#create output directories
if not os.path.isdir(os.path.join(outputdir, 'annotate_misc')):
os.makedirs(os.path.join(outputdir, 'annotate_misc'))
os.makedirs(os.path.join(outputdir, 'annotate_results'))
else:
lib.log.error(
"Output directory %s already exists, will use any existing data. If this is not what you want, exit, and provide a unique name for output folder"
% (outputdir))
lib.log.info("Parsing input files")
Scaffolds = os.path.join(outputdir, 'annotate_misc',
'genome.scaffolds.fasta')
Proteins = os.path.join(outputdir, 'annotate_misc',
'genome.proteins.fasta')
Transcripts = os.path.join(outputdir, 'annotate_misc',
'genome.transcripts.fasta')
lib.gb2output(genbank, Proteins, Transcripts, Scaffolds)
#make sure logfiles directory is present, will need later
if not os.path.isdir(os.path.join(outputdir, 'logfiles')):
os.makedirs(os.path.join(outputdir, 'logfiles'))
#get absolute path for all input so there are no problems later, not using Transcripts yet could be error? so take out here
Proteins = os.path.abspath(Proteins)
genbank = os.path.abspath(genbank)
if 'phobius' in args.methods or 'all' in args.methods:
#run Phobius to predict secreted proteins and membrane, default is local if installed, otherwise remote
phobius_out = os.path.join(outputdir, 'annotate_misc',
'phobius.results.txt')
phobiusLog = os.path.join(outputdir, 'logfiles', 'phobius.log')
lib.log.info(
#create output directories
if not os.path.isdir(os.path.join(outputdir, 'annotate_misc')):
os.makedirs(os.path.join(outputdir, 'annotate_misc'))
os.makedirs(os.path.join(outputdir, 'annotate_results'))
else:
lib.log.error(
"Output directory %s already exists, will use any existing data. If this is not what you want, exit, and provide a unique name for output folder"
% (outputdir))
lib.log.info("Parsing input files")
Scaffolds = os.path.join(outputdir, 'annotate_misc',
'genome.scaffolds.fasta')
Proteins = os.path.join(outputdir, 'annotate_misc',
'genome.proteins.fasta')
Transcripts = os.path.join(outputdir, 'annotate_misc',
'genome.transcripts.fasta')
lib.gb2output(genbank, Proteins, Transcripts, Scaffolds)
#get absolute path for all input so there are no problems later, not using Transcripts yet could be error? so take out here
Scaffolds, Proteins, GFF = [
os.path.abspath(i) for i in [Scaffolds, Proteins, GFF]
] #suggestion via GitHub
#get organism and isolate from GBK file
if not args.species:
if genbank != '':
with open(genbank, 'rU') as gbk:
SeqRecords = SeqIO.parse(gbk, 'genbank')
for record in SeqRecords:
for f in record.features:
if f.type == "source":
organism = f.qualifiers.get("organism", ["???"])[0]
lib.log.error("Properly formatted 'funannotate predict' files do no exist in this directory")
os._exit(1)
else:
if inputdir == outputdir: #I'm assuming means that user supplied the predict folder (probably bad to assume...)
outputdir = lib.get_parent_dir(inputdir)
#create output directories
if not os.path.isdir(os.path.join(outputdir, 'annotate_misc')):
os.makedirs(os.path.join(outputdir, 'annotate_misc'))
os.makedirs(os.path.join(outputdir, 'annotate_results'))
else:
lib.log.error("Output directory %s already exists, will use any existing data. If this is not what you want, exit, and provide a unique name for output folder" % (outputdir))
lib.log.info("Parsing input files")
Scaffolds = os.path.join(outputdir, 'annotate_misc', 'genome.scaffolds.fasta')
Proteins = os.path.join(outputdir, 'annotate_misc','genome.proteins.fasta')
Transcripts = os.path.join(outputdir, 'annotate_misc', 'genome.transcripts.fasta')
lib.gb2output(genbank, Proteins, Transcripts, Scaffolds)
#get absolute path for all input so there are no problems later
for i in Scaffolds, Proteins, Transcripts, GFF:
i = os.path.abspath(i)
#get organism and isolate from GBK file
if not args.species:
with open(genbank, 'rU') as gbk:
SeqRecords = SeqIO.parse(gbk, 'genbank')
for record in SeqRecords:
for f in record.features:
if f.type == "source":
organism = f.qualifiers.get("organism", ["???"])[0]
if not args.isolate: