def __main__():
# Parse Command Line
options, args = doc_optparse.parse(__doc__)
mincols = 0
strand_col = -1
if options.dbkey:
primary_species = options.dbkey
else:
primary_species = None
if primary_species in [None, "?", "None"]:
stop_err(
"You must specify a proper build in order to extract alignments. You can specify your genome build by clicking on the pencil icon associated with your interval file."
)
include_primary = True
secondary_species = maf_utilities.parse_species_option(options.species)
if secondary_species:
species = list(secondary_species) # make copy of species list
if primary_species in secondary_species:
secondary_species.remove(primary_species)
else:
include_primary = False
else:
species = None
if options.interval_file:
interval_file = options.interval_file
else:
stop_err("Input interval file has not been specified.")
if options.output_file:
output_file = options.output_file
else:
stop_err("Output file has not been specified.")
if not options.geneBED:
if options.chromCol:
chr_col = int(options.chromCol) - 1
else:
stop_err(
"Chromosome column not set, click the pencil icon in the history item to set the metadata attributes."
)
if options.startCol:
start_col = int(options.startCol) - 1
else:
stop_err(
"Start column not set, click the pencil icon in the history item to set the metadata attributes."
)
if options.endCol:
end_col = int(options.endCol) - 1
else:
stop_err(
"End column not set, click the pencil icon in the history item to set the metadata attributes."
)
if options.strandCol:
strand_col = int(options.strandCol) - 1
mafIndexFile = "%s/maf_index.loc" % options.mafIndexFileDir
overwrite_with_gaps = True
if options.overwrite_with_gaps and options.overwrite_with_gaps.lower(
) == 'false':
overwrite_with_gaps = False
# Finish parsing command line
# get index for mafs based on type
index = index_filename = None
# using specified uid for locally cached
if options.mafSourceType.lower() in ["cached"]:
index = maf_utilities.maf_index_by_uid(options.mafSource, mafIndexFile)
if index is None:
stop_err("The MAF source specified (%s) appears to be invalid." %
(options.mafSource))
elif options.mafSourceType.lower() in ["user"]:
# index maf for use here, need to remove index_file when finished
index, index_filename = maf_utilities.open_or_build_maf_index(
options.mafSource, options.mafIndex, species=[primary_species])
if index is None:
stop_err("Your MAF file appears to be malformed.")
else:
stop_err("Invalid MAF source type specified.")
# open output file
output = open(output_file, "w")
if options.geneBED:
region_enumerator = maf_utilities.line_enumerator(
open(interval_file, "r").readlines())
else:
region_enumerator = enumerate(
bx.intervals.io.NiceReaderWrapper(open(interval_file, 'r'),
chrom_col=chr_col,
start_col=start_col,
end_col=end_col,
strand_col=strand_col,
fix_strand=True,
return_header=False,
return_comments=False))
# Step through intervals
regions_extracted = 0
line_count = 0
for line_count, line in region_enumerator:
try:
if options.geneBED: # Process as Gene BED
try:
starts, ends, fields = maf_utilities.get_starts_ends_fields_from_gene_bed(
line)
# create spliced alignment object
alignment = maf_utilities.get_spliced_region_alignment(
index,
primary_species,
fields[0],
starts,
ends,
strand='+',
species=species,
mincols=mincols,
overwrite_with_gaps=overwrite_with_gaps)
primary_name = secondary_name = fields[3]
alignment_strand = fields[5]
except Exception, e:
print "Error loading exon positions from input line %i: %s" % (
line_count, e)
continue
else: # Process as standard intervals
try:
# create spliced alignment object
alignment = maf_utilities.get_region_alignment(
index,
primary_species,
line.chrom,
line.start,
line.end,
strand='+',
species=species,
mincols=mincols,
overwrite_with_gaps=overwrite_with_gaps)
primary_name = "%s(%s):%s-%s" % (line.chrom, line.strand,
line.start, line.end)
secondary_name = ""
alignment_strand = line.strand
except Exception, e:
print "Error loading region positions from input line %i: %s" % (
line_count, e)
continue
def __main__():
maf_source_type = sys.argv.pop( 1 )
input_maf_filename = sys.argv[1].strip()
input_interval_filename = sys.argv[2].strip()
output_filename = sys.argv[3].strip()
dbkey = sys.argv[4].strip()
try:
chr_col = int( sys.argv[5].strip() ) - 1
start_col = int( sys.argv[6].strip() ) - 1
end_col = int( sys.argv[7].strip() ) - 1
except:
print >>sys.stderr, "You appear to be missing metadata. You can specify your metadata by clicking on the pencil icon associated with your interval file."
sys.exit()
summary = sys.argv[8].strip()
if summary.lower() == "true": summary = True
else: summary = False
mafIndexFile = "%s/maf_index.loc" % sys.argv[9]
try:
maf_index_filename = sys.argv[10].strip()
except:
maf_index_filename = None
index = index_filename = None
if maf_source_type == "user":
#index maf for use here
index, index_filename = maf_utilities.open_or_build_maf_index( input_maf_filename, maf_index_filename, species = [dbkey] )
if index is None:
print >>sys.stderr, "Your MAF file appears to be malformed."
sys.exit()
elif maf_source_type == "cached":
#access existing indexes
index = maf_utilities.maf_index_by_uid( input_maf_filename, mafIndexFile )
if index is None:
print >> sys.stderr, "The MAF source specified (%s) appears to be invalid." % ( input_maf_filename )
sys.exit()
else:
print >>sys.stdout, 'Invalid source type specified: %s' % maf_source_type
sys.exit()
out = open(output_filename, 'w')
num_region = 0
species_summary = {}
total_length = 0
#loop through interval file
for num_region, region in enumerate( bx.intervals.io.NiceReaderWrapper( open( input_interval_filename, 'r' ), chrom_col = chr_col, start_col = start_col, end_col = end_col, fix_strand = True, return_header = False, return_comments = False ) ):
src = "%s.%s" % ( dbkey, region.chrom )
region_length = region.end - region.start
total_length += region_length
coverage = { dbkey: BitSet( region_length ) }
for block in maf_utilities.get_chopped_blocks_for_region( index, src, region, force_strand='+' ):
#make sure all species are known
for c in block.components:
spec = c.src.split( '.' )[0]
if spec not in coverage: coverage[spec] = BitSet( region_length )
start_offset, alignment = maf_utilities.reduce_block_by_primary_genome( block, dbkey, region.chrom, region.start )
for i in range( len( alignment[dbkey] ) ):
for spec, text in alignment.items():
if text[i] != '-':
coverage[spec].set( start_offset + i )
if summary:
#record summary
for key in coverage.keys():
if key not in species_summary: species_summary[key] = 0
species_summary[key] = species_summary[key] + coverage[key].count_range()
else:
#print coverage for interval
coverage_sum = coverage[dbkey].count_range()
out.write( "%s\t%s\t%s\t%s\n" % ( "\t".join( region.fields ), dbkey, coverage_sum, region_length - coverage_sum ) )
keys = coverage.keys()
keys.remove( dbkey )
keys.sort()
for key in keys:
coverage_sum = coverage[key].count_range()
out.write( "%s\t%s\t%s\t%s\n" % ( "\t".join( region.fields ), key, coverage_sum, region_length - coverage_sum ) )
if summary:
out.write( "#species\tnucleotides\tcoverage\n" )
for spec in species_summary:
out.write( "%s\t%s\t%.4f\n" % ( spec, species_summary[spec], float( species_summary[spec] ) / total_length ) )
out.close()
print "%i regions were processed with a total length of %i." % ( num_region, total_length )
maf_utilities.remove_temp_index_file( index_filename )
def __main__():
# Parse Command Line
options, args = doc_optparse.parse(__doc__)
mincols = 0
strand_col = -1
if options.dbkey:
primary_species = options.dbkey
else:
primary_species = None
if primary_species in [None, "?", "None"]:
stop_err("You must specify a proper build in order to extract alignments. You can specify your genome build by clicking on the pencil icon associated with your interval file.")
include_primary = True
secondary_species = maf_utilities.parse_species_option(options.species)
if secondary_species:
species = list(secondary_species) # make copy of species list
if primary_species in secondary_species:
secondary_species.remove(primary_species)
else:
include_primary = False
else:
species = None
if options.interval_file:
interval_file = options.interval_file
else:
stop_err("Input interval file has not been specified.")
if options.output_file:
output_file = options.output_file
else:
stop_err("Output file has not been specified.")
if not options.geneBED:
if options.chromCol:
chr_col = int(options.chromCol) - 1
else:
stop_err("Chromosome column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.startCol:
start_col = int(options.startCol) - 1
else:
stop_err("Start column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.endCol:
end_col = int(options.endCol) - 1
else:
stop_err("End column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.strandCol:
strand_col = int(options.strandCol) - 1
mafIndexFile = "%s/maf_index.loc" % options.mafIndexFileDir
overwrite_with_gaps = True
if options.overwrite_with_gaps and options.overwrite_with_gaps.lower() == 'false':
overwrite_with_gaps = False
# Finish parsing command line
# get index for mafs based on type
index = index_filename = None
# using specified uid for locally cached
if options.mafSourceType.lower() in ["cached"]:
index = maf_utilities.maf_index_by_uid(options.mafSource, mafIndexFile)
if index is None:
stop_err("The MAF source specified (%s) appears to be invalid." % (options.mafSource))
elif options.mafSourceType.lower() in ["user"]:
# index maf for use here, need to remove index_file when finished
index, index_filename = maf_utilities.open_or_build_maf_index(options.mafSource, options.mafIndex, species=[primary_species])
if index is None:
stop_err("Your MAF file appears to be malformed.")
else:
stop_err("Invalid MAF source type specified.")
# open output file
output = open(output_file, "w")
if options.geneBED:
region_enumerator = maf_utilities.line_enumerator(open(interval_file, "r").readlines())
else:
region_enumerator = enumerate(bx.intervals.io.NiceReaderWrapper(
open(interval_file, 'r'), chrom_col=chr_col, start_col=start_col,
end_col=end_col, strand_col=strand_col, fix_strand=True,
return_header=False, return_comments=False))
# Step through intervals
regions_extracted = 0
line_count = 0
for line_count, line in region_enumerator:
try:
if options.geneBED: # Process as Gene BED
try:
starts, ends, fields = maf_utilities.get_starts_ends_fields_from_gene_bed(line)
# create spliced alignment object
alignment = maf_utilities.get_spliced_region_alignment(
index, primary_species, fields[0], starts, ends,
strand='+', species=species, mincols=mincols,
overwrite_with_gaps=overwrite_with_gaps)
primary_name = secondary_name = fields[3]
alignment_strand = fields[5]
except Exception as e:
print("Error loading exon positions from input line %i: %s" % (line_count, e))
continue
else: # Process as standard intervals
try:
# create spliced alignment object
alignment = maf_utilities.get_region_alignment(
index, primary_species, line.chrom, line.start,
line.end, strand='+', species=species, mincols=mincols,
overwrite_with_gaps=overwrite_with_gaps)
primary_name = "%s(%s):%s-%s" % (line.chrom, line.strand, line.start, line.end)
secondary_name = ""
alignment_strand = line.strand
except Exception as e:
print("Error loading region positions from input line %i: %s" % (line_count, e))
continue
# Write alignment to output file
# Output primary species first, if requested
if include_primary:
output.write(">%s.%s\n" % (primary_species, primary_name))
if alignment_strand == "-":
output.write(alignment.get_sequence_reverse_complement(primary_species))
else:
output.write(alignment.get_sequence(primary_species))
output.write("\n")
# Output all remainging species
for spec in secondary_species or alignment.get_species_names(skip=primary_species):
if secondary_name:
output.write(">%s.%s\n" % (spec, secondary_name))
else:
output.write(">%s\n" % (spec))
if alignment_strand == "-":
output.write(alignment.get_sequence_reverse_complement(spec))
else:
output.write(alignment.get_sequence(spec))
output.write("\n")
output.write("\n")
regions_extracted += 1
except Exception as e:
print("Unexpected error from input line %i: %s" % (line_count, e))
continue
# close output file
output.close()
# remove index file if created during run
maf_utilities.remove_temp_index_file(index_filename)
# Print message about success for user
if regions_extracted > 0:
print("%i regions were processed successfully." % (regions_extracted))
else:
print("No regions were processed successfully.")
