def test_get_clashscore_internal(self): """ check that we get CCTBX clashscores """ print sys._getframe().f_code.co_name fn = '1G9W' # fetch pdb file fn = fetch.get_pdb (fn,'pdb',mirror='rcsb',log=null_out()) self.file_to_delete.append(fn) simple,sym,solv,all = cvp.get_cctbx_clashscores(file_name=fn) self.assertEqual(round(simple+sym+solv),round(all))
def test_get_probe_clashscore(self): """ check that we get PROBE clashscores """ print sys._getframe().f_code.co_name fn = '1G9W' # fetch pdb file fn = fetch.get_pdb (fn,'pdb',mirror='rcsb',log=null_out()) self.file_to_delete.append(fn) clashscore = cvp.get_probe_clashscore(file_name=fn) self.assertEqual(round(clashscore),0)
def test_1nl0(self):
'''Compare to published value'''
fn = '1nl0'
pdb_fn = fetch.get_pdb (fn,data_type='pdb',mirror='rcsb',log=null_out())
ph = pdb.input(file_name=pdb_fn).construct_hierarchy()
fab = fab_elbow_angle(pdb_hierarchy=ph,limit_light=107,limit_heavy=113)
calculated = fab.fab_elbow_angle
expected = 220
msg = 'FAB angle for {0} is {1:3.0f} instead of {2}'.format(fn,calculated,expected)
self.assertAlmostEqual(calculated,expected,delta=self.delta,msg=msg)
def get_cif_file(pdb_id):
""" get the cif file """
try:
fetched_file = fetch.get_pdb(
id=pdb_id, data_type='xray',
mirror='rcsb',quiet=True,log=null_out())
return fetched_file
except:
# avoid error if file already exist
pass
return False
def test_get_updated_file_name(self): """ check updating file using phenix.reduce """ print sys._getframe().f_code.co_name fn_start = '2H77' # fetch pdb file fn = fetch.get_pdb (fn_start,'pdb',mirror='rcsb',log=null_out()) self.file_to_delete.append(fn) update_fn = cvp.get_updated_file_name(file_name=fn) expected = fn_start + '.updated.pdb' self.assertEqual(expected,update_fn) self.file_to_delete.append(update_fn)
def get_pdb_file_info(self,pdb_id):
"""
Collect pdb file NCS and header info if there are NCS relations
and reslution >= 3
Args:
pdb_id (str): collect info for a single pdb file
Return:
new_rec (File_records object): object containing the collected info
"""
new_rec = File_records()
new_rec.pdb_id = pdb_id
fetched_file = pdb_id + '.pdb'
if not os.path.isfile(fetched_file):
fetched_file = fetch.get_pdb (
id=pdb_id, data_type='pdb',
mirror='rcsb',quiet=True,log=null_out())
else:
print 'file exist in local folder, did not fetch it..'
fn = os.path.realpath(fetched_file)
pdb_inp = iotbx.pdb.input(file_name=fn)
mtrix_info = pdb_inp.process_mtrix_records(eps=0.01)
t = (mtrix_info.as_pdb_string() == '')
t |= (not ncs_only(mtrix_info))
new_rec.only_master_in_pdb = not t
if len(mtrix_info.r) > 0 and new_rec.only_master_in_pdb:
m = multimer(file_name=fn,reconstruction_type='cau')
m.write(
pdb_output_file_name=fn,
crystal_symmetry=pdb_inp.crystal_symmetry())
# note that now the fn is a complete ASU
ncs_obj = iotbx.ncs.input(file_name=fn)
if (ncs_obj.number_of_ncs_groups == 0):
os.remove(fn)
return None
new_rec.n_ncs_groups = ncs_obj.number_of_ncs_groups
new_rec.n_ncs_copies = len(ncs_obj.ncs_transform)
pio = pdb_inp.get_r_rfree_sigma()
new_rec.resolution = pio.resolution
if new_rec.resolution and (new_rec.resolution < 3):
os.remove(fn)
return None
new_rec.year = pdb_inp.extract_header_year()
new_rec.experiment_type = pdb_inp.get_experiment_type()
new_rec.r_work_header = pio.r_work
new_rec.r_free_header = pio.r_free
try:
shutil.move(fn,self.asu_dir)
except:
# avoid error if file already exist
pass
return new_rec
def get_pdb_file(file_name):
from iotbx.pdb import fetch
class null_out(object):
"""Pseudo-filehandle for suppressing printed output."""
def isatty(self): return False
def close(self): pass
def flush(self): pass
def write(self, str): pass
def writelines(self, sequence): pass
log = null_out()
file_name = get_file_name(file_name)
return fetch.get_pdb (file_name,'pdb',mirror='rcsb',log=log)
def get_file_from_rcsb(pdb_id,data_type='pdb'):
""" (file_name) -> file_path
fetch pdb or structure factor file for pdb_id from the RCSB website
Args:
file_name: a pdb file name
data_type (str):
'pdb' -> pdb
'xray' -> structure factor
Returns:
a file path for the pdb file_name
"""
try:
file_name = fetch.get_pdb(pdb_id,data_type,mirror='rcsb',log=null_out())
except Sorry:
file_name = ''
return file_name
def get_pdb_file(file_name,fetch_file=False,print_out=True):
''' (file_name) -> file_path
This function will check if a pdb file_name exist.
If it is not, it will either fetch it from the RCSB website
or find it on LBLs pdb mirror folder
Argument:
file_name: a pdb file name
Return:
a file path for the pdb file_name
'''
from iotbx.pdb import fetch
class null_out(object):
"""Pseudo-filehandle for suppressing printed output."""
def isatty(self): return False
def close(self): pass
def flush(self): pass
def write(self, str): pass
def writelines(self, sequence): pass
log = null_out()
if not os.path.isfile(file_name):
# get a clean pdb file name
if print_out:
print 'No such file in working directory. Trying to fetch {} file from RCSB web site'.format(file_name)
file_name = get_file_name(file_name)
osType = sys.platform
if osType.startswith('win') or fetch_file==True:
# fetch pdb file
file_name = fetch.get_pdb (file_name,'pdb',mirror='rcsb',log=log)
else:
# find the file in LBL pdb mirror folder
pdb_dir = os.environ["PDB_MIRROR_PDB"]
pdb_files = open(os.path.join(pdb_dir, "INDEX"), "r").read().splitlines()
for i,p in enumerate(pdb_files):
if file_name in p:
break
file_name = os.path.join(pdb_dir,pdb_files[i])
elif print_out:
print 'Using the file {} found in the working directory'.format(file_name)
return file_name
def get_pdb_file(file_name, print_out=True):
""" (file_name) -> file_path
This function will check if a pdb file_name exist.
If it is not, it will either fetch it from the RCSB website
or find it on LBLs pdb mirror folder
Args:
file_name (str): a pdb file name
Returns:
file_name (str): the location, path, of the file
"""
if not os.path.isfile(file_name):
# get a clean pdb file name
if print_out:
s = 'No such file in working directory. ' \
'Trying to fetch {} file from RCSB web site'
print s.format(file_name)
file_name = get_4_letters_pdb_id(file_name)
osType = sys.platform
if osType.startswith('win'):
from iotbx.pdb import fetch
# fetch pdb file from intenet
file_name = fetch.get_pdb (file_name,'pdb',mirror='rcsb',log=null_out())
else:
# find the file in LBL pdb mirror folder
pdb_dir = os.environ["PDB_MIRROR_PDB"]
pdb_files = open(os.path.join(pdb_dir, "INDEX"), "r").read().splitlines()
for i,p in enumerate(pdb_files):
if file_name in p:
break
file_name = os.path.join(pdb_dir,pdb_files[i])
# # Second method
# f = 'pdb{}.ent.gz'.format(file_name)
# file_name = []
# for root, _, files in os.walk(pdb_dir):
# if f in files:
# file_name = os.path.join(root, f)
# break
elif print_out:
print 'Using the file {} found in the working directory'.format(file_name)
return file_name
def run():
work_dir = '/net/cci-filer2/raid1/home/youval/Work/work/junk'
os.chdir(work_dir)
#
#file_name = '3zzv'
#file_name = '4iw4'
#file_name = '2btv'
files = set(['3m8l', '2btv', '1vcr', '1llc', '3dpr', '3dar',
'2w4y', '2zah', '1tnv', '1dwn', '2w0c', '1w39',
'1x33', '2izw', '1x35', '3nop', '2bny', '1ei7',
'3not', '3nou', '1dzl', '3lob', '3nap', '1vsz'])
for fn in files:
sf_fn = fetch.get_pdb (fn,'xray',mirror='rcsb',log=sys.stdout,format='cif')
cmd = 'phenix.cif_as_mtz {0} --output-file-name=tmp_file.mtz --merge --remove-systematic-absences --map-to-asu --extend-flags'.format(sf_fn)
r = easy_run.go(cmd)
print 'Results for file: {}'.format(fn)
print '-'*60
for x in r.stdout_lines:
print x
print '='*60
from iotbx.pdb.fetch import get_pdb
import sys
get_pdb(id="3nd4",
data_type="xray",
mirror="rcsb",
format="cif",
log=sys.stdout)
def run2(args, log=sys.stdout):
"""
Fetches pdb files and/or reflection data from the PDB.
Parameters
----------
args : list of str
log : file, optional
Returns
-------
str or list of str
List of file names that were downloaded.
"""
if len(args) < 1:
raise Usage("""\
phenix.fetch_pdb [-x|-f|--all] [--mtz] [-q] ID1 [ID2, ...]
Command-line options:
-x Get structure factors (mmCIF file)
-c Get model file in mmCIF format
-f Get sequence (FASTA file)
--all Download all available data
--mtz Download structure factors and PDB file, and generate MTZ
-q suppress printed output
""")
from iotbx.pdb.fetch import get_pdb
quiet = False
convert_to_mtz = False
data_type = "pdb"
format = "pdb"
mirror = "rcsb"
ids = []
for arg in args:
if (arg == "--all"):
data_type = "all"
elif (arg == "-x"):
data_type = "xray"
elif (arg == "-f"):
data_type = "fasta"
elif (arg == "-q"):
quiet = True
elif (arg == "--mtz"):
convert_to_mtz = True
data_type = "all"
elif (arg == "-c"):
format = "cif"
elif (arg.startswith("--mirror=")):
mirror = arg.split("=")[1]
if (not mirror in ["rcsb", "pdbe", "pdbj", "pdb-redo"]):
raise Sorry(
"Unrecognized mirror site '%s' (choices: rcsb, pdbe, pdbj, pdb-redo)"
% mirror)
else:
ids.append(arg)
if (len(ids) == 0):
raise Sorry("No PDB IDs specified.")
if (data_type != "all"):
#mirror = "rcsb"
files = []
for id in ids:
files.append(get_pdb(id, data_type, mirror, log, format=format))
if (len(files) == 1):
return files[0]
return files
else:
files = []
for id in ids:
for data_type_, data_format in [("pdb", "pdb"), ("fasta", "pdb"),
("xray", "pdb"), ("pdb", "cif")]:
files.append(
get_pdb(id, data_type_, mirror, log, format=data_format))
if (convert_to_mtz):
misc_args = [
"--merge", "--map_to_asu", "--extend_flags",
"--ignore_bad_sigmas"
]
easy_run.call("phenix.cif_as_mtz %s-sf.cif %s" %
(id, " ".join(misc_args)))
if os.path.isfile("%s-sf.mtz" % id):
os.rename("%s-sf.mtz" % id, "%s.mtz" % id)
print >> log, "Converted structure factors saved to %s.mtz" % id
# os.remove("%s-sf.cif" % id)
files[-1] = os.path.abspath("%s.mtz" % id)
if (not os.path.isfile("%s.mtz" % id)):
raise Sorry(
"MTZ conversion failed - try running phenix.cif_as_mtz "
+ "manually (and check %s-sf.cif for format errors)." %
id)
from iotbx.file_reader import any_file
mtz_in = any_file("%s.mtz" % id)
mtz_in.assert_file_type("hkl")
for array in mtz_in.file_server.miller_arrays:
if (array.anomalous_flag()):
print >> log, " %s is anomalous" % array.info(
).label_string()
return files
def get_file(fn):
if not os.path.isfile(fn + '.pdb'):
sf_fn = fetch.get_pdb (fn,data_type='pdb',mirror='rcsb',log=sys.stdout)
# Description: Fetch pdb file from RCSB in PDB format.
# Source: NA
"""
from iotbx.pdb.fetch import get_pdb
import sys
get_pdb(id="${1:3nd4}",data_type="pdb", mirror="rcsb", format="pdb", log=sys.stdout)
"""
from iotbx.pdb.fetch import get_pdb
import sys
get_pdb(id="3nd4",data_type="pdb", mirror="rcsb", format="pdb", log=sys.stdout)
def run2(args, log=sys.stdout):
"""
Fetches pdb files and/or reflection data from the PDB.
Parameters
----------
args : list of str
log : file, optional
Returns
-------
str or list of str
List of file names that were downloaded.
"""
if len(args) < 1:
raise Usage(
"""\
phenix.fetch_pdb [-x|-f|--all] [--mtz] [-q] ID1 [ID2, ...]
Command-line options:
-x Get structure factors (mmCIF file)
-c Get model file in mmCIF format
-f Get sequence (FASTA file)
--all Download all available data
--mtz Download structure factors and PDB file, and generate MTZ
-q suppress printed output
"""
)
from iotbx.pdb.fetch import get_pdb
quiet = False
convert_to_mtz = False
data_type = "pdb"
format = "pdb"
mirror = "rcsb"
ids = []
for arg in args:
if arg == "--all":
data_type = "all"
elif arg == "-x":
data_type = "xray"
elif arg == "-f":
data_type = "fasta"
elif arg == "-q":
quiet = True
elif arg == "--mtz":
convert_to_mtz = True
data_type = "all"
elif arg == "-c":
format = "cif"
elif arg.startswith("--mirror="):
mirror = arg.split("=")[1]
if not mirror in ["rcsb", "pdbe", "pdbj"]:
raise Sorry("Unrecognized mirror site '%s' (choices: rcsb, pdbe, pdbj)" % mirror)
else:
ids.append(arg)
if len(ids) == 0:
raise Sorry("No PDB IDs specified.")
if data_type != "all":
# mirror = "rcsb"
files = []
for id in ids:
files.append(get_pdb(id, data_type, mirror, log, format=format))
if len(files) == 1:
return files[0]
return files
else:
files = []
for id in ids:
for data_type_, data_format in [("pdb", "pdb"), ("fasta", "pdb"), ("xray", "pdb"), ("pdb", "cif")]:
files.append(get_pdb(id, data_type_, mirror, log, format=data_format))
if convert_to_mtz:
misc_args = ["--merge", "--map_to_asu", "--extend_flags", "--ignore_bad_sigmas"]
easy_run.call("phenix.cif_as_mtz %s-sf.cif %s" % (id, " ".join(misc_args)))
if os.path.isfile("%s-sf.mtz" % id):
os.rename("%s-sf.mtz" % id, "%s.mtz" % id)
print >> log, "Converted structure factors saved to %s.mtz" % id
# os.remove("%s-sf.cif" % id)
files[-1] = os.path.abspath("%s.mtz" % id)
if not os.path.isfile("%s.mtz" % id):
raise Sorry(
"MTZ conversion failed - try running phenix.cif_as_mtz "
+ "manually (and check %s-sf.cif for format errors)." % id
)
from iotbx.file_reader import any_file
mtz_in = any_file("%s.mtz" % id)
mtz_in.assert_file_type("hkl")
for array in mtz_in.file_server.miller_arrays:
if array.anomalous_flag():
print >> log, " %s is anomalous" % array.info().label_string()
return files
def get_file(fn):
if len(fn)==4: fn = fn + '.pdb'
if not os.path.isfile(fn):
fn = fetch.get_pdb (fn,data_type='pdb',mirror='rcsb',log=sys.stdout)
return fn
def __init__(self,
pdb_file_name,
chain_ID_light='L',
chain_ID_heavy='H',
limit_light=107,
limit_heavy=113):
'''
Get elbow angle for Fragment antigen-binding (Fab)
- Default heavy and light chains IDs are: H : heavy, L : light
- Default limit (cutoff) between variable and constant parts
is residue number 107/113 for light/heavy chains
- Variable domain si from residue 1 to limit.
Constant domain form limit+1 to end.
