def download(self):
if not self.has_local:
raise NameError('A local SCOP database directory must be defined.')
Path.mkdir(self.local)
urllib.urlretrieve(SCOPftp['desc'], self._desc)
urllib.urlretrieve(SCOPftp['rel'], self._rel)
return True
def download(self):
if not self.has_local:
raise NameError('A local GO database directory must be defined.')
Path.mkdir(self.local)
destination = os.path.join(self.local, self._gfile)
urllib.urlretrieve(GOftp['source'], destination)
self._process()
return True
def download(self):
if not self.has_local:
raise NameError('A local drugBank database directory must be defined.')
Path.mkdir(self.local)
here = os.getcwd()
os.chdir(self.local)
os.system("svn export {0}".format(PDBTMftp['svn']))
self._process()
return True
def download(self):
if not self.has_local:
raise NameError(
'A local Enzyme database directory must be defined.')
Path.mkdir(self.local)
urllib.urlretrieve(Enzymeftp['dat'], self._dfile)
urllib.urlretrieve(Enzymeftp['cls'], self._cfile)
self._process()
return True
def download(self):
if not self.has_local:
raise NameError(
'A local drugBank database directory must be defined.')
Path.mkdir(self.local)
urllib.urlretrieve(drugBankftp['targets'], self._target)
urllib.urlretrieve(drugBankftp['main'], self._main)
self._process()
return True
def download(self):
if not self.has_local:
raise NameError('A local Uniprot database directory must be defined.')
Path.mkdir(self.local)
destination = os.path.join(self.local, 'uniprot_sprot.dat.gz')
urllib.urlretrieve(Uniprotftp['swissprot'], destination)
destination = os.path.join(self.local, 'uniprot_trembl.dat.gz')
urllib.urlretrieve(Uniprotftp['trembl'], destination)
self._process()
return True
def make_PDBseq(self, log_file, resolution_threshold=None):
if not self.has_local:
raise NameError(
'A local PDB database must be defined to do create a PDBseq database.'
)
outdir = self.PDBseq if self.PDBseq is not None else os.curdir
Path.mkdir(self.PDBseq)
fasta_file = File(file_name=os.path.join(outdir, 'PDBseq.fa'),
action='w',
overwrite=True)
fasta_fd = fasta_file.descriptor
idx_file = File(file_name=os.path.join(outdir, 'PDBseq.fa.idx'),
action='w',
overwrite=True)
idx_fd = idx_file.descriptor
# if resolution_threshold is not None:
# filtered_file_name = self.get_PDBseq_filtered(resolution_threshold)
# filtered_file = File(file_name = filtered_file_name, action = 'w', overwrite = True)
# filtered_fd = filtered_file.descriptor
# resolutions = self.get_resolutions(resolution_threshold = resolution_threshold)
log_file = File(file_name=log_file, action='w', overwrite=True)
log_idx = log_file.descriptor
for pdb_file in self.localPDBs:
log_idx.write("Reading File: {0}\n".format(pdb_file))
newPDB = PDB(pdb_file=pdb_file, dehydrate=True)
fasta_idx = newPDB.FASTA_IDX(nucleotide=False)
if len(fasta_idx['FASTA']) != len(fasta_idx['IDX']):
log_idx.write(
'ERROR!!!!! Number of fastas and indexes are different for pdb {0}!!\n'
.format(newPDB.id))
if len(fasta_idx['FASTA']) > 0:
log_idx.write('\tPrinting FASTA and IDX...\n')
else:
log_idx.write('\tProblably just a nucleotide PDB...\n')
for c in range(len(fasta_idx['FASTA'])):
sequence = fasta_idx['FASTA'][c].split('\n')[1]
sequence = sequence.replace('X', '').replace('x', '')
if len(sequence) > 0:
fasta_fd.write(fasta_idx['FASTA'][c] + "\n")
if resolution_threshold is not None and newPDB.id in resolutions and not newPDB.is_all_ca:
filtered_fd.write(fasta_idx['FASTA'][c] + "\n")
idx_fd.write(fasta_idx['IDX'][c] + "\n")
del (newPDB)
#CLOSE & END
fasta_file.close()
idx_file.close()
if resolution_threshold is not None:
filtered_fd.close()
