def read_pdb_file_content(input_type, input_value):
"""
Read the content of a PDB file either from a local path or via fetching the file from
the PDB webserver.
Parameters
----------
input_type : str
Either 'pdb_code' or 'pdb_filepath'.
input_value : str
Either a valid PDB code, or a local filepath of a PDB file.
Returns
-------
str
Content of the PDB file as a single string.
"""
if input_type == "pdb_code":
pdb_file_content = pypdb.get_pdb_file(input_value)
elif input_type == "pdb_filepath":
with open(input_value) as f:
pdb_file_content = f.read()
else:
raise ValueError(f"Provided input type {input_type} not valid. Accepted values are 'pdb_code' and 'pdb_filepath'.")
return pdb_file_content
def readPDB(id, property_map={}):
"""Read a molecular system from a Protein Data Bank (PDBP) ID in the RSCB PDB
website.
Parameters
----------
id : str
The PDB ID string.
property_map : dict
A dictionary that maps system "properties" to their user defined
values. This allows the user to refer to properties with their
own naming scheme, e.g. { "charge" : "my-charge" }
Returns
-------
system : :class:`System <BioSimSpace._SireWrappers.System>`
A molecular system.
Examples
--------
Create a molecular system from the deoxy human haemoglobin Protein
Data Bank (PDB) record.
>>> import BioSimSpace as BSS
>>> system = BSS.readPDB("1a3n")
"""
if not _has_pypdb:
_warn("BioSimSpace.IO: PyPDB could not be imported on this system.")
return None
if type(id) is not str:
raise TypeError("'id' must be of type 'str'")
# Strip any whitespace from the PDB ID and convert to upper case.
id = id.replace(" ", "").upper()
# Create a temporary directory to write the PDB file.
tmp_dir = _tempfile.TemporaryDirectory()
# Attempt to download the PDB file. (Compression is currently broken!)
try:
pdb_string = _pypdb.get_pdb_file(id, filetype="pdb", compression=False)
except:
raise IOError("Invalid PDB ID: '%s'" % id)
# Create the name of the PDB file.
pdb_file = "%s/%s.pdb" % (tmp_dir.name, id)
# Now write the PDB string to file.
with open(pdb_file, "w") as file:
file.write(pdb_string)
# Read the file and return a molecular system.
return readMolecules(pdb_file, property_map)
def get_pdb(id, cache):
if len(id) > 4:
return get_chain_pdb(id[:4], id[4:], cache)
cache_path = './cache/data/' + id + '.pdb'
if os.path.isfile(cache_path):
return cache_path
if len(id) != 4:
print("BAD ID:", id)
if cache:
print("CACHE MISS WHEN REQUIRED: ", id)
with open(cache_path + ".gz", 'wb') as file:
file.write(pb.get_pdb_file(id, compression=True))
console("unpigz -f -q " + cache_path + ".gz")
return cache_path
def fill_proteins_sequences(proteins_list, folder_path, special_folder):
for protein in proteins_list:
pdb_structure = get_pdb_file(protein.id,
filetype='pdb',
compression=False)
if not os.path.exists(folder_path + '/' + special_folder):
os.makedirs(folder_path + '/' + special_folder)
file = write_to_file(str(protein.id), "pdb", pdb_structure,
folder_path + "/" + special_folder)
protein.sequence = str(extract_sequence(file.name))
return proteins_list
def get_pdb(
): # функция извлекает pdb файлы для каждого pdb_id, содержащегося в k00
conn = sqlite3.connect('test_proteins2.db')
c = conn.cursor()
first_k = c.execute(
"SELECT s_m_title,s_bioluminate_Antigen_Type, s_bioluminate_Antigen_Chain, s_bioluminate_Antigen_Seq FROM 'PrimeStructureDB_DataTable'"
)
k = c.fetchall()
k = [x for x in k if x[1] is not None]
k02 = [k0[2] for k0 in k] # символ цепи, к которой относится антиген
k00 = [k0[0] for k0 in k] # pdb_id из test_proteins2.db
pdbs = [
pypdb.get_pdb_file(k_i, filetype='pdb', compression=False).split('\n')
for k_i in k00[:4]
] # проверила на первых 4 шт.
return pdbs
def fetch_and_save_pdb_file(pdb_code, output_filepath):
"""
Fetch a PDB file from the PDB webserver and save locally.
Parameters
----------
pdb_code : str
PDB code of the protein structure.
output_filepath : str or pathlib.Path
Local filepath (including filename) to save the PDB file in.
Returns
-------
pathlib.Path
The full path of the saved PDB file.