- Method of calculating angle is based on Stanfield, et al., JMB 2006
Argument:
---------
pdb_file_name : 4 characters string, a PDB name
chain_ID_heavy : The heavy protion of the protein, chain ID
chain_ID_light : The light protion of the protein, chain ID
limit_heavy : the number of the cutoff residue, between
the variable and constant portions in the heavy chian
limit_light : the number of the cutoff residue, between
the variable and constant portions in the light chian
Main attributes:
----------------
self.FAB_elbow_angle : the elbow angle calculated as the dot product of
the VL-VH pseudodyade axie and the CL-CH pseudodyade axie
The angle always computes between 90 and 180
Test program at:
cctbx_project\mmtbx\regression\tst_FAB_elbow_angle.py
Example:
--------
>>>fab = FAB_elbow_angle(
pdb_file_name='1bbd',
chain_ID_light='L',
chain_ID_heavy='H',
limit_light=114,
limit_heavy=118)
>>> print fab.FAB_elbow_angle
133
>>>fab = FAB_elbow_angle(pdb_file_name='1bbd')
>>> print fab.FAB_elbow_angle
126 (127 in Stanfield, et al., JMB 2006)
>>> print fab.var_L
'VL from N ASP L 1 to O GLY L 107 '
>>> print fab.var_L_nAtoms
826
@author Youval Dar (LBL 2014)
'''
# abolute path and test that file exist
pdb_file_name = self.get_pdb_file_name_and_path(pdb_file_name)
# Devide to variable and constant part, and get the hirarchy for
# H : heavy, L : light
# start_to_limit : Constant
# limit_to_end : Variable
pdb_var_H,pdb_const_H = self.get_pdb_protions(
pdb_file_name=pdb_file_name,
chain_ID=chain_ID_heavy,
limit=limit_heavy)
pdb_var_L,pdb_const_L = self.get_pdb_protions(
pdb_file_name=pdb_file_name,
chain_ID=chain_ID_light,
limit=limit_light)
# Collect info about FAB segments
self.var_L,self.var_L_nAtoms = self.get_segment_info(pdb_var_L,'VL')
self.var_H,self.var_H_nAtoms = self.get_segment_info(pdb_var_H,'VH')
self.const_L,self.const_L_nAtoms = self.get_segment_info(pdb_const_L,'CL')
self.const_H,self.const_H_nAtoms = self.get_segment_info(pdb_const_H,'CH')
# get 1bbd
currnet_dir = os.getcwd()
tempdir = tempfile.mkdtemp('tempdir')
os.chdir(tempdir)
fetch.get_pdb ('1bbd',data_type='pdb',mirror='rcsb',log=null_out())
# seperate chains for testing and referance
test_var_H,test_const_H = self.get_pdb_protions(
pdb_file_name=pdb_file_name,
chain_ID=chain_ID_heavy,
limit=limit_heavy)
pdb_ref_var_H,pdb_ref_const_H = self.get_pdb_protions(
pdb_file_name='1bbd.pdb',
chain_ID=chain_ID_heavy,
limit=limit_heavy)
# clean temp folder
os.chdir(currnet_dir)
shutil.rmtree(tempdir)
# get rotation and translation
tranformation_const = self.get_transformation(
pdb_hierarchy_fixed=pdb_const_H,
pdb_hierarchy_moving=pdb_const_L)
tranformation_var = self.get_transformation(
pdb_hierarchy_fixed=pdb_var_H,
pdb_hierarchy_moving=pdb_var_L)
tranformation_ref_const = self.get_transformation(
pdb_hierarchy_fixed=pdb_ref_const_H,
pdb_hierarchy_moving=test_const_H)
# Apply transformation on the variable portion of the tesed protein
new_sites = tranformation_ref_const.r.elems*test_var_H.atoms().extract_xyz() + tranformation_ref_const.t
test_var_H.atoms().set_xyz(new_sites)
# get rotation and translation
tranformation_ref_var = self.get_transformation(
pdb_hierarchy_fixed=pdb_ref_var_H,
pdb_hierarchy_moving=test_var_H)
# Get the angle and eigenvalues
eigen_const = eigensystem.real_symmetric(tranformation_const.r.as_sym_mat3())
eigen_var = eigensystem.real_symmetric(tranformation_var.r.as_sym_mat3())
eigen_ref = eigensystem.real_symmetric(tranformation_ref_var.r.as_sym_mat3())
#
eigen_vectors_const = self.get_eigenvector(eigen_const)
eigen_vectors_var = self.get_eigenvector(eigen_var)
eigen_vectors_var_ref = self.get_eigenvector(eigen_ref)
#
angle = self.get_angle(vec1=eigen_vectors_const, vec2=eigen_vectors_var)
print '+'*30
ref_angle = self.get_angle(vec1=eigen_vectors_var_ref, vec2=eigen_vectors_var,larger=False)
# Resolve ambiguity with angle
if ref_angle > 90: ref_angle = 180 - ref_angle
if angle + ref_angle > 180:
# Choose angle smaller than 180
angle = 360 - angle
self.FAB_elbow_angle = angle