if line_count > 0 and options.geneBED:
print("This tool requires your input file to conform to the 12 column BED standard.")
def __main__():
index = index_filename = None
# Parse Command Line
options, args = doc_optparse.parse(__doc__)
if options.dbkey:
dbkey = options.dbkey
else:
dbkey = None
if dbkey in [None, "?"]:
maf_utilities.tool_fail(
"You must specify a proper build in order to extract alignments. You can specify your genome build by clicking on the pencil icon associated with your interval file."
)
species = maf_utilities.parse_species_option(options.species)
if options.chromCol:
chromCol = int(options.chromCol) - 1
else:
maf_utilities.tool_fail(
"Chromosome column not set, click the pencil icon in the history item to set the metadata attributes."
)
if options.startCol:
startCol = int(options.startCol) - 1
else:
maf_utilities.tool_fail(
"Start column not set, click the pencil icon in the history item to set the metadata attributes."
)
if options.endCol:
endCol = int(options.endCol) - 1
else:
maf_utilities.tool_fail(
"End column not set, click the pencil icon in the history item to set the metadata attributes."
)
if options.strandCol:
strandCol = int(options.strandCol) - 1
else:
strandCol = -1
if options.interval_file:
interval_file = options.interval_file
else:
maf_utilities.tool_fail("Input interval file has not been specified.")
if options.output_file:
output_file = options.output_file
else:
maf_utilities.tool_fail("Output file has not been specified.")
split_blocks_by_species = remove_all_gap_columns = False
if options.split_blocks_by_species and options.split_blocks_by_species == 'split_blocks_by_species':
split_blocks_by_species = True
if options.remove_all_gap_columns and options.remove_all_gap_columns == 'remove_all_gap_columns':
remove_all_gap_columns = True
else:
remove_all_gap_columns = True
# Finish parsing command line
# Open indexed access to MAFs
if options.mafType:
if options.indexLocation:
index = maf_utilities.maf_index_by_uid(options.mafType,
options.indexLocation)
else:
index = maf_utilities.maf_index_by_uid(options.mafType,
options.mafIndexFile)
if index is None:
maf_utilities.tool_fail(
"The MAF source specified (%s) appears to be invalid." %
(options.mafType))
elif options.mafFile:
index, index_filename = maf_utilities.open_or_build_maf_index(
options.mafFile, options.mafIndex, species=[dbkey])
if index is None:
maf_utilities.tool_fail("Your MAF file appears to be malformed.")
else:
maf_utilities.tool_fail(
"Desired source MAF type has not been specified.")
