Memory optimisation o sequence file handling;

README.md

@@ -33,7 +33,7 @@ sanntis test/files/BGC0001472.fna
 conda deactivate sanntis
 ```
 
-### Support of preprocessed InterProScan outputs
+#### Support of preprocessed InterProScan outputs
 
 SanntiS can be executed using preprocessed InterProScan outputs along with a GenBank (GBK) file specifying the coding sequences (CDSs). This integration increases user flexibility.
 ```bash

sanntis/modules/BGCdetection.py

@@ -99,16 +99,14 @@ def transformCDSpredToCDScontigs(self, cdsPredFile, file_format):
         if not os.path.isfile(cdsPredFile):
             log.exception(f"{cdsPredFile} file not found")
 
-        recs = list(SeqIO.parse(open(cdsPredFile, "r"), file_format))
-
         if file_format == "fasta":
 
             _prodigal_pattern = re.compile(
                 r"_\d+\s#\s(\d+)\s#\s(\d+)\s#\s(-?1)\s#\sID=(\d+_\d+);partial=(\d{2});start_type="
                 r"(\w+);rbs_motif=(.+);rbs_spacer=(\S+);gc_cont=(\d+\.\d+)"
             )
 
-            for record in recs:
+            for record in SeqIO.parse(open(cdsPredFile, "r"), file_format):
                 header = record.description
                 prodigal_match = _prodigal_pattern.search(header)
                 if not prodigal_match:
@@ -126,7 +124,7 @@ def transformCDSpredToCDScontigs(self, cdsPredFile, file_format):
 
         elif file_format == "genbank":
 
-            for record in recs:
+            for record in SeqIO.parse(open(cdsPredFile, "r"), file_format):
                 for f in record.features:
                     if f.type == "CDS":
                         start, end = int(f.location.start) + 1, int(f.location.end)