def __main__():
try:
species = maf_utilities.parse_species_option(sys.argv[1])
except Exception as e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
try:
input_filename = sys.argv[2]
except Exception as e:
maf_utilities.tool_fail("Error reading MAF filename: %s" % e)
try:
file_out = open(sys.argv[3], 'w')
except Exception as e:
maf_utilities.tool_fail("Error opening file for output: %s" % e)
if species:
print "Restricted to species: %s" % ', '.join(species)
else:
print "Not restricted to species."
if not species:
try:
species = maf_utilities.get_species_in_maf(input_filename)
except Exception as e:
maf_utilities.tool_fail(
"Error determining species in input MAF: %s" % e)
for spec in species:
file_out.write(">" + spec + "\n")
try:
for start_block in maf.Reader(open(input_filename, 'r')):
for block in maf_utilities.iter_blocks_split_by_species(
start_block):
block.remove_all_gap_columns() # remove extra gaps
component = block.get_component_by_src_start(
spec
) # blocks only have one occurrence of a particular species, so this is safe
if component:
file_out.write(component.text)
else:
file_out.write("-" * block.text_size)
except Exception as e:
maf_utilities.tool_fail(
"Your MAF file appears to be malformed: %s" % e)
file_out.write("\n")
file_out.close()
def __main__():
try:
species = maf_utilities.parse_species_option(sys.argv[1])
except Exception as e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
try:
input_filename = sys.argv[2]
except Exception as e:
maf_utilities.tool_fail("Error reading MAF filename: %s" % e)
try:
file_out = open(sys.argv[3], 'w')
except Exception as e:
maf_utilities.tool_fail("Error opening file for output: %s" % e)
if species:
print("Restricted to species: %s" % ', '.join(species))
else:
print("Not restricted to species.")
if not species:
try:
species = maf_utilities.get_species_in_maf(input_filename)
except Exception as e:
maf_utilities.tool_fail("Error determining species in input MAF: %s" % e)
for spec in species:
file_out.write(">" + spec + "\n")
try:
for start_block in maf.Reader(open(input_filename, 'r')):
for block in maf_utilities.iter_blocks_split_by_species(start_block):
block.remove_all_gap_columns() # remove extra gaps
component = block.get_component_by_src_start(spec) # blocks only have one occurrence of a particular species, so this is safe
if component:
file_out.write(component.text)
else:
file_out.write("-" * block.text_size)
except Exception as e:
maf_utilities.tool_fail("Your MAF file appears to be malformed: %s" % e)
file_out.write("\n")
file_out.close()
def __main__():
try:
maf_reader = maf.Reader( open( sys.argv[1] ) )
except Exception as e:
maf_utilities.tool_fail( "Error opening MAF: %s" % e )
try:
out = maf.Writer( open( sys.argv[2], "w") )
except Exception as e:
maf_utilities.tool_fail( "Error opening file for output: %s" % e )
try:
collapse_columns = string_as_bool( sys.argv[3] )
except Exception as e:
maf_utilities.tool_fail( "Error determining collapse columns value: %s" % e )
start_count = 0
end_count = 0
for start_count, start_block in enumerate( maf_reader ):
for block in maf_utilities.iter_blocks_split_by_species( start_block ):
if collapse_columns:
block.remove_all_gap_columns()
out.write( block )
end_count += 1
out.close()
if end_count:
print "%i alignment blocks created from %i original blocks." % ( end_count, start_count + 1 )
else:
print "No alignment blocks were created."
def __main__():
try:
maf_reader = maf.Reader(open(sys.argv[1]))
except Exception as e:
maf_utilities.tool_fail("Error opening input MAF: %s" % e)
try:
file_out = open(sys.argv[2], 'w')
except Exception as e:
maf_utilities.tool_fail("Error opening file for output: %s" % e)
try:
species = maf_utilities.parse_species_option(sys.argv[3])
if species:
num_species = len(species)
else:
num_species = 0
except Exception as e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
try:
partial = sys.argv[4]
except Exception as e:
maf_utilities.tool_fail("Error determining keep partial value: %s" % e)
if species:
print("Restricted to species: %s" % ', '.join(species))
else:
print("Not restricted to species.")
for block_num, block in enumerate(maf_reader):
if species:
block = block.limit_to_species(species)
if len(maf_utilities.get_species_in_block(
block)) < num_species and partial == "partial_disallowed":
continue
spec_counts = {}
for component in block.components:
spec, chrom = maf_utilities.src_split(component.src)
if spec not in spec_counts:
spec_counts[spec] = 0
else:
spec_counts[spec] += 1
file_out.write("%s\n" % maf_utilities.get_fasta_header(
component, {
'block_index': block_num,
'species': spec,
'sequence_index': spec_counts[spec]
},
suffix="%s_%i_%i" % (spec, block_num, spec_counts[spec])))
file_out.write("%s\n" % component.text)
file_out.write("\n")
file_out.close()
def __main__():
try:
maf_reader = maf.Reader(open(sys.argv[1]))
except Exception as e:
maf_utilities.tool_fail("Error opening input MAF: %s" % e)
try:
file_out = open(sys.argv[2], 'w')
except Exception as e:
maf_utilities.tool_fail("Error opening file for output: %s" % e)
try:
species = maf_utilities.parse_species_option(sys.argv[3])
if species:
num_species = len(species)
else:
num_species = 0
except Exception as e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
try:
partial = sys.argv[4]
except Exception as e:
maf_utilities.tool_fail("Error determining keep partial value: %s" % e)
if species:
print("Restricted to species: %s" % ', '.join(species))
else:
print("Not restricted to species.")
