def set_meta( self, dataset, **kwd ):
Text.set_meta(self, dataset, **kwd )
data_dir = dataset.extra_files_path
## search data_dir/genome_version for files
regulation_pattern = 'regulation_(.+).bin'
# annotation files that are included in snpEff by a flag
annotations_dict = {'nextProt.bin' : '-nextprot','motif.bin': '-motif'}
regulations = []
annotations = []
if data_dir and os.path.isdir(data_dir):
for root, dirs, files in os.walk(data_dir):
for fname in files:
if fname.startswith('snpEffectPredictor'):
# if snpEffectPredictor.bin download succeeded
genome_version = os.path.basename(root)
dataset.metadata.genome_version = genome_version
else:
m = re.match(regulation_pattern,fname)
if m:
name = m.groups()[0]
regulations.append(name)
elif fname in annotations_dict:
value = annotations_dict[fname]
name = value.lstrip('-')
annotations.append(name)
dataset.metadata.regulation = regulations
dataset.metadata.annotation = annotations
def __init__(self, **kwd):
Text.__init__(self, **kwd)
self.add_composite_file(
"%s.grp", description="Group File", substitute_name_with_metadata="reference_name", is_binary=False
)
self.add_composite_file(
"%s.ti", description="", substitute_name_with_metadata="reference_name", is_binary=False
)
def __init__(self, **kwd):
Text.__init__(self, **kwd)
self.add_composite_file('%s.gz',
description='dbNSFP bgzip',
substitute_name_with_metadata='reference_name',
is_binary=True)
self.add_composite_file('%s.gz.tbi',
description='Tabix Index File',
substitute_name_with_metadata='reference_name',
is_binary=True)
def __init__(self, **kwd):
Text.__init__(self, **kwd)
self.add_composite_file('%s.grp',
description='Group File',
substitute_name_with_metadata='reference_name',
is_binary=False)
self.add_composite_file('%s.ti',
description='',
substitute_name_with_metadata='reference_name',
is_binary=False)
def set_meta(self, dataset, **kwd):
Text.set_meta(self, dataset, **kwd)
data_dir = dataset.extra_files_path
# search data_dir/genome_version for files
regulation_pattern = 'regulation_(.+).bin'
# annotation files that are included in snpEff by a flag
annotations_dict = {
'nextProt.bin': '-nextprot',
'motif.bin': '-motif',
'interactions.bin': '-interaction'
}
regulations = []
annotations = []
genome_version = None
snpeff_version = None
if data_dir and os.path.isdir(data_dir):
for root, dirs, files in os.walk(data_dir):
for fname in files:
if fname.startswith('snpEffectPredictor'):
# if snpEffectPredictor.bin download succeeded
genome_version = os.path.basename(root)
dataset.metadata.genome_version = genome_version
# read the first line of the gzipped snpEffectPredictor.bin file to get the SnpEff version
snpeff_version = self.getSnpeffVersionFromFile(
os.path.join(root, fname))
if snpeff_version:
dataset.metadata.snpeff_version = snpeff_version
else:
m = re.match(regulation_pattern, fname)
if m:
name = m.groups()[0]
regulations.append(name)
elif fname in annotations_dict:
value = annotations_dict[fname]
name = value.lstrip('-')
annotations.append(name)
dataset.metadata.regulation = regulations
dataset.metadata.annotation = annotations
try:
with open(dataset.file_name, 'w') as fh:
fh.write(
"%s\n" %
genome_version if genome_version else 'Genome unknown')
fh.write("%s\n" % snpeff_version
if snpeff_version else 'SnpEff version unknown')
if annotations:
fh.write("annotations: %s\n" % ','.join(annotations))
if regulations:
fh.write("regulations: %s\n" % ','.join(regulations))
except Exception:
pass
def merge(split_files, output_file):
"""Merging multiple MIRA files is non-trivial and may not be possible..."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no MIRA, %r, to merge into %s" \
% (split_files, output_file))
raise NotImplementedError("Merging MIRA Assembly Files has not been implemented")
def set_meta( self, dataset, **kwd ):
Text.set_meta(self, dataset, **kwd )
data_dir = dataset.extra_files_path
# search data_dir/genome_version for files
regulation_pattern = 'regulation_(.+).bin'
# annotation files that are included in snpEff by a flag
annotations_dict = {'nextProt.bin' : '-nextprot', 'motif.bin': '-motif'}
regulations = []
annotations = []
genome_version = None
snpeff_version = None
if data_dir and os.path.isdir(data_dir):
for root, dirs, files in os.walk(data_dir):
for fname in files:
if fname.startswith('snpEffectPredictor'):
# if snpEffectPredictor.bin download succeeded
genome_version = os.path.basename(root)
dataset.metadata.genome_version = genome_version
# read the first line of the gzipped snpEffectPredictor.bin file to get the SnpEff version
snpeff_version = self.getSnpeffVersionFromFile(os.path.join(root, fname))
if snpeff_version:
dataset.metadata.snpeff_version = snpeff_version
else:
m = re.match(regulation_pattern, fname)
if m:
name = m.groups()[0]
regulations.append(name)
elif fname in annotations_dict:
value = annotations_dict[fname]
name = value.lstrip('-')
annotations.append(name)
dataset.metadata.regulation = regulations
dataset.metadata.annotation = annotations
try:
fh = file(dataset.file_name, 'w')
