def split(args):
'''fasta splitting and region splitting, dispatched by main()'''
if args.region_length is None:
split_fasta(args.fasta,args.num_files,args.per_file)
else:
split_regions(args.fasta,args.region_length,args.num_files,args.per_file)
def split(args):
'''fasta splitting and region splitting, dispatched by main()'''
if args.region_length is None:
split_fasta(args.fasta, args.num_files, args.per_file)
else:
split_regions(args.fasta, args.region_length, args.num_files,
args.per_file)
def parse_regions(args):
'''Takes the region and region_file arguments and parses them into
appropriate regions, depending on whcih are specified:
- If args.region_file specified, load and use those regions without
modification
- If region with position info specified directly, use that without
modification (eg. 1000:2000 or Lambda_NEB:1000:2000)
- If region with name specified but no position, split by max_length
using split_regions (eg. `-r Lambda_NEB`)
- If no region specified, split all sequences in reference fasta
into regions of max_length using split_regions
'''
regions = []
# if we specified region files, load regions from there, directly, no modifications
if args.region_file is not None:
if os.path.isfile(args.region_file):
regions += [x.strip() for x in open(args.region_file).readlines()]
# if we specified a region with positions directly, just use that
reginfo = RegionInfo(args.region)
if reginfo.start is not None:
regions.append(args.region)
# now only split if none specified from file and if args.region does not contain # info
if regions == []:
# make sure to split the regions up
if 'max_length' in args.params:
# split the regions if max length specified
regions = split_regions(args.ref,
args.params['max_length'],
userefs=args.region)
else:
# or use 10kb by default
regions = split_regions(args.ref, 10000, userefs=args.region)
return regions
def parse_regions(args):
'''Takes the region and region_file arguments and parses them into
appropriate regions, depending on whcih are specified:
- If args.region_file specified, load and use those regions without
modification
- If region with position info specified directly, use that without
modification (eg. 1000:2000 or Lambda_NEB:1000:2000)
- If region with name specified but no position, split by max_length
using split_regions (eg. `-r Lambda_NEB`)
- If no region specified, split all sequences in reference fasta
into regions of max_length using split_regions
'''
regions = []
# if we specified region files, load regions from there, directly, no modifications
if args.region_file is not None:
if os.path.isfile(args.region_file):
regions += [x.strip() for x in open(args.region_file).readlines()]
# if we specified a region with positions directly, just use that
reginfo = RegionInfo(args.region)
if reginfo.start is not None:
regions.append(args.region)
# now only split if none specified from file and if args.region does not contain # info
if regions == []:
# make sure to split the regions up
if 'max_length' in args.params:
# split the regions if max length specified
regions = split_regions(args.ref, args.params['max_length'], userefs=args.region)
else:
# or use 10kb by default
regions = split_regions(args.ref, 10000, userefs=args.region)
return regions