"""
pdb_file_content = pypdb.get_pdb_file(pdb_code)
full_filepath = Path(output_filepath).with_suffix(".pdb")
with open(full_filepath, "w") as f:
f.write(pdb_file_content)
return full_filepath
def download_pdb(pdbid, file_pathway):
"""
Args:
pdbid: 4 letter string specifying the PDB ID of the file yoou want to fix
file_pathway: a string containing the pathway specifying how you want to organize the PDB files once written
Returns: nothing, but it does write the PDB file
***Note: this function does NOT fix any mistakes with the PDB file
"""
if not os.path.exists(file_pathway):
os.makedirs(file_pathway)
if bunit == True:
pdb = get_pdb_biological_unit(pdbid)
else:
pdb = pypdb.get_pdb_file(pdbid)
write_file(os.path.join(file_pathway, '%s.pdb' % pdbid), pdb)
def getPDB(self):
"""
Downloads the PDB file from the Protein Data Bank.
Returns
-------
pdb : str
Returns the absolute path to the PDB file downloaded from the Protein Data Bank.
"""
if self._pdb: return self._pdb
try:
pdb_string = _pypdb.get_pdb_file(self._code,
filetype="pdb",
compression=False)
except:
raise ValueError("Invalid PDB code: '%s'" % self._code)
filename = _os.path.abspath(self._code + ".pdb")
with open(filename, "w") as file:
file.write(pdb_string)
self._pdb = filename
return self._pdb
def process_input_pdb(request):
import pypdb
import re
pdb_file = None
try:
pdb_file = request.FILES['pdb_file']
except:
pass
pdb_search = request.POST.get('pdb_search')
pdb = None
chains = []
if (pdb_file):
pdb = pdb_file.read().decode('utf-8')
if (pdb_search):
pdb = pypdb.get_pdb_file(pdb_search)
if (pdb):
chains = get_chains(pdb)
data = {
'chains': chains
}
return JsonResponse(data)
def _down(pdb, outdir):
check, niter = True, 0
while check and niter < 10:
try:
data = pypdb.get_pdb_file(pdb,
filetype='pdb',
compression=False)
check = False
except:
print('PDBDown -> Issue with :', pdb)
print('Trying again in 5 sec')
niter += 1
time.sleep(5)
if check:
print('PDBdown -> Could not download ', pdb)
return False
else:
fname = os.path.join(outdir, pdb)
fname += '.pdb'
f = open(fname, 'w')
f.write(data)
f.close()
return True
return structureList
ignoreFileList = ["cryoem_n_glycosylated.csv", "xray_n_glycosylated.csv"]
ignoreFileList = [""]
rootDir = os.getcwd()
structureListDir = os.path.join(rootDir, "structures")
for structureListFile in os.listdir(structureListDir):
if structureListFile.endswith(".csv") and structureListFile not in ignoreFileList:
print(structureListFile)
structureListFileName = os.path.splitext(os.path.basename(structureListFile))[0]
outputDir = os.path.join(structureListDir, structureListFileName)
CreateFolder(outputDir)
currentStructureList = GenerateListOfStructures(structureListDir, structureListFile)
for count, pdbID in enumerate(currentStructureList):
print(f'Currently downloading: {pdbID}\nProgress: {count} out of {len(currentStructureList)}\t Progress - {int((count/len(currentStructureList)*100))}%')
newFileName = pdbID + '.pdb'
currentPDB = pdb.get_pdb_file(pdbID, filetype='pdb', compression=False)
WriteFile(outputDir, newFileName, currentPDB)
def get_pdb(ID):
pdb_data = pypdb.get_pdb_file(ID, filetype='cif', compression=False)
return pdb_data
def _fetch_from_rcsb(pdb_id):
pdb_data = pypdb.get_pdb_file(pdb_id, filetype="pdb")
if pdb_data is None:
raise PDBAddError(f"no PDB with ID '{pdb_id}' found")
return pdb_data.encode()
import pypdb
import os
pdbs = ['1ubq']
for p in pdbs:
pdb_file = pypdb.get_pdb_file(p)
with open('{}.pdb'.format(p), 'w') as f:
f.write(pdb_file)
os.system("mkdir {}".format(p))
os.system("mkdir {}/input".format(p))
os.system("mv {}.pdb {}/input".format(p, p))
print("{} done".format(p))
def submit(request):
import subprocess
import os
import re