fh.write("%s\n" % genome_version if genome_version else 'Genome unknown')
fh.write("%s\n" % snpeff_version if snpeff_version else 'SnpEff version unknown')
if annotations:
fh.write("annotations: %s\n" % ','.join(annotations))
if regulations:
fh.write("regulations: %s\n" % ','.join(regulations))
fh.close()
except:
pass
def merge(split_files, output_file):
"""Merging multiple MIRA files is non-trivial and may not be possible..."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no MIRA, %r, to merge into %s" \
% (split_files, output_file))
raise NotImplementedError(
"Merging MIRA Assembly Files has not been implemented")
def set_meta(self, dataset, **kwd):
Text.set_meta(self, dataset, **kwd)
data_dir = dataset.extra_files_path
## search data_dir/genome_version for files
regulation_pattern = "regulation_(.+).bin"
# annotation files that are included in snpEff by a flag
annotations_dict = {"nextProt.bin": "-nextprot", "motif.bin": "-motif"}
regulations = []
annotations = []
if data_dir and os.path.isdir(data_dir):
for root, dirs, files in os.walk(data_dir):
for fname in files:
if fname.startswith("snpEffectPredictor"):
# if snpEffectPredictor.bin download succeeded
genome_version = os.path.basename(root)
dataset.metadata.genome_version = genome_version
else:
m = re.match(regulation_pattern, fname)
if m:
name = m.groups()[0]
regulations.append(name)
elif fname in annotations_dict:
value = annotations_dict[fname]
name = value.lstrip("-")
annotations.append(name)
dataset.metadata.regulation = regulations
dataset.metadata.annotation = annotations
try:
fh = file(dataset.file_name, "w")
fh.write("%s\n" % genome_version)
if annotations:
fh.write("annotations: %s\n" % ",".join(annotations))
if regulations:
fh.write("regulations: %s\n" % ",".join(regulations))
fh.close()
except:
pass
def merge(split_files, output_file):
"""
Merging fps files requires merging the header manually.
We take the header from the first file.
"""
if len(split_files) == 1:
# For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("No fps files given, %r, to merge into %s" %
(split_files, output_file))
with open(output_file, "w") as out:
first = True
for filename in split_files:
with open(filename) as handle:
for line in handle:
if line.startswith('#'):
if first:
out.write(line)
else:
# line is no header and not a comment, we assume the first header is written to out and we set 'first' to False
first = False
out.write(line)
def merge(split_files, output_file):
"""
Merging CML files.
"""
if len(split_files) == 1:
# For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no CML files, %r, to merge into %s" %
(split_files, output_file))
with open(output_file, "w") as out:
for filename in split_files:
with open(filename) as handle:
header = handle.readline()
if not header:
raise ValueError("CML file %s was empty" % filename)
if not header.lstrip().startswith('<?xml version="1.0"?>'):
out.write(header)
raise ValueError("%s is not a valid XML file!" %
filename)
line = handle.readline()
header += line
if not line.lstrip().startswith(
'<cml xmlns="http://www.xml-cml.org/schema'):
out.write(header)
raise ValueError("%s is not a CML file!" % filename)
molecule_found = False
for line in handle.readlines():
# We found two required header lines, the next line should start with <molecule >
if line.lstrip().startswith('</cml>'):
continue
if line.lstrip().startswith('<molecule'):
molecule_found = True
if molecule_found:
out.write(line)
out.write("</cml>\n")
def init_meta(self, dataset, copy_from=None):
Text.init_meta(self, dataset, copy_from=copy_from)
def merge(split_files, output_file):
"""Merging multiple XML files is non-trivial and must be done in subclasses."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no BLAST XML files, %r, to merge into %s" \
% (split_files, output_file))
out = open(output_file, "w")
h = None
for f in split_files:
if not os.path.isfile(f):
log.warning("BLAST XML file %s missing, retry in 1s..." % f)
sleep(1)
if not os.path.isfile(f):
log.error("BLAST XML file %s missing" % f)
raise ValueError("BLAST XML file %s missing" % f)
h = open(f)
header = h.readline()
if not header:
out.close()
h.close()
#Retry, could be transient error with networked file system...
log.warning("BLAST XML file %s empty, retry in 1s..." % f)
sleep(1)
h = open(f)
header = h.readline()
if not header:
log.error("BLAST XML file %s was empty" % f)
raise ValueError("BLAST XML file %s was empty" % f)
if header.strip() != '<?xml version="1.0"?>':
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not an XML file!" % f)
line = h.readline()
header += line
if line.strip() not in [
'<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">',
'<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "NCBI_BlastOutput.dtd">'
]:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file!" % f)
while True:
line = h.readline()
if not line:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("BLAST XML file %s ended prematurely" % f)
header += line
if "<Iteration>" in line:
break
if len(header) > 10000:
#Something has gone wrong, don't load too much into memory!
