def read(self, ag):
sio = io.StringIO()
prody.writePDBStream(sio, ag)
cont = sio.getvalue().rstrip()
sio.close()
mol = openbabel.OBMol()
self.ReadString(mol, cont)
return mol
def add_mol(self, mol, keep_chains=False, keep_resi=False):
"""
This behaves bad when molecules have same chain names
"""
ag1 = self.ag.copy()
ag2 = mol.ag.copy()
if ag1.numCoordsets() != ag2.numCoordsets():
raise RuntimeError('Atom groups have different numbers of coordinate sets')
nsets = ag1.numCoordsets()
chains1 = list(set(ag1.getChids()))
chains2 = list(set(ag2.getChids()))
all_chains = chains1 + chains2
if len(set(all_chains)) != len(all_chains) and keep_chains:
logger.warning('Two atom groups contain same chain IDs, merging can go wrong')
if keep_resi and len(set(ag1.getResnums()).intersection(set(ag2.getResnums()))) > 0:
raise RuntimeError('Refusing to merge atom groups which contain same chain IDs AND residue IDs')
if not keep_chains:
if len(chains1) + len(chains2) > len(self._chain_order):
raise RuntimeError('Total number of chains is too large, out of chain ID letters')
iter_chains = iter(self._chain_order)
map1 = {x: next(iter_chains) for x in chains1}
map2 = {x: next(iter_chains) for x in chains2}
for old, new in map1.items():
ag1.select('chain ' + old).setChids(new)
for old, new in map2.items():
ag2.select('chain ' + old).setChids(new)
if not keep_resi:
resi = 1
for r in ag1.getHierView().iterResidues():
r.setResnum(resi)
resi += 1
for r in ag2.getHierView().iterResidues():
r.setResnum(resi)
resi += 1
buf = StringIO()
for i in range(nsets):
if nsets > 1:
buf.write('MODEL \n' + str(i + 1))
prody.writePDBStream(buf, ag1, csets=i)
prody.writePDBStream(buf, ag2, csets=i)
if nsets > 1:
buf.write('ENDMDL\n')
else:
buf.write('END\n')
buf.seek(0)
joint = BasePDB(ag=prody.parsePDBStream(buf))
joint.renumber(keep_resi=True, keep_chains=True)
buf.close()
return joint
def RDKit_Mol_from_ProDy(prody_instance, removeHs=True):
"""
Creates an RDKit Mol object from a ProDy AtomGroup instance
:return:
"""
residue_io = io.StringIO()
prody.writePDBStream(residue_io, prody_instance)
return Chem.MolFromPDBBlock(residue_io.getvalue(), removeHs=removeHs)
def add_hydrogens(self, trim=True, csets=None):
raise NotImplementedError()
output = []
natoms = -1
csets = self._make_csets(csets)
for i in csets:
if trim:
p_start = Popen([define.REDUCE_EXE, '-Quiet', '-Trim', '-'], stdin=PIPE, stdout=PIPE, stderr=STDOUT)
p_finish = Popen([define.REDUCE_EXE, '-Quiet', '-FLIP', '-'], stdin=p_start.stdout, stdout=PIPE,
stderr=STDOUT)
else:
p_start = Popen([define.REDUCE_EXE, '-Quiet', '-FLIP', '-'], stdin=PIPE, stdout=PIPE, stderr=STDOUT)
p_finish = p_start
prody.writePDBStream(p_start.stdin, self.ag, csets=i)
p_start.stdin.close()
output += ['MODEL%9i\n' % (i + 1)]
reduced = []
while p_finish.poll() is None:
reduced = p_finish.stdout.readlines()
p_start.wait()
p_finish.wait()
print(reduced)
natoms_cur = len(list(filter(lambda x: x.startswith('ATOM') or x.startswith('HETATM'), reduced)))
if i == csets[0]:
natoms = natoms_cur
elif natoms != natoms_cur:
raise RuntimeError('Number of atoms in reduced model %i is different from the first model (%i, %i)' % (
i, natoms_cur, natoms))
output += reduced
output += ['ENDMDL\n']
status = p_finish.poll()
if status != 0:
logger.error('Called process returned ' + str(status))
self.ag = prody.parsePDBStream(StringIO(''.join(output)))
self.renumber()
return self
def print_pdb(self, ifg, parsed_pdb, comb):
vdm_renum = renumber_chids_resnums(self, 'X')
ifg_renum = renumber_chids_resnums(ifg, 'Y')
filename = comb.output_dir_pdb + 'iFG_' + str(ifg.count) + '_vdM_' + str(ifg.vdm_count) \
+ '_' + comb.file_tag + '.pdb.gz'
with gzip.open(filename, 'wt') as pdbfile:
pr.writePDBStream(pdbfile, vdm_renum)
pr.writePDBStream(pdbfile, ifg_renum)
if ifg.contact_atoms_water:
pr.writePDBStream(pdbfile, ifg.contact_atoms_water)
if ifg.contact_atoms_metal:
pr.writePDBStream(pdbfile, ifg.contact_atoms_metal)
if ifg.contact_atoms_ligand:
pr.writePDBStream(
pdbfile,
parsed_pdb.prody_pdb.select('resindex ' + ' '.join(
str(ri) for ri in np.unique(
ifg.contact_atoms_ligand.getResindices()))))
def __str__(self):
ss = io.StringStream()
prody.writePDBStream(ss, self._pdb)
return ss.read()
def searchDali(pdb, chain=None, subset='fullPDB', daliURL=None, **kwargs):
"""Search Dali server with input of PDB ID (or local PDB file) and chain ID.
Dali server: http://ekhidna2.biocenter.helsinki.fi/dali/
:arg pdb: PDB code or local PDB file for the protein to be searched
:arg chain: chain identifier (only one chain can be assigned for PDB)
:type chain: str
:arg subset: fullPDB, PDB25, PDB50, PDB90
:type subset: str
"""
import requests
LOGGER.timeit('_dali')
# timeout = 120
timeout = kwargs.pop('timeout', 120)
if daliURL is None:
daliURL = "http://ekhidna2.biocenter.helsinki.fi/cgi-bin/sans/dump.cgi"
if isinstance(pdb, Atomic):
atoms = pdb
chain_set = set(atoms.getChids())
if chain and not chain in chain_set:
raise ValueError('input structure (%s) does not have chain %s'%(atoms.getTitle(), chain))
if len(chain_set) > 1:
if not chain:
raise TypeError('the structure (%s) contains more than one chain, therefore a chain identifier '
'needs to be specified'%pdb.getTitle())
atoms = atoms.select('chain '+chain)
else:
chain = chain_set.pop()
stream = createStringIO()
writePDBStream(stream, atoms)
data = stream.getvalue()
stream.close()
files = {"file1" : data}
pdbId = atoms.getTitle()
pdb_chain = ''
dali_title = 'Title_'+pdbId+chain
elif isinstance(pdb, str):
if os.path.isfile(pdb):
atoms = parsePDB(pdb)
chain_set = set(atoms.getChids())
# pdbId = "s001"
filename = os.path.basename(pdb)
filename, ext = os.path.splitext(filename)
if ext.lower() == '.gz':
filename2, ext2 = os.path.splitext(filename)
if ext2.lower() == '.pdb':
filename = filename2
pdbId = filename
if chain and not chain in chain_set:
raise ValueError('input PDB file does not have chain ' + chain)
if len(chain_set) > 1:
if not chain:
raise TypeError('PDB file (%s) contains more than one chain, therefore a chain identifier '
'needs to be specified'%pdb)
atoms = atoms.select('chain '+chain)
#local_temp_pdb = pdbId+chain+'.pdb'
#local_temp_pdb = 's001'+chain+'.pdb'
stream = createStringIO()
writePDBStream(stream, atoms)
data = stream.getvalue()
stream.close()
else:
data = open(pdb, "rb")
chain = chain_set.pop()
