def __init__(self,
num,
assign,
ppm,
width,
box,
shape,
volume,
intensity,
status,
isReading=True):
self.num = returnInt(num, default=None)
self.volume = self.returnFloat(volume)
self.intensity = self.returnFloat(intensity)
self.status = returnInt(status, default=None)
self.shape = shape[:]
self.assign = []
self.ppm = []
self.width = [] # In ppm!!
self.box = [] # In ppm!!
for i in range(0, len(assign)):
self.ppm.append(self.returnFloat(ppm[i]))
self.width.append(self.returnFloat(width[i]))
self.box.append(self.returnFloat(box[i]))
# Get rid of ?, when reading
if isReading and assign[i] == '?':
assign[i] = None
self.assign.append(assign[i])
def __init__(self,
parent,
serial,
atomName,
resName,
chainId,
seqCode,
x,
y,
z,
segId,
insertionCode=defaultSeqInsertCode):
self.parent = parent
self.serial = returnInt(serial)
self.atomName = string.strip(atomName)
self.resName = string.strip(resName)
self.chainId = chainId
self.seqCode = returnInt(seqCode)
self.x = returnFloat(x)
self.y = returnFloat(y)
self.z = returnFloat(z)
self.segId = string.strip(segId)
self.insertionCode = insertionCode
if not self.segId:
self.segId = self.chainId
def __init__(self,
serial,
atomName,
seqCode,
resName,
chainId,
x,
y,
z,
insertionCode=defaultSeqInsertCode,
refChainId=None,
verbose=False):
self.serial = returnInt(serial, verbose=verbose)
self.atomName = atomName.strip()
self.seqCode = returnInt(seqCode, verbose=verbose)
self.resName = resName.strip()
self.chainId = chainId
self.x = returnFloat(x, default=None, verbose=verbose)
self.y = returnFloat(y, default=None, verbose=verbose)
self.z = returnFloat(z, default=None, verbose=verbose)
self.segId = ''
self.insertionCode = insertionCode
if refChainId:
self.refChainId = refChainId
else:
self.refChainId = chainId
def __init__(self,
num,
ppm,
colour,
userCode,
volume,
volumeError,
intCode,
assign,
verbose=False,
comment=None,
textAssign=False):
self.num = returnInt(num, default=None, verbose=verbose)
self.volume = returnFloat(volume, default=None, verbose=verbose)
self.volumeError = returnFloat(volumeError,
default=None,
verbose=verbose)
self.colour = returnInt(colour, default=None, verbose=verbose)
self.userCode = userCode
self.intCode = intCode
self.comment = comment
self.textAssign = textAssign
self.ppm = []
self.assign = []
self.ambiguousAssign = []
for i in range(len(assign)):
self.ppm.append(returnFloat(ppm[i], default=None, verbose=verbose))
self.assign.append(self.getAssignmentValue(assign[i]))
def read(self, verbose=0):
if verbose == 1:
print "Reading %s assignment file %s" % (self.format, self.name)
fin = open(self.name, 'rU')
# Read, look for first line
line = fin.readline()
while line:
cols = line.split()
if self.patt['emptyline'].search(line) or self.patt['hash'].search(
line):
pass
if len(cols) == 3:
(ccpCode, seqId) = cols[0].split(self.residueSep)
(void, spinSystemId) = cols[1].split(self.residueSep)
reliability = cols[2][1]
self.assignments.append(
MarsAssignment(returnInt(spinSystemId), returnInt(seqId),
ccpCode, reliability))
line = fin.readline()
fin.close()
def __init__(self,
serial,
atomName,
resName,
segId,
seqCode,
x,
y,
z,
insertionCode=defaultSeqInsertCode,
altLoc=defaultAltLoc,
chainId=None):
self.serial = returnInt(serial)
self.atomName = atomName.strip()
self.resName = resName.strip()
self.seqCode = returnInt(seqCode)
self.x = returnFloat(x)
self.y = returnFloat(y)
self.z = returnFloat(z)
self.insertionCode = insertionCode
self.altLoc = altLoc
self.segId = segId.strip()
if chainId == None:
self.chainId = self.segId
if not self.chainId:
self.chainId = defaultMolCode
else:
self.chainId = chainId
def __init__(self, parent, atomSerial, x, y, z, atomType, massDiff, charge,
Hcount, stereoCare, valence):
self.parent = parent
self.parent.numAtoms -= 1
self.serial = atomSerial
self.x = returnFloat(x, verbose=0)
self.y = returnFloat(y, verbose=0)
self.z = returnFloat(z, verbose=0)
"""
entry in periodic table or L for atom list,
A, Q, * for unspecified atom, and LP for
lone pair, or R# for Rgroup label
"""
atomType = string.strip(atomType)
if atomType in ['A', 'Q', '*']:
atomType = None
elif atomType == 'LP':
atomType = None
#atomType = 'lone pair' TODO TODO can't handle this yet
self.atomType = atomType
"""
-3, -2, -1, 0, 1, 2, 3, 4
(0 if value beyond these limits)
"""
self.massDiff = returnInt(massDiff, verbose=0)
"""
0 = uncharged or value other than these,
1 = +3, 2 = +2, 3 = +1,
4 = doublet radical, 5 = -1, 6 = -2, 7 = -3
"""
chargeCode = returnInt(charge, verbose=0)
self.charge = [0, 3, 2, 1, 'dr', -1, -2, -3][chargeCode]
"""
1 = H0, 2 = H1, 3 = H2, 4 = H3, 5 = H4
"""
self.Hcount = returnInt(Hcount, verbose=0) - 1
"""
0 = ignore stereo configuration of this
double bond atom, 1 = stereo
configuration of double bond atom
must match
"""
self.stereoCare = returnInt(stereoCare, verbose=0)
"""
0 = no marking (default)
(1 to 14) = (1 to 14) 15 = zero valence
"""
self.valence = returnInt(valence, verbose=0)
def setAtomMembers(self, chainCode, seqCode1, atomName1, seqCode2,
atomName2):
self.items.append(ModuleConstraintItem())
self.items[-1].members.append(
ModuleConstraintMember(chainCode, returnInt(seqCode1),
string.upper(atomName1)))
self.items[-1].members.append(
ModuleConstraintMember(chainCode, returnInt(seqCode2),
string.upper(atomName2)))
def __init__(self, Id, origId, patt=None, format=None):
self.Id = returnInt(Id)
if origId != None:
self.origId = returnInt(origId)
else:
self.origId = None
self.items = []
self.patt = patt
self.format = format
def __init__(self,serial,chainId,atomName,resName,seqCode,x,y,z, insertionCode = defaultSeqInsertCode):
self.serial = returnInt(serial)
self.atomName = atomName.strip()
self.resName = resName.strip()
self.seqCode = returnInt(seqCode)
self.x = returnFloat(x)
self.y = returnFloat(y)
self.z = returnFloat(z)
self.insertionCode = insertionCode
self.chainId = chainId
def __init__(self,serial,atomName,resName,segId,seqCode,segSeqCode,x,y,z, insertionCode = defaultSeqInsertCode,verbose=False):
self.serial = returnInt(serial,verbose=verbose)
self.atomName = string.strip(atomName)
self.resName = string.strip(resName)
self.seqCode = returnInt(seqCode,verbose=verbose)
self.segSeqCode = returnInt(segSeqCode,verbose=verbose)
self.x = returnFloat(x,default=None,verbose=verbose)
self.y = returnFloat(y,default=None,verbose=verbose)
self.z = returnFloat(z,default=None,verbose=verbose)
self.insertionCode = insertionCode
self.chainId = self.segId = string.strip(segId)
if not self.chainId:
self.chainId = defaultMolCode
def getPdbChainInfo():
"""
Read info on chain information of PDB entries
"""
pdbChainInfoDict = {}
dataLines = getReferenceTextFileFromHttp(pdbChainInfoUrl,pdbChainInfoFilePath,refText = "PDB entry chain information", isGzipped = True)
for dataLine in dataLines:
cols = dataLine.split()
if cols and cols[0][0] == '>':
(pdbCode,chainCode) = cols[0][1:].split("_")
molType = cols[1][4:]
chainLength = returnInt(cols[2][7:])
molName = ' '.join(cols[3:])
if not pdbChainInfoDict.has_key(pdbCode):
pdbChainInfoDict[pdbCode] = {}
pdbChainInfoDict[pdbCode][chainCode] = [chainLength,molName,None]
else:
pdbChainInfoDict[pdbCode][chainCode][2] = cols[0]
return pdbChainInfoDict
def setRdcData(self,value,error=0.00, energyCst=1.0, orientation=0): self.error = returnFloat(error) self.value = returnFloat(value) self.energyCst = returnFloat(energyCst) self.orientation = returnInt(orientation)
def readDsspInfoFile(self, fileName):
fin = open(fileName)
lines = fin.readlines()
fin.close()
dataLine = False
for line in lines:
cols = line.split()
if cols[0] == '#' and cols[1] == 'RESIDUE':
dataLine = True
elif dataLine:
# Note; No insertion code?
seqCodeStr = line[5:10]
seqCodeStr = seqCodeStr.strip()
if len(seqCodeStr) < 1:
# happens for PDB entry 1cjg for 2 residues
# and for 2k6q for 2 residues.
nTdebug("Skipping DSSP line for Vasco with empty seqCode string: " + line.strip())
continue
seqCode = returnInt(seqCodeStr)
chainCode = line[11:12]
secStruc = line[16:17]
if not self.allSsInfo.has_key(chainCode):
self.allSsInfo[chainCode] = {}
seqKey = (seqCode, ' ')
if not self.allSsInfo[chainCode].has_key(seqKey):
self.allSsInfo[chainCode][seqKey] = []
self.allSsInfo[chainCode][seqKey].append(secStruc)
def setAtomMembers(self, chainCode, seqCode, resLabel, refAtomName):
refAtom = self.cyanaLib.findAtom(resLabel, refAtomName)
seqCode = returnInt(seqCode)
if refAtom:
if refAtom.bondedAtomSerials.count(0) != 3:
print " Error: invalid single atom %s (%s %s, chain '%s'). No or multiple bonded atoms" % (
refAtomName, resLabel, seqCode, chainCode)
else:
self.items.append(DyanaConstraintItem())
self.items[-1].members.append(
DyanaConstraintMember(chainCode, seqCode, resLabel,
refAtomName))
atomSerial = refAtom.bondedAtomSerials[0]
bondedAtom = self.cyanaLib.findAtomBySerial(
resLabel, atomSerial)
self.items[-1].members.append(
DyanaConstraintMember(chainCode, seqCode, resLabel,
bondedAtom.name))
else:
print " Error: cannot write RDC restraint, atom %s for residue %s not found." % (
refAtomName, resLabel)
def __init__(self,
numPoints,
numPointsOrig,
valuePerPoint,
nucleus,
phase=None):
self.numPoints = returnInt(numPoints)
self.numPointsOrig = returnInt(numPointsOrig)
self.valuePerPoint = returnFloat(valuePerPoint)
self.nucleus = nucleus
if phase:
self.phase = returnFloats(phase)
else:
self.phase = 2 * [0.0]
def __init__(self, parent, peakNum):
self.peakNum = returnInt(peakNum)
self.parent = parent
self.assignments = []
self.assignCombinations = []
def __init__(self,serial,name,atomSerials): self.serial = returnInt(serial) self.name = name self.atomSerials = returnInts(atomSerials) self.atomNames = [] self.atoms = []
def read(self, isOutputFile=False, headerCols=None, verbose=0):
if verbose == 1:
print "Reading %s chemical shift list %s" % (self.format,
self.name)
fin = open(self.name, 'rU')
headerCols = []
line = fin.readline()
while line:
if self.patt['emptyline'].search(line):
line = fin.readline()
