def getPairsOfResiduesInContact(self, structureL, structureR):
'''
Computes which amino acids of ligand are in contact with which amino acids of receptor
@param structureL: Bio.PDB.Structure. Structure of ligand (bound state if available)
@param structureR: Bio.PDB.Structure. Structure of receptor (bound state if available).
@return positiveContacts: Set {(Bio.PDB.Residue.fullResId (from bound structure structureL), Bio.PDB.Residue.fullResId (from bound structure structureR))}
@return chainsNotContactL: Set { str(chainId structureL)}
@return chainsNotContactR: Set { str(chainId structureR)}
'''
try:
atomListL = [
atom for atom in structureL.child_list[0].get_atoms()
if not atom.name.startswith("H")
]
except IndexError:
raise NoValidPDBFile("Problems parsing pdbFile 1")
try:
atomListR = [
atom for atom in structureR.child_list[0].get_atoms()
if not atom.name.startswith("H")
]
except IndexError:
raise NoValidPDBFile("Problems parsing pdbFile 2")
searcher = NeighborSearch(atomListL + atomListR)
allNeigs = searcher.search_all(self.res2res_dist, level="R")
lStructId = structureL.get_id()
rStructId = structureR.get_id()
positiveContacts = set([])
chainsInContactL = set([])
chainsInContactR = set([])
for res1, res2 in allNeigs:
pdbId1, modelId1, chainId1, resId1 = res1.get_full_id()
pdbId2, modelId2, chainId2, resId2 = res2.get_full_id()
fullResId1 = res1.get_full_id()
fullResId2 = res2.get_full_id()
if pdbId1 == lStructId and pdbId2 == rStructId:
positiveContacts.add((fullResId1, fullResId2))
chainsInContactL.add(fullResId1[2])
chainsInContactR.add(fullResId2[2])
elif pdbId1 == rStructId and pdbId2 == lStructId:
positiveContacts.add((fullResId2, fullResId1))
chainsInContactL.add(fullResId2[2])
chainsInContactR.add(fullResId1[2])
if CONSIDER_HOMOOLIG_AS_POS:
positiveContacts, chainsInContactL, chainsInContactR = self.fixHomooligomers(
structureL, structureR, positiveContacts, chainsInContactL,
chainsInContactR)
allChainsL = set([elem.get_id() for elem in structureL[0].get_list()])
allChainsR = set([elem.get_id() for elem in structureR[0].get_list()])
chainsNotContactL = allChainsL.difference(chainsInContactL)
chainsNotContactR = allChainsR.difference(chainsInContactR)
return positiveContacts, chainsNotContactL, chainsNotContactR
def getPairsOfResiduesInContact(self, structureL, structureR):
'''
Computes which amino acids of ligand are in contact with which amino acids of receptor
:param structureL: Bio.PDB.Structure. Structure of ligand unbound state if available
:param structureR: Bio.PDB.Structure. Structure of receptor unbound state if available.
:return positiveContacts, chainsNotContactL, chainsNotContactR
positiveContacts: Set {( Bio.PDB.Residue.fullResId (from bound structure structureL),
Bio.PDB.Residue.fullResId (from bound structure structureR) )
}
chainsNotContactL: Set { Bio.PDB.Chain.get_id()} for ligand chains that are not in contact
chainsNotContactR: Set { Bio.PDB.Chain.get_id()} for receptor chains that are not in contact
'''
try:
atomListL = [
atom for atom in structureL.child_list[0].get_atoms()
if not atom.name.startswith("H")
]
except IndexError:
raise NoValidPDBFile("Problems parsing pdbFile 1")
try:
atomListR = [
atom for atom in structureR.child_list[0].get_atoms()
if not atom.name.startswith("H")
]
except IndexError:
raise NoValidPDBFile("Problems parsing pdbFile 2")
searcher = NeighborSearch(atomListL + atomListR)
allNeigs = searcher.search_all(self.res2res_dist, level="R")
lStructId = structureL.get_id()
rStructId = structureR.get_id()
positiveContactsResidues = set([])
chainsInContactL = set([])
chainsInContactR = set([])
for res1, res2 in allNeigs:
pdbId1, modelId1, chainId1, resId1 = res1.get_full_id()
pdbId2, modelId2, chainId2, resId2 = res2.get_full_id()
if pdbId1 == lStructId and pdbId2 == rStructId:
positiveContactsResidues.add((res1, res2))
chainsInContactL.add(chainId1)
chainsInContactR.add(chainId2)
elif pdbId1 == rStructId and pdbId2 == lStructId:
positiveContactsResidues.add((res2, res1))
chainsInContactL.add(chainId2)
chainsInContactR.add(chainId1)
allChainsL = set([elem.get_id() for elem in structureL[0].get_list()])
allChainsR = set([elem.get_id() for elem in structureR[0].get_list()])
chainsNotContactL = allChainsL.difference(chainsInContactL)
chainsNotContactR = allChainsR.difference(chainsInContactR)
return positiveContactsResidues, chainsNotContactL, chainsNotContactR
def checkIfSuccess(fname, maxNumberOfChains=MAX_NUMBER_OF_CHAINS):
try:
parser = myPDBParser()
struct = parser.get_structure("pdb", fname)
if not 0 in struct:
return False
if len(struct[0]) > maxNumberOfChains:
raise NoValidPDBFile(
"The maximun number of allowed chains is %d (%d) for %s" %
(maxNumberOfChains, len(struct[0]), pdbId))
return True
except (Exception, ValueError) as e:
print(e)
if isinstance(e, NoValidPDBFile):
raise e
return False
def downloadUsingMmtf(pdbId, fnameOut, maxNumberOfChains=MAX_NUMBER_OF_CHAINS):
print("downloadUsingMmtf")
try:
parser = MMTFParser()
struct = parser.get_structure_from_url(pdbId)
if not 0 in struct:
return False
if len(struct[0]) > maxNumberOfChains:
raise NoValidPDBFile(
"The maximun number of allowed chains is %d (%d) for %s" %
(maxNumberOfChains, len(struct[0]), pdbId))
writter = PDBIO()
writter.set_structure(struct)
writter.save(fnameOut)
return True
except (Exception, ValueError, HTTPError) as e:
print(e)
if isinstance(e, NoValidPDBFile):
raise e
return False
def createFileForError(self, pdbStruct, outName):
'''
Creates a fake DSSP raw output generated when DSSP fails. All residues will be assigned secStruc= Z
@param pdbStruct: Bio.PDB.Structure. Structure of the psb that is being analyzed
@param outName: str. output fname
'''
oneResLine = "%5d%5d%2s%2s %2s\n"
try:
f = open(outName, "w")
f.write(DsspComputer.DSSP_HEADER)
if len(pdbStruct) == 0:
raise NoValidPDBFile(
"No valid pdb File. There are no models contained")
for chain in pdbStruct[0]:
for i, res in enumerate(chain):
if not is_aa(res): continue
## print i,res,res.get_id()
seqIndex = i + 1
structIndex = res.get_id()[1]
letter = self.threeLetterAA_to_one(res.resname)
fakeSecStruct = "Z"
fakeCharacters1 = tuple("f" * 7)
fakeDigits1 = tuple([0, 0, "f", 0])
fakeStrs = tuple("f" * 4)
fakeFloats = tuple(elem + 0.0 for elem in range(8))
## print ((seqIndex,structIndex, chain.get_id(), letter, fakeSecStruct)+
## fakeCharacters1+fakeDigits1+fakeStrs+fakeFloats)
## print oneResLine%( (seqIndex,structIndex, chain.get_id(), letter, fakeSecStruct)+
## fakeCharacters1+fakeDigits1+fakeStrs+fakeFloats)
f.write(oneResLine %
(seqIndex, structIndex, chain.get_id(), letter,
fakeSecStruct))
f.close()
except (KeyboardInterrupt, Exception):
print("Exception happend computing %s" % outName)
tryToRemove(outName)
raise
return 0
def computeFeaturesOneComplex(self,
fnameL,
fnameR,
lPdbId=None,
rPdbId=None,
isHomoComplex=False):
'''
Computes all features needed for complex codification.