# Create MAF writter
out = bx.align.maf.Writer(open(output_file, "w"))
# Iterate over input regions
num_blocks = 0
num_regions = None
for num_regions, region in enumerate(
bx.intervals.io.NiceReaderWrapper(
open(interval_file),
chrom_col=chromCol,
start_col=startCol,
end_col=endCol,
strand_col=strandCol,
fix_strand=True,
return_header=False,
return_comments=False)): # noqa: B007
src = maf_utilities.src_merge(dbkey, region.chrom)
for block in index.get_as_iterator(src, region.start, region.end):
if split_blocks_by_species:
blocks = [
new_block for new_block in
maf_utilities.iter_blocks_split_by_species(block)
if maf_utilities.component_overlaps_region(
new_block.get_component_by_src_start(dbkey), region)
]
else:
blocks = [block]
for block in blocks:
block = maf_utilities.chop_block_by_region(block, src, region)
if block is not None:
if species is not None:
block = block.limit_to_species(species)
block = maf_utilities.orient_block_by_region(
block, src, region)
if remove_all_gap_columns:
block.remove_all_gap_columns()
out.write(block)
num_blocks += 1
# Close output MAF
out.close()
# remove index file if created during run
maf_utilities.remove_temp_index_file(index_filename)
if num_blocks:
print("%i MAF blocks extracted for %i regions." % (num_blocks,
(num_regions + 1)))
elif num_regions is not None:
print("No MAF blocks could be extracted for %i regions." %
(num_regions + 1))
else:
print("No valid regions have been provided.")
def __main__():
maf_source_type = sys.argv.pop(1)
input_maf_filename = sys.argv[1].strip()
input_interval_filename = sys.argv[2].strip()
output_filename = sys.argv[3].strip()
dbkey = sys.argv[4].strip()
try:
chr_col = int(sys.argv[5].strip()) - 1
start_col = int(sys.argv[6].strip()) - 1
end_col = int(sys.argv[7].strip()) - 1
except Exception:
print(
"You appear to be missing metadata. You can specify your metadata by clicking on the pencil icon associated with your interval file.",
file=sys.stderr)
sys.exit()
summary = sys.argv[8].strip()
if summary.lower() == "true":
summary = True
else:
summary = False
mafIndexFile = "%s/maf_index.loc" % sys.argv[9]
try:
maf_index_filename = sys.argv[10].strip()
except Exception:
maf_index_filename = None
index = index_filename = None
if maf_source_type == "user":
# index maf for use here
index, index_filename = maf_utilities.open_or_build_maf_index(
input_maf_filename, maf_index_filename, species=[dbkey])
if index is None:
print("Your MAF file appears to be malformed.", file=sys.stderr)
sys.exit()
elif maf_source_type == "cached":
# access existing indexes
index = maf_utilities.maf_index_by_uid(input_maf_filename,
mafIndexFile)
if index is None:
print("The MAF source specified (%s) appears to be invalid." %
(input_maf_filename),
file=sys.stderr)
sys.exit()
else:
print('Invalid source type specified: %s' % maf_source_type,
file=sys.stdout)
sys.exit()
out = open(output_filename, 'w')
num_region = None
num_bad_region = 0
species_summary = {}
total_length = 0
# loop through interval file
for num_region, region in enumerate(
bx.intervals.io.NiceReaderWrapper(
open(input_interval_filename, 'r'),
chrom_col=chr_col,
start_col=start_col,
end_col=end_col,
fix_strand=True,
return_header=False,
return_comments=False)): # noqa: B007
src = "%s.%s" % (dbkey, region.chrom)
region_length = region.end - region.start
if region_length < 1:
num_bad_region += 1
continue
total_length += region_length
coverage = {dbkey: BitSet(region_length)}
for block in index.get_as_iterator(src, region.start, region.end):
for spec in maf_utilities.get_species_in_block(block):
if spec not in coverage:
coverage[spec] = BitSet(region_length)
for block in maf_utilities.iter_blocks_split_by_species(block):
if maf_utilities.component_overlaps_region(
block.get_component_by_src(src), region):