def _process(self):
tmoFile = File(self._pdbtmfile,'w', True)
for xmlfile in Path.list_files(os.path.join(self._local,'pdbtm/database/'), '*.xml'):
xmldata = TM(pdb = os.path.splitext(os.path.split(xmlfile)[1])[0].upper())
skip_chains = set()
read = False
fdxml = open(xmlfile)
for line in fdxml:
if line.startswith(' <TMRES>'): xmldata.tmres = line
elif line.startswith(' <TMTYPE'): xmldata.tmtype = line
elif line.startswith(' <PDBKWRES'): xmldata.kwres = line
elif line.startswith(' <SIDEDEFINITION'):
m = re.search('Side1="(\S+)"', line)
xmldata.side = m.group(1)
elif line.startswith(' <APPLY_TO_CHAIN'):
m = re.search('NEW_CHAINID=\"(\S{1})\"', line)
if m: skip_chains.add(m.group(1))
elif line.startswith(' <CHAIN '):
m = re.search('CHAINID=\"(\S{1})\" NUM_TM=\"(\d{1})\" TYPE=\"(\S+)\"', line)
if m:
chain, num, tmtype = m.group(1), m.group(2), m.group(3)
if not chain in skip_chains:
cdata = tuple([chain, num, tmtype])
xmldata.set_chain(cdata)
read = True
elif line.startswith(' <REGION ') and read:
m = re.search('pdb_beg=\"(\-*\d+\w*)\"[\s\S]+pdb_end=\"(\-*\d+\w*)\"\s+type=\"(\w{1})\"', line)
ini, end, tmtype = m.group(1), m.group(2), m.group(3)
xmldata.set_chain(cdata, tuple([ini, end, tmtype]))
elif line.startswith(' </CHAIN>'): read = False
fdxml.close()
if len(xmldata.chains) > 0:
tmoFile.write(str(xmldata)+"\n")
tmoFile.close()
def download(self):
if not self.has_local:
raise NameError(
'A local TaxID database directory must be defined.')
Path.mkdir(self.local)
destination = os.path.join(self.local, 'taxdmp.zip')
urllib.urlretrieve(taxIDftp['global'], destination)
command = ['unzip', '-o', destination, '-d', self.local]
p = subprocess.Popen(command,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
out, err = p.communicate()
self._process()
return True
def download(self):
if not self.has_local:
raise NameError(
'A local PDBeChem database directory must be defined.')
Path.mkdir(self.local)
destination = os.path.join(self.local, 'mmcif.tar.gz')
try:
urllib.urlretrieve(PDBeChemftp['global'], destination)
except:
return False
command = ['tar', 'zxvf', destination, '-C', self.local]
p = subprocess.Popen(command,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
out, err = p.communicate()
return True
def sync_PDB(self, log_file=None):
if not self.has_local:
raise NameError(
'A local PDB database must be defined to sync with.')
Path.mkdir(self.local)
command = [
'rsync', '-rlpt', '-v', '-z', '--port=' + PDBrsync['port'],
PDBrsync['address'], self.local
]
p = subprocess.Popen(command,
stdout=open(log_file, 'w')
if log_file is not None else subprocess.PIPE,
stderr=subprocess.PIPE)
SBIglobals.alert('verbose', self,
'Executing: {0}'.format(" ".join(command)))
out, err = p.communicate()
if err.strip() != '':
raise SystemError('{0}'.format(err))
def get_PDB(self, pdbID):
if self.has_local:
rootdir = os.path.join(self.local, pdbID.lower()[1:3])
for pdb_file in Path.list_files(root=rootdir, pattern='*.ent.gz'):
newfile = File(file_name=pdb_file, action='r')
if newfile.prefix.lstrip('pdb').upper() == pdbID.upper():
return pdb_file
#If we do not find it in local (or we do not have a local) we search it on the FTP
pdb_file = 'pdb' + pdbID.lower() + '.ent.gz'
source = 'ftp://' + PDBftp['address'] + os.path.join(
PDBftp['structures'], pdbID[1:3].lower(), pdb_file)
try:
urllib.urlretrieve(source, pdb_file)
except:
return False
return os.path.abspath(pdb_file)
def localPDBeChems(self):
for chem_file in Path.list_files(root=self.local, pattern='*.cif'):
yield chem_file
def localPDBs(self):
for pdb_file in Path.list_files(root=self.local, pattern='*.ent.gz'):
yield pdb_file
