta_input_file, fasta_output_file):
-	fasta_input_file = os.path.abspath(fasta_input_file)
-	fasta_output_file = os.path.abspath(fasta_output_file)
 
-	threshold_length = 500000
-	overlap_length = int( threshold_length / 10 )
-	minimum_record_size = 11
+def main(fasta_input_file, fasta_output_file):
+    fasta_input_file = os.path.abspath(fasta_input_file)
+    fasta_output_file = os.path.abspath(fasta_output_file)
 
-	fasta_output_handle = open(fasta_output_file, 'w')
+    threshold_length = 500000
+    overlap_length = int(threshold_length / 10)
+    minimum_record_size = 11
 
-	with open(fasta_input_file, 'r') as fasta_input_handle:
-		for record in SeqIO.parse(fasta_input_handle, "fasta"):
+    fasta_output_handle = open(fasta_output_file, "w")
 
-			if len(record) >= minimum_record_size:
-				records_to_write = []
+    with open(fasta_input_file, "r") as fasta_input_handle:
+        for record in SeqIO.parse(fasta_input_handle, "fasta"):
+            if len(record) >= minimum_record_size:
+                records_to_write = []
 
-				slice_count = 0
-				while (slice_count * threshold_length) < len(record) - (threshold_length+overlap_length):
-					record_slice = record[(slice_count*threshold_length):((slice_count+1)*threshold_length + overlap_length)]
-					record_slice.id += '.chunk_' + str(slice_count+1)
+                slice_count = 0
+                while (slice_count * threshold_length) < len(record) - (threshold_length + overlap_length):
+                    record_slice = record[
+                        (slice_count * threshold_length) : ((slice_count + 1) * threshold_length + overlap_length)
+                    ]
+                    record_slice.id += ".chunk_" + str(slice_count + 1)
 
-					record_slice.description = ''
-					records_to_write.append(record_slice)
-					slice_count += 1
+                    record_slice.description = ""
+                    records_to_write.append(record_slice)
+                    slice_count += 1
 
-				final_record_slice = record[(slice_count*threshold_length):]
+                final_record_slice = record[(slice_count * threshold_length) :]
 
-				if slice_count > 0:
-					final_record_slice.id += '.chunk_' + str(slice_count+1)
-				final_record_slice.description = ''
+                if slice_count > 0:
+                    final_record_slice.id += ".chunk_" + str(slice_count + 1)
+                final_record_slice.description = ""
 
-				records_to_write.append(final_record_slice)
+                records_to_write.append(final_record_slice)
 
-				SeqIO.write(records_to_write, fasta_output_handle, 'fasta')
+                SeqIO.write(records_to_write, fasta_output_handle, "fasta")
 
-	fasta_output_handle.close()
+    fasta_output_handle.close()
 
 
 if __name__ == "__main__":

bin/summarise_vecscreen_output.py

@@ -46,8 +46,17 @@ def main(vecscreen_file, chunk_size):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument("vecscreen_file", type=str, help="Path to output file of VecScreen (run with -f3 flag), filtered with VSlistTo1HitPerLine.awk")
-    parser.add_argument("--chunk_size", type=int, help="Chunk size of the chunked FASTA file that VecScreen was run with, in bp. Default: 500000", default=50000)
+    parser.add_argument(
+        "vecscreen_file",
+        type=str,
+        help="Path to output file of VecScreen (run with -f3 flag), filtered with VSlistTo1HitPerLine.awk",
+    )
+    parser.add_argument(
+        "--chunk_size",
+        type=int,
+        help="Chunk size of the chunked FASTA file that VecScreen was run with, in bp. Default: 500000",
+        default=50000,
+    )
     parser.add_argument("-v", "--version", action="version", version="1.0")
     args = parser.parse_args()
     main(args.vecscreen_file, args.chunk_size)