# need to chop and orient the block
block = maf_utilities.orient_block_by_region(
maf_utilities.chop_block_by_region(block, src, region),
src,
region,
force_strand='+')
start_offset, alignment = maf_utilities.reduce_block_by_primary_genome(
block, dbkey, region.chrom, region.start)
for i in range(len(alignment[dbkey])):
for spec, text in alignment.items():
if text[i] != '-':
coverage[spec].set(start_offset + i)
if summary:
# record summary
for key in coverage.keys():
if key not in species_summary:
species_summary[key] = 0
species_summary[
key] = species_summary[key] + coverage[key].count_range()
else:
# print coverage for interval
coverage_sum = coverage[dbkey].count_range()
out.write("%s\t%s\t%s\t%s\n" %
("\t".join(region.fields), dbkey, coverage_sum,
region_length - coverage_sum))
keys = list(coverage.keys())
keys.remove(dbkey)
keys.sort()
for key in keys:
coverage_sum = coverage[key].count_range()
out.write("%s\t%s\t%s\t%s\n" %
("\t".join(region.fields), key, coverage_sum,
region_length - coverage_sum))
if summary:
out.write("#species\tnucleotides\tcoverage\n")
for spec in species_summary:
out.write("%s\t%s\t%.4f\n" %
(spec, species_summary[spec],
float(species_summary[spec]) / total_length))
out.close()
if num_region is not None:
print("%i regions were processed with a total length of %i." %
(num_region + 1, total_length))
if num_bad_region:
print("%i regions were invalid." % (num_bad_region))
maf_utilities.remove_temp_index_file(index_filename)
def __main__():
# Parse Command Line
options, args = doc_optparse.parse(__doc__)
mincols = 0
strand_col = -1
if options.dbkey:
primary_species = options.dbkey
else:
primary_species = None
if primary_species in [None, "?", "None"]:
stop_err(
"You must specify a proper build in order to extract alignments. You can specify your genome build by clicking on the pencil icon associated with your interval file."
)
include_primary = True
secondary_species = maf_utilities.parse_species_option(options.species)
if secondary_species:
species = list(secondary_species) # make copy of species list
if primary_species in secondary_species:
secondary_species.remove(primary_species)
else:
include_primary = False
else:
species = None
if options.interval_file:
interval_file = options.interval_file
else:
stop_err("Input interval file has not been specified.")
if options.output_file:
output_file = options.output_file
else:
stop_err("Output file has not been specified.")
if not options.geneBED:
if options.chromCol:
chr_col = int(options.chromCol) - 1
else:
stop_err(
"Chromosome column not set, click the pencil icon in the history item to set the metadata attributes."
)
if options.startCol:
start_col = int(options.startCol) - 1
else:
stop_err("Start column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.endCol:
end_col = int(options.endCol) - 1
else:
stop_err("End column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.strandCol:
strand_col = int(options.strandCol) - 1
mafIndexFile = "%s/maf_index.loc" % options.mafIndexFileDir
# Finish parsing command line
# get index for mafs based on type
index = index_filename = None
# using specified uid for locally cached
if options.mafSourceType.lower() in ["cached"]:
index = maf_utilities.maf_index_by_uid(options.mafSource, mafIndexFile)
if index is None:
stop_err("The MAF source specified (%s) appears to be invalid." % (options.mafSource))
elif options.mafSourceType.lower() in ["user"]:
# index maf for use here, need to remove index_file when finished
index, index_filename = maf_utilities.open_or_build_maf_index(
options.mafSource, options.mafIndex, species=[primary_species]
)
if index is None:
stop_err("Your MAF file appears to be malformed.")
else:
stop_err("Invalid MAF source type specified.")