for block_num, block in enumerate(maf_reader):
if species:
block = block.limit_to_species(species)
if len(maf_utilities.get_species_in_block(block)) < num_species and partial == "partial_disallowed":
continue
spec_counts = {}
for component in block.components:
spec, chrom = maf_utilities.src_split(component.src)
if spec not in spec_counts:
spec_counts[spec] = 0
else:
spec_counts[spec] += 1
d = OrderedDict([('block_index', block_num), ('species', spec), ('sequence_index', spec_counts[spec])])
file_out.write("%s\n" % maf_utilities.get_fasta_header(component, d, suffix="%s_%i_%i" % (spec, block_num, spec_counts[spec])))
file_out.write("%s\n" % component.text)
file_out.write("\n")
file_out.close()
def __main__():
try:
species = maf_utilities.parse_species_option(sys.argv[1])
except Exception, e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
pkg_resources.require("bx-python")
from bx.align import maf
from galaxy.tools.util import maf_utilities
assert sys.version_info[:2] >= (2, 4)
def __main__():
try:
species = maf_utilities.parse_species_option(sys.argv[1])
except Exception, e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
try:
input_filename = sys.argv[2]
except Exception, e:
maf_utilities.tool_fail("Error reading MAF filename: %s" % e)
try:
file_out = open(sys.argv[3], "w")
except Exception, e:
maf_utilities.tool_fail("Error opening file for output: %s" % e)
if species:
print "Restricted to species: %s" % ", ".join(species)
else:
print "Not restricted to species."
if not species:
try:
species = maf_utilities.get_species_in_maf(input_filename)
except Exception, e:
maf_utilities.tool_fail("Error determining species in input MAF: %s" % e)
def __main__():
try:
species = maf_utilities.parse_species_option(sys.argv[1])
except Exception, e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
pkg_resources.require("bx-python")
from bx.align import maf
from galaxy.tools.util import maf_utilities
assert sys.version_info[:2] >= (2, 4)
def __main__():
try:
species = maf_utilities.parse_species_option(sys.argv[1])
except Exception, e:
maf_utilities.tool_fail("Error determining species value: %s" % e)
try:
input_filename = sys.argv[2]
except Exception, e:
maf_utilities.tool_fail("Error reading MAF filename: %s" % e)
try:
file_out = open(sys.argv[3], 'w')
except Exception, e:
maf_utilities.tool_fail("Error opening file for output: %s" % e)
if species:
print "Restricted to species: %s" % ', '.join(species)
else:
print "Not restricted to species."
if not species:
try:
species = maf_utilities.get_species_in_maf(input_filename)
except Exception, e:
maf_utilities.tool_fail(
def __main__():
try:
maf_reader = maf.Reader( open( sys.argv[1] ) )
except Exception, e:
maf_utilities.tool_fail( "Error opening MAF: %s" % e )
from bx.align import maf
from galaxy.tools.util import maf_utilities
from galaxy.util import string_as_bool
def __main__():
try:
maf_reader = maf.Reader( open( sys.argv[1] ) )
except Exception, e:
maf_utilities.tool_fail( "Error opening MAF: %s" % e )
try:
out = maf.Writer( open( sys.argv[2], "w") )
except Exception, e:
maf_utilities.tool_fail( "Error opening file for output: %s" % e )
try:
collapse_columns = string_as_bool( sys.argv[3] )
except Exception, e:
maf_utilities.tool_fail( "Error determining collapse columns value: %s" % e )
start_count = 0
end_count = 0
for start_count, start_block in enumerate( maf_reader ):
for block in maf_utilities.iter_blocks_split_by_species( start_block ):
if collapse_columns:
block.remove_all_gap_columns()
out.write( block )
end_count += 1
out.close()
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__():
try:
maf_reader = maf.Reader( open( sys.argv[1] ) )
except Exception, e:
maf_utilities.tool_fail( "Error opening MAF: %s" % e )
import pkg_resources; pkg_resources.require( "bx-python" )
from bx.align import maf
from galaxy.tools.util import maf_utilities
from galaxy.util import string_as_bool
assert sys.version_info[:2] >= ( 2, 4 )
def __main__():
try:
maf_reader = maf.Reader( open( sys.argv[1] ) )
except Exception, e:
maf_utilities.tool_fail( "Error opening MAF: %s" % e )
try:
out = maf.Writer( open( sys.argv[2], "w") )
except Exception, e:
maf_utilities.tool_fail( "Error opening file for output: %s" % e )
try:
collapse_columns = string_as_bool( sys.argv[3] )
except Exception, e:
maf_utilities.tool_fail( "Error determining collapse columns value: %s" % e )
start_count = 0
end_count = 0
for start_count, start_block in enumerate( maf_reader ):
for block in maf_utilities.iter_blocks_split_by_species( start_block ):
if collapse_columns:
block.remove_all_gap_columns()
out.write( block )
end_count += 1
out.close()
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.")
from galaxy import eggs
import pkg_resources; pkg_resources.require( "bx-python" )
from bx.align import maf
from galaxy.tools.util import maf_utilities
assert sys.version_info[:2] >= ( 2, 4 )
def __main__():
try:
maf_reader = maf.Reader( open( sys.argv[1] ) )
except Exception, e:
maf_utilities.tool_fail( "Error opening input MAF: %s" % e )
try:
file_out = open( sys.argv[2], 'w' )
except Exception, e:
maf_utilities.tool_fail( "Error opening file for output: %s" % e )
try:
species = maf_utilities.parse_species_option( sys.argv[3] )
if species:
num_species = len( species )
else:
num_species = 0
except Exception, e:
maf_utilities.tool_fail( "Error determining species value: %s" % e )
try:
partial = sys.argv[4]
except Exception, e:
maf_utilities.tool_fail( "Error determining keep partial value: %s" % e )
if species:
print "Restricted to species: %s" % ', '.join( species )