continue
#
# Get the info...
#
cols = line.split()
if cols[0].count('NUM'):
headerCols = line.split()
colLen = len(headerCols)
elif len(cols) == colLen and not cols[0].count("-"):
badShifts = False
# These are fishy shifts, need to remove the *!
if cols[0][0] == '*':
cols[0] = cols[0][1:]
badShifts = True
seqCode = returnInt(cols[0], default=None, verbose=False)
resLabel = cols[1]
if seqCode != None:
self.seqCodeLabels[seqCode] = resLabel
for i in range(2, colLen):
atomName = headerCols[i]
value = returnFloat(cols[i],
default=None,
verbose=False)
# Ignore if value is 0.00. This is stupid but has to be done because format is set up this way.
if value != 0.00:
self.chemShifts.append(
self.shiftClass(self, value, atomName, seqCode,
resLabel, self.defaultMolCode))
line = fin.readline()
fin.close()
def setOriginalData(format,parent,rawData,name,isUnique = True):
#
# Code to set original data in the data model as application data
#
if hasattr(rawData,name):
keyword = 'orig' + name[0].upper() + name[1:]
value = getattr(rawData,name)
appDataClass = None
if value != None:
if type(returnInt(value,default=None,verbose=0)) == type(value):
appDataClass = 'AppDataInt'
elif type(returnFloat(value,default=None,verbose=0)) == type(value):
appDataClass = 'AppDataFloat'
elif type(returnLong(value,default=None,verbose=0)) == type(value):
appDataClass = 'AppDataLong'
if not appDataClass:
appDataClass = 'AppDataString'
value = str(value)
if isUnique:
setUniqueAppData(appDataClass,parent,format,keyword,value)
else:
appData = getattr(Implementation,appDataClass)(application = format,keyword = keyword,value = value)
parent.addApplicationData(appData)
return True
return False
def read(self, verbose=0):
#
# TODO TODO not sure if this is correct!!! Check!
#
if verbose == 1:
print "Reading %s sequence file %s" % (self.format, self.name)
self.sequences.append(PippSequence())
seqCode = 1
fin = open(self.name, 'rU')
# Read, look for first line
line = fin.readline()
while line:
cols = line.split()
if len(cols) == 0 or self.patt['hash'].search(line):
pass
else:
if len(cols) == 2:
seqCode = returnInt(cols[1])
self.sequences[-1].elements.append(
PippSequenceElement(seqCode, cols[0]))
seqCode += 1
line = fin.readline()
fin.close()
def __init__(self, parent, atomSerial1, atomSerial2, bondType, bondStereo,
bondTopology):
self.parent = parent
self.parent.numBonds -= 1
self.atomSerial1 = returnInt(atomSerial1, verbose=0)
self.atom1 = self.parent.atoms[self.atomSerial1 - 1]
self.atomSerial2 = returnInt(atomSerial2, verbose=0)
self.atom2 = self.parent.atoms[self.atomSerial2 - 1]
"""
1 = Single, 2 = Double,
3 = Triple, 4 = Aromatic,
5 = Single or Double,
6 = Single or Aromatic,
7 = Double or Aromatic, 8 = Any
"""
bondTypeCode = returnInt(bondType, verbose=0)
self.bondType = [
'void', 'single', 'double', 'triple', 'aromatic', 'single/double',
'single/aromatic', 'double/aromatic', 'unknown'
][bondTypeCode]
"""
Single bonds: 0 = not stereo,
1 = Up, 4 = Either,
6 = Down,
Double bonds: 0 = Use x-, y-, z-coords
from atom block to determine cis or trans,
3 = Cis or trans (either) double bond
"""
bondStereoCode = returnInt(bondStereo, verbose=0)
if self.bondType == 'single':
self.bondStereo = [None, 'up', None, None, 'either', None,
'down'][bondStereoCode]
elif self.bondType == 'double':
self.bondStereo = ['coordinates', None, None,
'either'][bondStereoCode]
"""
0 = Either, 1 = Ring, 2 = Chain
"""
bondTopologyCode = returnInt(bondTopology, verbose=0)
self.bondTopology = ['either', 'ring', 'chain'][bondTopologyCode]
def read(self, verbose=0):
if verbose == 1:
print "Reading %s sequence file %s" % (self.format, self.name)
self.sequences.append(ShiftxSequence())
fin = open(self.name, 'rU')
headerCols = []
# Read, look for first line
line = fin.readline()
colLen = None
lastSeqCode = None
while line:
if self.patt['emptyline'].search(line):
line = fin.readline()