files = {"file1" : data}
# case: multiple chains. apply fetch ? multiple times?
pdb_chain = ''
dali_title = 'Title_' + pdbId + chain
else:
pdbId, ch = _getPDBid(pdb)
if not chain:
chain = ch
if not chain:
raise TypeError('a chain identifier is needed for the search')
pdb_chain = pdbId + chain
dali_title = 'Title_' + pdb_chain
files = ''
parameters = { 'cd1' : pdb_chain, 'method': 'search', 'title': dali_title, 'address': '' }
# enc_params = urllib.urlencode(parameters).encode('utf-8')
# request = urllib2.Request(daliURL, enc_params)
request = requests.post(daliURL, parameters, files=files)
try_error = 3
while try_error >= 0:
try:
# url = urllib2.urlopen(request).url
url = request.url
break
except:
try_error -= 1
if try_error >= 0:
LOGGER.sleep(2, '. Connection error happened. Trying to reconnect...')
continue
else:
# url = urllib2.urlopen(request).url
url = request.url
break
if url.split('.')[-1].lower() in ['html', 'php']:
# print('test -1: '+url)
url = url.replace(url.split('/')[-1], '')
LOGGER.debug('Submitted Dali search for PDB "{0}{1}".'.format(pdbId, chain))
LOGGER.info(url)
LOGGER.clear()
return DaliRecord(url, pdbId, chain, subset=subset, timeout=timeout, **kwargs)
def __str__(self):
ss = io.StringStream()
prody.writePDBStream(ss, self._pdb)
return ss.read()
def save_cluster_elements(elements,
ids,
out_pdb_name,
data_handler,
options,
cluster_sizes = None):
"""
Saves a pdb file containing the most representative elements of the clustering.
@param elements: A list of the representative elements of the clustering we want to extract.
@params ids: A list with the cluster ids (1 to 1 mapping with 'elements').
@param out_pdb_name: The complete path of the produced file.
@param data_handler: The trajectory handler for this run or an array with pdb file paths.
@param options: postprocessing options to generate the file. Currently a dic with any of these:
"keep_remarks" - Will add each model's remarks before the model header if present
Possible values are:
- "NONE": not to store remarks (Default)
- "STANDARD": stores remarks that follow pdb standard
- "NOT STANDARD": stores remarks not following the pdb standard
- "ALL": stores all remarks
"add_source_details" - Will add two remarks before the model tag: the path of the source file and
the original model number.
@params cluster_sizes: specific for the representatives case. Each element of this array holds the
size of its cluster.
"""
keep_remarks = options.get_value("keep_remarks", default_value = "NONE")
add_source_details = options.get_value("add_source_details", default_value = False)
file_handler_out = open(out_pdb_name, "w")
data = data_handler.get_data()
merged_structure = data.get_all_elements()
file_handler_out.write("REMARK 000 File created using Prody and pyProCT\n")
if not keep_remarks == "NONE" and not add_source_details:
prody.writePDBStream(file_handler_out, merged_structure, csets = elements)
else:
all_remarks = filter_remarks(data.get_all_remarks(), subset= keep_remarks)
all_model_numbers = data.get_all_model_numbers()
current_model = 0
for i, element_id in enumerate(elements):
if keep_remarks:
remarks = all_remarks[element_id]
file_handler_out.write("".join(remarks))
if add_source_details:
model_number = all_model_numbers[element_id]
conf_source = data_handler.get_source_of_element(element_id).get_path()
file_handler_out.write("REMARK 000 source : %s\n"%conf_source)
file_handler_out.write("REMARK 000 original model nr : %d\n"%model_number)
file_handler_out.write("REMARK 000 cluster id : %s\n"%ids[i])
file_handler_out.write("REMARK 000 cluster element : %d\n"%element_id)
if cluster_sizes is not None:
file_handler_out.write("REMARK 000 cluster population : %s\n"%(cluster_sizes[i]))
file_handler_out.write("MODEL"+str(current_model).rjust(9)+"\n")
pdb_handler = cStringIO.StringIO()
prody.writePDBStream(pdb_handler, merged_structure, csets= element_id)
# skip the first remark if any
lines = filter(lambda line: line[0:6]!="REMARK" and line[0:5]!="MODEL" and line[0:6]!="ENDMDL",
pdb_handler.getvalue().splitlines(True))
pdb_handler.close()
file_handler_out.write("".join(lines))
file_handler_out.write("ENDMDL\n")
current_model+=1
file_handler_out.close()
def alignment_monstrosity(self,
rmsd_cutoff=0.5,
use_local_pdb_database=False,
verify_substructure=True):
"""
Consequences of not thinking ahead...