from . import helpers
from .forms import JobForm
import pypdb
import shutil
pdb_search = request.POST['pdb_search']
pdb_file = None
pdb_filename = None
available_chains = []
def run_script(processed_pdb_filename, job_dir, orig_bin_dir, archive_name):
[os.symlink(os.path.join(os.path.dirname(os.path.realpath(__file__)), '..', orig_bin_dir, f),
os.path.join(job_dir, f)) for f in os.listdir(os.path.join(os.path.dirname(os.path.realpath(__file__)), '..', orig_bin_dir))]
with helpers.change_workingdir(job_dir):
shutil.copy(os.path.join('..', processed_pdb_filename), job_dir)
if job.ph_range:
subprocess.Popen(['./run_pdg-ph.sh', processed_pdb_filename.split('.')[0], 'MC', archive_name], shell=False)
else:
subprocess.Popen(['./run_pdg.sh', str(temperature), str(ph),
processed_pdb_filename, archive_name], shell=False)
if (pdb_search):
pdb = pypdb.get_pdb_file(pdb_search)
pdb_filename = pdb_search + '.pdb'
else:
pdb_file = None
try:
pdb_file = request.FILES['pdb_file']
except:
pass
if (pdb_file):
pdb_filename = re.sub('[^0-9a-zA-Z.]+', '_', pdb_file.name)
pdb = pdb_file.read().decode('utf-8')
available_chains = [[x,x] for x in get_chains(pdb)]
form = JobForm(available_chains, request.POST, request.FILES)
if form.is_valid():
name = form.cleaned_data['name']
temperature = form.cleaned_data['temperature']
ph = form.cleaned_data['ph']
ph_range = form.cleaned_data['ph_range']
email = form.cleaned_data['email']
chain = form.cleaned_data['chain']
tksamc_version = int(form.cleaned_data['tksamc_version'])
job = Job(name=name, ph=ph, ph_range=ph_range,
temperature=temperature, email=email, chain=chain, tksamc_version=tksamc_version)
job.save()
job_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../media/jobs/', str(job.id))
os.makedirs(job_dir)
tksamc_job_dir = None
gtksamc_job_dir = None
if tksamc_version == 1 or tksamc_version == 0:
tksamc_job_dir = os.path.join(job_dir, 'tksamc')
os.makedirs(tksamc_job_dir)
if tksamc_version == 2 or tksamc_version == 0:
gtksamc_job_dir = os.path.join(job_dir, 'gtksamc')
os.makedirs(gtksamc_job_dir)
if (not chain):
chain = ['^\s']
with open(os.path.join(job_dir, pdb_filename), 'w') as destination:
new_pdb = '\n'.join(re.findall(r'^ATOM\s+(?:[^\s]+\s+){3}[%s]\s+.*' % ('|'.join(chain)), pdb, re.MULTILINE))
destination.write(new_pdb)
with helpers.change_workingdir(job_dir):
subprocess.check_output(['/bin/sed', '-i', 's/AALA/ ALA/g;s/ACYS/ CYS/g;s/AASP/ ASP/g;s/AGLU/ GLU/g;s/APHE/ PHE/g;s/AGLY/ GLY/g;s/AHIS/ HIS/g;s/AILE/ ILE/g;s/ALYS/ LYS/g;s/ALEU/ LEU/g;s/AMET/ MET/g;s/AASN/ ASN/g;s/APRO/ PRO/g;s/AGLN/ GLN/g;s/AARG/ ARG/g;s/ASER/ SER/g;s/ATHR/ THR/g;s/AVAL/ VAL/g;s/ATRP/ TRP/g;s/ATYR/ TYR/g', pdb_filename], shell=False)
subprocess.check_output(['/bin/sed', '-i', '/BALA/d;/BCYS/d;/BASP/d;/BGLU/d;/BPHE/d;/BGLY/d;/BHIS/d;/BILE/d;/BLYS/d;/BLEU/d;/BMET/d;/BASN/d;/BPRO/d;/BGLN/d;/BARG/d;/BSER/d;/BTHR/d;/BVAL/d;/BTRP/d;/BTYR/d', pdb_filename], shell=False)
subprocess.check_output(['/usr/bin/gmx', 'editconf', '-f', pdb_filename, '-c', '-resnr',
'1', '-label', 'A', '-o', 'processed_{0}'.format(pdb_filename)], shell=False)
if job.name != '':
base_archive_name = job.name
else:
base_archive_name = str(job.id)
if tksamc_job_dir:
run_script('processed_{0}'.format(pdb_filename),
tksamc_job_dir, 'tksamc_bin', 'tksamc_' + base_archive_name)
if gtksamc_job_dir:
run_script('processed_{0}'.format(pdb_filename),
gtksamc_job_dir, 'gtksamc_bin', 'gtksamc_' + base_archive_name)
if email != '':
job_url = request.build_absolute_uri(
reverse('check_job', args=[job.id]))
helpers.send_email(email, job.name, job_url)
return HttpResponseRedirect(reverse('check_job', args=[job.id]))
else:
return render(request, 'main/index.html', {'form': form, 'nav': 'home'})