continue
#
# Get the info...
#
cols = line.split()
if cols[0] == 'NUM' and not colLen:
headerCols = line.split()
colLen = len(headerCols)
elif len(cols) == colLen and not cols[0].count("-"):
# These are fishy shifts, need to remove the *!
if cols[0][0] == '*':
cols[0] = cols[0][1:]
seqCode = returnInt(cols[0])
resLabel = cols[1]
if lastSeqCode == None:
lastSeqCode = seqCode
elif lastSeqCode != seqCode - 1:
for tmpSeqCode in range(lastSeqCode + 1, seqCode):
self.sequences[-1].elements.append(
ShiftxSequenceElement(tmpSeqCode, 'X'))
lastSeqCode = seqCode
else:
lastSeqCode = seqCode
self.sequences[-1].elements.append(
ShiftxSequenceElement(seqCode, resLabel))
line = fin.readline()
fin.close()
def readGeneric(self,verbose = 0):
if verbose == 1:
print "Reading %s file %s" % (self.format,self.name)
#
# Read all information...
#
fin = open(self.name, 'rU')
line = fin.readline()
triposSection = None
while line:
if self.patt['emptyline'].search(line):
line = fin.readline()
continue
triposTagSearch = self.patt[self.format + 'TriposTag'].search(line)
if triposTagSearch:
triposSection = triposTagSearch.group(1).strip()
sectionLine = 0
if not self.infoDict.has_key(triposSection):
self.infoDict[triposSection] = {}
elif triposSection:
sectionLine += 1
if triposSection == 'MOLECULE':
if sectionLine in (1,3,4,5,6):
infoName = self.readDict[triposSection][sectionLine][0]
self.infoDict[triposSection][infoName] = line.strip()
elif sectionLine == 2:
numbers = line.split()
for i in range(len(numbers)):
infoName = self.readDict[triposSection][sectionLine][i]
self.infoDict[triposSection][infoName] = returnInt(numbers[i])
elif triposSection in ('ATOM','BOND','SUBSTRUCTURE'):
if not self.infoDict[triposSection]:
self.infoDict[triposSection] = []
self.infoDict[triposSection].append({})
atomCols = line.split()
for i in range(len(atomCols)):
(infoName,returnFunc) = self.readDict[triposSection][i]
self.infoDict[triposSection][-1][infoName] = returnFunc(atomCols[i])
line = fin.readline()
fin.close()
def __init__(self, serial, chainCode, seqCode, atomName, atomNumber,
resName, x, y, z):
self.serial = returnInt(serial)
self.atomName = atomName.strip()
self.atomNumber = returnInt(atomNumber)
self.resName = resName.strip().upper()
self.seqCode = seqCode
self.chainCode = chainCode.strip()
self.x = returnFloat(x)
self.y = returnFloat(y)
self.z = returnFloat(z)
# Not supported
self.insertionCode = defaultSeqInsertCode
self.chainId = defaultMolCode
def __init__(self,Id,name,cyanaLib,verbose=False): self.Id = returnInt(Id,default=None,verbose=verbose) self.items = [] self.name = name self.seqCode = None self.cyanaLib = cyanaLib
def __init__(self,serial,name,atomType,bondedAtomSerials): self.serial = returnInt(serial) self.name = name self.atomType = atomType self.location = 0 self.bondedAtomSerials = returnInts(bondedAtomSerials)
def __init__(self,parent,atomSerial,value,valueError,atomName,seqCode,verbose=False): self.atomSerial = returnInt(atomSerial,default=None,verbose=verbose) self.value = returnFloat(value,default=None,verbose=verbose) self.valueError = returnFloat(valueError,default=None,verbose=verbose) self.atomName = atomName (self.seqCode,self.seqInsertCode) = getSeqAndInsertCode(seqCode) self.molCode = parent.defaultMolCode
def getAssignmentValue(self, assignInitValue):
if not self.textAssign:
assignValue = returnInt(assignInitValue, default=None)
else:
assignValue = assignInitValue
return assignValue
def setValue(self, valueKey, values):
if len(values) == 1 and type(values[0]) == type(''):
value = values[0]
if not self.parent.patt['emptyline'].search(value):
if valueKey == 'num':
self.num = returnInt(value)
elif valueKey == 'assignment':
assignment = value.strip()
self.assign = assignment.split(self.parent.assignSep)
elif self.intensity == None and valueKey in ('dataHeight',
'height'):
self.intensity = returnFloat(value)
elif valueKey == 'fitHeight':
self.intensityFit = returnFloat(value)
elif valueKey == 'intensity':
self.intensity = returnFloat(value)
elif valueKey == 'volume':
(volume, volumeMethod) = value.strip().split()
self.volume = returnFloat(volume)
if volumeMethod == 'ga':
self.volumeMethod = 'Gaussian'
elif volumeMethod == 'lo':
self.volumeMethod = 'Lorentzian'
elif volumeMethod == 'bx':
self.volumeMethod = 'Sum over box'
elif volumeMethod == 'el':
self.volumeMethod = 'Sum over ellipse'
elif volumeMethod == '--':
self.volumeMethod = 'Unknown method'
else:
self.volumeMethod = 'Unknown method'
print " Error: unknown volume method %s in sparky peaks file (please define)." % volumeMethod
elif len(values) >= 1:
if valueKey == 'freqDimsPpm':
self.ppm = returnFloats(values)
elif valueKey == 'freqDimsHz':
self.hz = returnFloats(values)
elif valueKey == 'freqDimsWidth':
self.widths = returnFloats(values[:-1])
else:
print " Warning: empty data field for Sparky peak file."