#Write what we have to the merged file for diagnostics
out.write(header)
out.close()
h.close()
raise ValueError(
"BLAST XML file %s has too long a header!" % f)
if "<BlastOutput>" not in header:
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file:\n%s\n..." %
(f, header))
if f == split_files[0]:
out.write(header)
old_header = header
elif old_header[:300] != header[:300]:
#Enough to check <BlastOutput_program> and <BlastOutput_version> match
out.close()
h.close()
raise ValueError("BLAST XML headers don't match for %s and %s - have:\n%s\n...\n\nAnd:\n%s\n...\n" \
% (split_files[0], f, old_header[:300], header[:300]))
else:
out.write(" <Iteration>\n")
for line in h:
if "</BlastOutput_iterations>" in line:
break
#TODO - Increment <Iteration_iter-num> and if required automatic query names
#like <Iteration_query-ID>Query_3</Iteration_query-ID> to be increasing?
out.write(line)
h.close()
out.write(" </BlastOutput_iterations>\n")
out.write("</BlastOutput>\n")
out.close()
def __init__(self, **kwd):
Text.__init__(self, **kwd)
self.max_lines = 10
def __init__( self, **kwd ):
Text.__init__( self, **kwd )
self.add_composite_file( '%s.grp', description = 'Group File', substitute_name_with_metadata = 'reference_name', is_binary = False )
self.add_composite_file( '%s.ti', description = '', substitute_name_with_metadata = 'reference_name', is_binary = False )
def init_meta( self, dataset, copy_from=None ):
Text.init_meta( self, dataset, copy_from=copy_from )
def __init__( self, **kwd ):
Text.__init__( self, **kwd )
def __init__(self, **kwd):
Text.__init__(self, **kwd)
self.max_lines = 10
def merge(split_files, output_file):
"""Merging multiple XML files is non-trivial and must be done in subclasses."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no BLAST XML files, %r, to merge into %s" \
% (split_files, output_file))
out = open(output_file, "w")
h = None
for f in split_files:
if not os.path.isfile(f):
log.warning("BLAST XML file %s missing, retry in 1s..." % f)
sleep(1)
if not os.path.isfile(f):
log.error("BLAST XML file %s missing" % f)
raise ValueError("BLAST XML file %s missing" % f)
h = open(f)
body = False
header = h.readline()
if not header:
out.close()
h.close()
#Retry, could be transient error with networked file system...
log.warning("BLAST XML file %s empty, retry in 1s..." % f)
sleep(1)
h = open(f)
header = h.readline()
if not header:
log.error("BLAST XML file %s was empty" % f)
raise ValueError("BLAST XML file %s was empty" % f)
if header.strip() != '<?xml version="1.0"?>':
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not an XML file!" % f)
line = h.readline()
header += line
if line.strip() not in ['<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">',
'<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "NCBI_BlastOutput.dtd">']:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file!" % f)
while True:
line = h.readline()
if not line:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("BLAST XML file %s ended prematurely" % f)
header += line
if "<Iteration>" in line:
break
if len(header) > 10000:
#Something has gone wrong, don't load too much into memory!
#Write what we have to the merged file for diagnostics
out.write(header)
out.close()
h.close()
raise ValueError("BLAST XML file %s has too long a header!" % f)
if "<BlastOutput>" not in header:
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file:\n%s\n..." % (f, header))
if f == split_files[0]:
out.write(header)
old_header = header
elif old_header[:300] != header[:300]:
#Enough to check <BlastOutput_program> and <BlastOutput_version> match
out.close()
h.close()
raise ValueError("BLAST XML headers don't match for %s and %s - have:\n%s\n...\n\nAnd:\n%s\n...\n" \
% (split_files[0], f, old_header[:300], header[:300]))
else:
out.write(" <Iteration>\n")
for line in h:
if "</BlastOutput_iterations>" in line:
break
#TODO - Increment <Iteration_iter-num> and if required automatic query names
#like <Iteration_query-ID>Query_3</Iteration_query-ID> to be increasing?
out.write(line)
h.close()
out.write(" </BlastOutput_iterations>\n")
out.write("</BlastOutput>\n")
out.close()
def __init__( self, **kwd ):
Text.__init__( self, **kwd )
self.add_composite_file( '%s.gz', description='dbNSFP bgzip', substitute_name_with_metadata='reference_name', is_binary=True )
self.add_composite_file( '%s.gz.tbi', description='Tabix Index File', substitute_name_with_metadata='reference_name', is_binary=True )
def __init__(self, **kwd):
Text.__init__(self, **kwd)