# open output file
output = open(output_file, "w")
if options.geneBED:
region_enumerator = maf_utilities.line_enumerator(open(interval_file, "r").readlines())
else:
region_enumerator = enumerate(
bx.intervals.io.NiceReaderWrapper(
open(interval_file, "r"),
chrom_col=chr_col,
start_col=start_col,
end_col=end_col,
strand_col=strand_col,
fix_strand=True,
return_header=False,
return_comments=False,
)
)
# Step through intervals
regions_extracted = 0
line_count = 0
for line_count, line in region_enumerator:
try:
if options.geneBED: # Process as Gene BED
try:
starts, ends, fields = maf_utilities.get_starts_ends_fields_from_gene_bed(line)
# create spliced alignment object
alignment = maf_utilities.get_spliced_region_alignment(
index, primary_species, fields[0], starts, ends, strand="+", species=species, mincols=mincols
)
primary_name = secondary_name = fields[3]
alignment_strand = fields[5]
except Exception, e:
print "Error loading exon positions from input line %i: %s" % (line_count, e)
continue
else: # Process as standard intervals
try:
# create spliced alignment object
alignment = maf_utilities.get_region_alignment(
index,
primary_species,
line.chrom,
line.start,
line.end,
strand="+",
species=species,
mincols=mincols,
)
primary_name = "%s(%s):%s-%s" % (line.chrom, line.strand, line.start, line.end)
secondary_name = ""
alignment_strand = line.strand
except Exception, e:
print "Error loading region positions from input line %i: %s" % (line_count, e)
continue
def __main__():
index = index_filename = None
# Parse Command Line
options, args = doc_optparse.parse(__doc__)
if options.dbkey:
dbkey = options.dbkey
else:
dbkey = None
if dbkey in [None, "?"]:
maf_utilities.tool_fail("You must specify a proper build in order to extract alignments. You can specify your genome build by clicking on the pencil icon associated with your interval file.")
species = maf_utilities.parse_species_option(options.species)
if options.chromCol:
chromCol = int(options.chromCol) - 1
else:
maf_utilities.tool_fail("Chromosome column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.startCol:
startCol = int(options.startCol) - 1
else:
maf_utilities.tool_fail("Start column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.endCol:
endCol = int(options.endCol) - 1
else:
maf_utilities.tool_fail("End column not set, click the pencil icon in the history item to set the metadata attributes.")
if options.strandCol:
strandCol = int(options.strandCol) - 1
else:
strandCol = -1
if options.interval_file:
interval_file = options.interval_file
else:
maf_utilities.tool_fail("Input interval file has not been specified.")
if options.output_file:
output_file = options.output_file
else:
maf_utilities.tool_fail("Output file has not been specified.")
split_blocks_by_species = remove_all_gap_columns = False
if options.split_blocks_by_species and options.split_blocks_by_species == 'split_blocks_by_species':
split_blocks_by_species = True
if options.remove_all_gap_columns and options.remove_all_gap_columns == 'remove_all_gap_columns':
remove_all_gap_columns = True
else:
remove_all_gap_columns = True
# Finish parsing command line
# Open indexed access to MAFs
if options.mafType:
if options.indexLocation:
index = maf_utilities.maf_index_by_uid(options.mafType, options.indexLocation)
else:
index = maf_utilities.maf_index_by_uid(options.mafType, options.mafIndexFile)
if index is None:
maf_utilities.tool_fail("The MAF source specified (%s) appears to be invalid." % (options.mafType))
elif options.mafFile:
index, index_filename = maf_utilities.open_or_build_maf_index(options.mafFile, options.mafIndex, species=[dbkey])
if index is None:
maf_utilities.tool_fail("Your MAF file appears to be malformed.")
else:
maf_utilities.tool_fail("Desired source MAF type has not been specified.")