pass
def __init__(self,serial,atomName,resName,segId,seqCode,x,y,z, insertionCode = defaultSeqInsertCode):
self.serial = returnInt(serial)
self.atomName = atomName.strip()
self.resName = resName.strip()
self.seqCode = returnInt(seqCode)
self.x = returnFloat(x)
self.y = returnFloat(y)
self.z = returnFloat(z)
self.insertionCode = insertionCode
self.chainId = self.segId = segId.strip()
if not self.chainId:
self.chainId = defaultMolCode
# Hack - the naming system is otherwise an esoteric mix of other ones
if self.atomName == 'HN':
self.atomName = 'H'
def readWhatIfAsaInfoFile(self, fileName):
'Return True on error.'
# nTdebug('Now in ' + getCallerName() + ' for ' + fileName)
fin = open(fileName)
lines = fin.readlines()
fin.close()
atomsRead = 0
_hydrogensSkipped = 0
skipHydrogens = False # already corrected for elsewhere?
# dataLine = False
for line in lines:
line = line.strip()
# nTdebug('Line: ' + line)
if line[0] == '*' or not line:
continue
fields = line.split(';')
resLabel = fields[1]
seqId = fields[2]
insertionCode = fields[3]
chainCode = fields[4]
# field 5 has nothing?
atomName = fields[6]
accessibility = fields[7]
if skipHydrogens and atomName[0] == 'H':
_hydrogensSkipped += 1 # are zero anyway.
continue
if not insertionCode:
insertionCode = ' '
seqKey = (returnInt(seqId), insertionCode)
if not (accessibility[0] == '|' and accessibility[-1] == '|'):
nTerror("Skipping line without valid format for accessibility: " + line)
continue
if len(accessibility) < 3:
nTerror("Skipping line with too short accessibility string: " + line)
continue
accessibilityStr = accessibility[1:-1]
accessibilityStr = accessibilityStr.strip()
if len(accessibilityStr) < 1:
nTerror("Skipping line with empty accessibility string: " + line) # happens for PDB entry 1cjg for 2 residues
continue
accessibility = returnFloat(accessibilityStr)
d = self.allWhatIfInfo['chains']
if not d.has_key(chainCode):
d[chainCode] = {}
if not d[chainCode].has_key(seqKey):
d[chainCode][seqKey] = {'hasBadAtoms': False, 'resLabel': resLabel, 'atoms': {}}
if not d[chainCode][seqKey]['atoms'].has_key(atomName):
d[chainCode][seqKey]['atoms'][atomName] = []
d[chainCode][seqKey]['atoms'][atomName].append(accessibility)
# TODO: match to cing data model for storage at atom level and to RDB cingresidue.wi_wsvacc using
# WSVACC_STR
atomsRead += 1
# end for
# nTdebug("Read %s atoms" % atomsRead)
# nTdebug("Skipped %s hydrogen" % hydrogensSkipped)
# nTdebug("Seen %s atoms" % (atomsRead + hydrogensSkipped))
if not atomsRead:
nTerror("Failed to read any atom")
return True
