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 __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 setSpectrum(self, specName, ppm):
specName = string.strip(specName)
# If spectrum name already exists, see if number of dims matches
if self.specNames.count(specName) == 1:
specNameIndex = self.specNames.index(specName)
numDim = self.numDims[specNameIndex]
# Just to make sure not fluke peak with ppm 0.00000 as first one
# for a particular spectrum, check again
# TODO: this slows things down... should only do this ten times or so
ndim = self.maxDim
for ppmVal in ppm:
if returnFloat(ppmVal) == 0.0:
ndim -= 1
if ndim > numDim:
self.numDims[specNameIndex] = None
# If doesn't exist, create
else:
self.specNames.append(specName)
ndim = self.maxDim
for ppmVal in ppm:
if returnFloat(ppmVal) == 0.0:
ndim -= 1
self.numDims.append(ndim)
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,
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 __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 readCloudFile(fileName, hydrogenOnly=True):
file = open(fileName, 'r')
coords = []
atoms = []
shifts = []
serials = []
for line in file.readlines():
key = line[0:6].strip()
if key == 'ATOM':
a = line[13:16].strip()
x = returnFloat(line[30:38])
y = returnFloat(line[38:46])
z = returnFloat(line[46:54])
n = int(float(line[54:60].strip() or 0.0) * 100)
s = float(line[60:66].strip() or 0.0) / 10.0
if hydrogenOnly:
if (a[0] == 'H') or (a == 'CH3'):
coords.append([x, y, z])
shifts.append(s)
atoms.append(a)
serials.append(n)
else:
coords.append([x, y, z])
shifts.append(s)
atoms.append(a)
serials.append(n)
return (coords, serials, shifts, atoms)
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 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, 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 setOtherData(self, weight, peakNum, peakVol, ppms):
if weight != None:
self.weight = returnFloat(weight)
else:
self.weight = None
self.peakNum = returnInt(peakNum)
self.peakVol = returnFloat(peakVol)
self.ppms = returnFloats(ppms)
def __init__(self, num, ppm, intensity, verbose=False):
self.num = returnInt(num, default=None, verbose=verbose)
self.intensity = returnFloat(intensity, default=None, verbose=verbose)
self.assign = []
self.ppm = []
for i in range(0, len(ppm)):
self.ppm.append(returnFloat(ppm[i], default=None, verbose=verbose))
self.assign.append(None)
def __init__(self, Id, intensity, assign, ppm, dimSlice=[]):
self.num = returnInt(Id)
self.intensity = returnFloat(intensity)
self.assign = assign[:]
self.dimSlice = dimSlice[:]
self.ppm = []
for i in range(0, len(ppm)):
self.ppm.append(returnFloat(ppm[i]))
def __init__(self, num, assign, ppm, intensity, status):
self.num = returnInt(num)
self.intensity = returnFloat(intensity)
self.status = status
self.assign = []
self.ppm = []
for i in range(0, len(assign)):
self.ppm.append(returnFloat(ppm[i]))
self.assign.append(assign[i])
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 setAngleData(self,
lowerAngle,
upperAngle,
energyCst=1.0,
verbose=False):
self.lowerAngle = returnFloat(lowerAngle,
default=None,
verbose=verbose)
self.upperAngle = returnFloat(upperAngle,
default=None,
verbose=verbose)
self.energyCst = returnFloat(energyCst, verbose=verbose)
def setRdcData(self,value,error,weight):
self.value = returnFloat(value)
if error == None:
self.error = 1.0
else:
self.error = returnFloat(error)
if weight == None:
self.weight = 1.0
else:
self.weight = returnFloat(weight)
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 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 setSpecificInfo(self):
for parameterType in ['pH', 'Temperature', 'Pressure']:
if hasattr(self, parameterType):
setattr(self, parameterType,
returnFloat(getattr(self, parameterType)))
def returnFloat(self, value):
if value == 'nan':
value = None
else:
value = returnFloat(value)
return value
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 returnFloatValue(self, value):
value = self.returnColumnValue(value)
if value:
value = returnFloat(value)
return value
def __init__(self, parent, atomSerial, name, x, y, z, atomType):
self.parent = parent
self.serial = returnInt(atomSerial)
self.name = string.strip(name)
self.x = returnFloat(x, verbose=0)
self.y = returnFloat(y, verbose=0)
self.z = returnFloat(z, verbose=0)
self.atomType = string.strip(atomType)
if not self.atomType:
for char in self.name:
if char not in '0123456789':
self.atomType = char
break
def getValues(self, line):
vals = []
line = string.replace(line, '{', '')
line = string.replace(line, '}', '')
vallist = line.split()
for i in range(0, len(vallist)):
vals.append(returnFloat(vallist[i]))
return vals
def __init__(self, parent, type, value, error, units):
# Warning: need to do some retyping here, data type not always correct in original NMR-STAR
self.parent = parent
self.type = type
self.value = None
if value:
self.value = returnFloat(value)
self.error = None
if error:
self.error = returnFloat(error)
self.units = units
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 setValue(self, valueKey, values):
if len(values) == 1:
value = values[0]
if not self.parent.patt['emptyline'].search(value):
if valueKey == 'residue':
value = value.strip()
self.resLabel = value[0]
seqCodes = value[1:].split(',')
(self.seqCode,
self.seqInsertCode) = getSeqAndInsertCode(seqCodes[0])
if self.seqCode == None:
self.resLabel = value
# Can have multiple values - need to take care of that...
if len(seqCodes) > 1:
for seqCode in seqCodes[1:]:
self.otherSeqAndInsertCodes.append(
getSeqAndInsertCode(seqCode))
elif valueKey == 'atom':
self.atomName = value.strip()
elif valueKey == 'atomType':
self.atomType = value.strip()
elif valueKey == 'chemShift':
self.value = returnFloat(value)
elif valueKey == 'chemShiftError':
self.valueError = returnFloat(value)
elif valueKey == 'numAssignments':
self.numAssignments = returnInt(value)
else:
print " Warning: empty or invalid data field %s for Sparky chemical shift file." % valueKey
pass
def __init__(self, value, atomName, seqCode, spinSystemId, resLabel,
defaultMolCode):
self.value = returnFloat(value)
self.atomName = atomName
(self.seqCode, self.seqInsertCode) = getSeqAndInsertCode(seqCode)
self.molCode = defaultMolCode
self.resLabel = resLabel
self.spinSystemId = spinSystemId
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