# Create MAF writter
out = bx.align.maf.Writer(open(output_file, "w"))
# Iterate over input regions
num_blocks = 0
num_regions = None
for num_regions, region in enumerate(bx.intervals.io.NiceReaderWrapper(open(interval_file, 'r'), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False, return_comments=False)):
src = maf_utilities.src_merge(dbkey, region.chrom)
for block in index.get_as_iterator(src, region.start, region.end):
if split_blocks_by_species:
blocks = [new_block for new_block in maf_utilities.iter_blocks_split_by_species(block) if maf_utilities.component_overlaps_region(new_block.get_component_by_src_start(dbkey), region)]
else:
blocks = [block]
for block in blocks:
block = maf_utilities.chop_block_by_region(block, src, region)
if block is not None:
if species is not None:
block = block.limit_to_species(species)
block = maf_utilities.orient_block_by_region(block, src, region)
if remove_all_gap_columns:
block.remove_all_gap_columns()
out.write(block)
num_blocks += 1
# Close output MAF
out.close()
# remove index file if created during run
maf_utilities.remove_temp_index_file(index_filename)
if num_blocks:
print("%i MAF blocks extracted for %i regions." % (num_blocks, (num_regions + 1)))
elif num_regions is not None:
print("No MAF blocks could be extracted for %i regions." % (num_regions + 1))
else:
print("No valid regions have been provided.")
def __main__():
index = index_filename = None
mincols = 0
#Parse Command Line
options, args = doc_optparse.parse( __doc__ )
if options.dbkey: dbkey = options.dbkey
else: dbkey = None
if dbkey in [None, "?"]:
print >>sys.stderr, "You must specify a proper build in order to extract alignments. You can specify your genome build by clicking on the pencil icon associated with your interval file."
sys.exit()
species = maf_utilities.parse_species_option( options.species )
if options.chromCol: chromCol = int( options.chromCol ) - 1
else:
print >>sys.stderr, "Chromosome column not set, click the pencil icon in the history item to set the metadata attributes."
sys.exit()
if options.startCol: startCol = int( options.startCol ) - 1
else:
print >>sys.stderr, "Start column not set, click the pencil icon in the history item to set the metadata attributes."
sys.exit()
if options.endCol: endCol = int( options.endCol ) - 1
else:
print >>sys.stderr, "End column not set, click the pencil icon in the history item to set the metadata attributes."
sys.exit()
if options.strandCol: strandCol = int( options.strandCol ) - 1
else:
strandCol = -1
if options.interval_file: interval_file = options.interval_file
else:
print >>sys.stderr, "Input interval file has not been specified."
sys.exit()
if options.output_file: output_file = options.output_file
else:
print >>sys.stderr, "Output file has not been specified."
sys.exit()
#Finish parsing command line
#Open indexed access to MAFs
if options.mafType:
if options.indexLocation:
index = maf_utilities.maf_index_by_uid( options.mafType, options.indexLocation )
else:
index = maf_utilities.maf_index_by_uid( options.mafType, options.mafIndexFile )
if index is None:
print >> sys.stderr, "The MAF source specified (%s) appears to be invalid." % ( options.mafType )
sys.exit()
elif options.mafFile:
index, index_filename = maf_utilities.open_or_build_maf_index( options.mafFile, options.mafIndex, species = [dbkey] )
if index is None:
print >> sys.stderr, "Your MAF file appears to be malformed."
sys.exit()
else:
print >>sys.stderr, "Desired source MAF type has not been specified."
sys.exit()
#Create MAF writter
out = bx.align.maf.Writer( open(output_file, "w") )
#Iterate over input regions
num_blocks = 0
num_regions = None
for num_regions, region in enumerate( bx.intervals.io.NiceReaderWrapper( open( interval_file, 'r' ), chrom_col = chromCol, start_col = startCol, end_col = endCol, strand_col = strandCol, fix_strand = True, return_header = False, return_comments = False ) ):
src = "%s.%s" % ( dbkey, region.chrom )
for block in maf_utilities.get_chopped_blocks_for_region( index, src, region, species, mincols ):
out.write( block )
num_blocks += 1
#Close output MAF
out.close()
#remove index file if created during run
maf_utilities.remove_temp_index_file( index_filename )
if num_blocks:
print "%i MAF blocks extracted for %i regions." % ( num_blocks, ( num_regions + 1 ) )
elif num_regions is not None:
print "No MAF blocks could be extracted for %i regions." % ( num_regions + 1 )
else:
print "No valid regions have been provided."