:param fnameL: str. Path to the the pdb or fasta file of the ligand of the complex
:param fnameR: str. Path to the the pdb or fasta file of the receptor of the complex
:param lPdbId: str. pdbId of receptor in order to query 3dCons. If None, psiblast will be launched directly
:param rPdbId: str. pdbId of receptor in order to query 3dCons. If None, psiblast will be launched directly
:param isHomoComplex: boolean. If True, just lPartner is provided and both partners are equal.
'''
prefixL, chainTypeL = self.splitExtendedPrefix(
self.getExtendedPrefix(fnameL))[:2]
prefixR, chainTypeR = self.splitExtendedPrefix(
self.getExtendedPrefix(fnameR))[:2]
assert prefixL == prefixR, "Error, prefixes are different for %s - %s" % (
fnameL, fnameR)
structureL, __ = loadPdbIfIsPath(
fnameL) #structureL will be none if fnameL is a fasta file
structureR, __ = loadPdbIfIsPath(
fnameR) #structureR will be none if fnameL is a fasta file
if (structureL is None
or structureR is None) and self.areForTrainAndTest:
raise NoValidPDBFile(
"Error, Training requeries both inputs to be pdbs. \n" +
"For prediction they can be either pdbs or sequences. You are training"
)
cMapper = ContactMapper(self.prefix,
computedFeatsRootDir=self.computedFeatsRootDir,
areForTrainAndTest=self.areForTrainAndTest,
boundAvailable=self.boundAvailable,
statusManager=self.statusManager)
if isHomoComplex and not self.areForTrainAndTest:
resDictL, resDictR = cMapper.computeComplex(
fnameL, None, structureL, None)
else:
resDictL, resDictR = cMapper.computeComplex(fnameL,
fnameR,
structureL,
structureR,
isHomoLR=isHomoComplex)
seqFeatComputer = SeqFeatComputer(
self.prefix,
computedFeatsRootDir=self.computedFeatsRootDir,
statusManager=self.statusManager)
if not self.methodProtocol.startswith("seq"):
structComputer = StructFeatComputer(
self.prefix,
computedFeatsRootDir=self.computedFeatsRootDir,
statusManager=self.statusManager)
if isHomoComplex and not self.areForTrainAndTest:
structComputer.computeComplex(fnameL, None, structureL, None)
else:
structComputer.computeComplex(fnameL, fnameR, structureL,
structureR)
seqFeatComputer.computeComplex(fnameL,
fnameR,
structureL,
structureR,
lPdbId=lPdbId,
rPdbId=rPdbId,
areLRequivalentProteins=isHomoComplex
and not self.areForTrainAndTest)
if isHomoComplex and not self.areForTrainAndTest:
self.copyFeaturesToReceptor(
fnameL,
fnameR,
isSeqInput=self.methodProtocol.startswith("seq"))
def downloadPDB(pdbId,
pdbOutPath,
chainId=None,
bioUnit=None,
removeOtherChains=False,
checkObsolete=True):
if not len(pdbId) == 4:
raise ValueError("bad format pdbId '%s'" % (pdbId))
pdbId = pdbId.lower()
outName = os.path.join(pdbOutPath, pdbId + '.pdb')
print("Trying to download pdbId %s to %s" % (pdbId, outName))
success = False
if not os.path.isfile(outName):
if not bioUnit:
success = downloadUsingMmtf(pdbId, outName)
if not success or bioUnit:
if checkObsolete:
r = requests.get(
"https://www.ebi.ac.uk/pdbe/api/pdb/entry/summary/%s" %
(pdbId))
if r.status_code != 200:
raise ValueError(
"pdb id %s does not exist according to https://www.ebi.ac.uk/pdbe/api/pdb/entry/summary/%s. It may be obsolete or cif"
% (pdbId, pdbId))
if bioUnit:
cmd = 'wget -qO- ftp://ftp.wwpdb.org/pub/pdb/data/biounit/coordinates/all/%s.pdb%d.gz --timeout=30 | zcat > %s' % (
pdbId, bioUnit, outName)
else:
cmd = 'wget -qO- http://www.rcsb.org/pdb/files/%s.pdb.gz --timeout=30 | zcat > %s' % (