For each fragment, align all fragment-containing ligands to fragment
Generate PDBs with aligned coordinate systems
:param args:
:param rmsd_cutoff: fragment alignment RMSD cutoff, anything higher gets rejected
:return:
"""
# Create directory for processed PDBs
rejected_dict = self.load_previously_rejected_pdbs()
# Create directories...
if not use_local_pdb_database:
os.makedirs(self.pdb_bank_dir, exist_ok=True)
os.makedirs(self.processed_PDBs_path, exist_ok=True)
# If use_local_pdb_database=False, use PDB FTP to download all structures
# Otherwise, all relevant structures should be found in the local PDB database
if not use_local_pdb_database:
prody.pathPDBFolder(folder=self.pdb_bank_dir)
for current_fragment in self.pdb_ligand_json:
# Only download PDBs that aren't already in PDB bank directory
existing_PDBs = [
pdb[:4].lower() for pdb in os.listdir(self.pdb_bank_dir)
]
PDBs_to_download = list(
set(self.pdb_ligand_json[current_fragment]['PDBs']) -
set(existing_PDBs))
if len(PDBs_to_download) > 0:
print(f'Downloading PDBs for {current_fragment}...\n')
prody.fetchPDBviaFTP(*PDBs_to_download)
else:
print(
f'All relevant PDBs for {current_fragment} found in {self.pdb_bank_dir}!\n'
)
# Fragment_1, Fragment_2, ...
for current_fragment in self.pdb_ligand_json:
# Create directory for processed PDBs
processed_dir = os.path.join(self.processed_PDBs_path,
current_fragment)
processed_dir_exists = os.path.exists(processed_dir)
os.makedirs(processed_dir, exist_ok=True)
# Get list of already processed PDBs for current_fragment
already_processed_pdbs = [
file[:4].lower() for file in os.listdir(processed_dir)
]
# Save ideal_ligand_containers for each fragment so things are only downloaded once
ideal_ligand_dict = dict()
ideal_ligand_dict['Ligands'] = dict()
ideal_ligand_dict['Failed'] = list()
# Align_PDB class holds all information for the current fragment
align = Align_PDB(self.user_defined_dir,
current_fragment,
self.sanitized_smiles_dict[current_fragment],
verify_substructure=verify_substructure)
# Get PDB IDs that are viable for extracting protein-fragment contacts
reject_pdbs = rejected_dict[
current_fragment] if current_fragment in rejected_dict.keys(
) else list()
if not processed_dir_exists:
reject_pdbs = list()
reject_pdbs.append('3k87') # DEBUGGING
viable_pdbs = list(
set(self.pdb_ligand_json[current_fragment]['PDBs']) -
set(reject_pdbs) - set(already_processed_pdbs))
# For each PDB containing a fragment-containing compound
for pdbid in viable_pdbs:
# Return path of PDB file to use for processing
found_pdb, pdb_path = self.return_PDB_to_use_for_alignments(
pdbid, use_local_pdb_database=use_local_pdb_database)
if not found_pdb:
print(f'Cannot find {pdbid}!')