pdbId, outName)
print(cmd)
p = Popen(cmd, stdin=PIPE, stdout=PIPE, stderr=PIPE, shell=True)
out = p.communicate()
if len(out[1]) > 0 or not checkIfSuccess(outName):
print(out)
try:
os.remove(outName)
except OSError:
pass
msg= "Error downloading pdb_id: %s biounit: %s. Does biounit exists?"%(pdbId, bioUnit) if bioUnit else \
"Error downloading pdb_id: %s"%pdbId
raise NoValidPDBFile(msg)
else:
print("Already downloaded pdb_id %s" % (pdbId))
if not chainId is None:
print("extracting chain '%s'" % (chainId))
try:
splitter = ChainSplitter(os.path.split(outName)[0])
outName_extract = splitter.make_pdb(outName,
chainId,
rejectInsteadAccept=False)
# print(outName_extract, outName)
if removeOtherChains:
os.remove(outName)
except NoChainInPdb:
raise
except (ValueError, OSError):
try:
os.remove(outName_extract)
except (OSError, UnboundLocalError):
pass
raise
return outName_extract
else:
return outName
def prepareInput(allRootDir,
idName,
pdbId,
fname,
sequence,
chainType="l",
removeInputs=False):
'''
:param allRootDir: str. Path where files will be generated
:param idName: an id for the complex, typically a pdbId
:param pdbId: A pdbId, potentially augmented with chainId and bioUnit info.
:param fname: str. A path to a fasta or pdb file. Ignored if pdbId provided
:param sequence: str. A sequence of amino acids. Ignored if pdbId or fname provided
:param chainType: "l" or "r"
:param removeInputs: bool. Remove input files
'''
assert chainType in ["l",
"r"], "Error, chain type must be either 'l' or 'r'"
finalInputPath = myMakeDir(allRootDir, "finalInput")
newFname = os.path.join(finalInputPath,
"%s_%s_u.pdb" % (idName, chainType))
if pdbId and fname is None and sequence is None:
print("%s_%s" % (pdbId, chainType))
matchObj = re.match(r"(^\d[a-zA-Z0-9]{3})(:[a-zA-Z0-9])?(_\d*)?$",
pdbId)
if matchObj:
pdbId = matchObj.group(1)
chainId = matchObj.group(2)
biounit = matchObj.group(3)
isThisParnerSeq = False
if not chainId is None: chainId = chainId[1:]
if biounit is None or len(biounit) == 1: biounit = None
else:
biounit = int(biounit[1:])
if biounit == 0: biounit = None
try:
fname = downloadPDB(pdbId,
finalInputPath,
chainId=chainId,
bioUnit=biounit,
removeOtherChains=removeInputs)
print(type(fname), fname)
except ValueError as e:
traceback.print_exc()
raise NoAvailableForDownloadPDB(str(e) + "-> %s" % (pdbId))
try:
if not removeInputs:
shutil.copyfile(fname, newFname)
else:
os.rename(fname, newFname)
except OSError:
NoAvailableForDownloadPDB(
"Error. pdb %s was not recover from wwpdb.org" % pdbId)
else:
raise NoAvailableForDownloadPDB("Error: bad pdb provided %s" %
(pdbId))
elif fname:
if checkIfIsFasta(fname):
sequence = parseFasta(fname)
if removeInputs:
os.remove(fname)
isThisParnerSeq = True
else: #check if fname is valid pdb
success = moveAndWriteAsPDBIfMmcif(fname,
newFname,
removeInput=removeInputs)
if not success:
raise NoValidPDBFile(
"Error. It was not possible to parse your pdb file %d" %
(1 if chainType == "l" else 2))
isThisParnerSeq = False
elif sequence:
sequence = parseSeq(sequence)
isThisParnerSeq = True
else:
raise ValueError(
"One of the following arguments should be provided pdbId, fname, sequence"
)
if sequence: #Save sequence
newFname = os.path.join(finalInputPath,
"%s_%s_u.fasta" % (idName, chainType))
with open(newFname, "w") as f:
f.write(">" + os.path.basename(newFname) + "\n" + sequence)
return isThisParnerSeq, newFname, pdbId