continue
# Proceed with processing if the current PDB passes all filters
print("\n\nProcessing {}...".format(pdbid))
# --- Check which ligands contain relevant fragments --- #
relevant_ligands = self.return_substructure_containing_ligands(
pdb_path, self.pdb_ligand_json, current_fragment)
# Set things up! Get ligands from Ligand Expo if haven't already tried and failed
for ligand in relevant_ligands:
if not ideal_ligand_dict['Ligands'].get(
ligand
) and ligand not in ideal_ligand_dict['Failed']:
ideal_ligand_container = Ideal_Ligand_PDB_Container(
ligand)
if ideal_ligand_container.success:
ideal_ligand_dict['Ligands'][
ligand] = ideal_ligand_container
else:
ideal_ligand_dict['Failed'].append(ligand)
# Create a temp list for ligands that will be pulled from the current PDB
ligand_container_dict_for_current_pdb = {
lig: ideal_ligand_dict['Ligands'][lig]
for lig in ideal_ligand_dict['Ligands']
if lig in relevant_ligands
}
relevant_ligands_prody_dict = align.extract_ligand_records(
pdb_path, ligand_container_dict_for_current_pdb)
# Reject if no ligands with all atoms represented can be found for the given PDB
if len(relevant_ligands_prody_dict) < 1:
if current_fragment in rejected_dict.keys():
rejected_dict[current_fragment].append(pdbid)
else:
rejected_dict[current_fragment] = [pdbid]
print(
'REJECTED - no target ligands were fully represented in the PDB'
)
continue
# --- Perform alignment of PDB fragment substructure (mobile) onto defined fragment (target) --- #
# ...if PDB has not been processed, rejected, or excluded by the user
else:
# Iterate over ligands found to contain fragments as substructures
for ligand_resname, ligand_chain, ligand_resnum in relevant_ligands_prody_dict:
# Mapping of fragment atoms to target ligand atoms
target_ligand_ideal_smiles = ligand_container_dict_for_current_pdb[
ligand_resname].smiles
# todo: catch ligands with missing SMILES strings earlier...
if target_ligand_ideal_smiles is None:
continue
target_ligand_pdb_string = io.StringIO()
target_ligand_prody = relevant_ligands_prody_dict[(
ligand_resname, ligand_chain,
ligand_resnum)].select('not hydrogen')
prody.writePDBStream(target_ligand_pdb_string,
target_ligand_prody)
mapping_successful, fragment_target_map = align.fragment_target_mapping(
target_ligand_ideal_smiles,
target_ligand_pdb_string)
if not mapping_successful:
if current_fragment in rejected_dict.keys():
rejected_dict[current_fragment].append(pdbid)
else:
rejected_dict[current_fragment] = [pdbid]
print(
'REJECTED - failed atom mapping between target and reference fragment'
)
continue
print(
f'\n{len(fragment_target_map)} possible mapping(s) of fragment onto {pdbid}:{ligand} found...\n'
)
# Iterate over possible mappings of fragment onto current ligand
rmsd_success = False
for count, mapping in enumerate(fragment_target_map):
# todo: refactor to use RDKit's atom.GetMonomerInfo() for atom selections...
# Determine translation vector and rotation matrix
target_coords_and_serials, frag_atom_coords, transformation_matrix = align.determine_rotation_and_translation(
mapping, target_ligand_prody)
trgt_atom_coords, target_fragment_atom_serials = target_coords_and_serials
# Apply transformation to protein_ligand complex if rmsd if below cutoff
# Use information from PubChem fragment SMILES in determining correct mappings
# Actually, map fragment onto source ligand and use valence information to determine correct mappings
rmsd = prody.calcRMSD(
frag_atom_coords,
prody.applyTransformation(
transformation_matrix, trgt_atom_coords))
print(
'RMSD of target onto reference fragment:\t{}'.
format(rmsd))
if rmsd < rmsd_cutoff:
transformed_pdb = align.apply_transformation(
pdb_path, ligand_resnum,
target_fragment_atom_serials,
transformation_matrix)
# Continue if transformed_pdb - ligand is None
if transformed_pdb.select(
f'not (resname {ligand_resname})'
) is None:
continue
transformed_pdb_name = f'{pdbid}_{ligand_resname}_{ligand_chain}_{ligand_resnum}-{count}.pdb'
prody.writePDB(
os.path.join(processed_dir,
transformed_pdb_name),
transformed_pdb)
rmsd_success = True
else:
print(
'REJECTED - high RMSD upon alignment to reference fragment'
)
if rmsd_success is False:
if current_fragment in rejected_dict.keys():
rejected_dict[current_fragment].append(pdbid)
else:
rejected_dict[current_fragment] = [pdbid]
# Remember rejected PDBs
with open(self.rejected_dict_pickle, 'wb') as reject_pickle:
pickle.dump(rejected_dict, reject_pickle)
