def plotHistogramOverall():
graphicsFormat = "png"
alpha = 0.8 # was 0.8; looks awful with alpha = 1
n = 20
# d = 3 # number of ss types.
extent = (0, n) + (0, n)
cmapList = [green_inv, blue_inv, yellow_inv]
colorList = ['green', 'blue', 'yellow']
i = 1 # decides on color picked.
# If set it will do a single ssType otherwise the overall.
for doOverall in [False, True]:
# for doOverall in [ True ]:
if doOverall:
ssTypeList = [None]
else:
ssTypeList = [' ', 'S', 'H']
for ssType in ssTypeList:
m = zeros((n * n), dtype=int).reshape(n, n)
# mBySs = zeros((n,n,d), dtype=int).reshape(n,n,d)
tickList = [
NTdb.getResidueDefByName(resType).shortName
for resType in common20AAList
]
# tickListRev = tickList[:]
# tickListRev.reverse()
for r, resTypePrev in enumerate(common20AAList):
for c, resType in enumerate(common20AAList):
if doOverall:
hist1 = getDeepByKeys(hPlot.histd1ByResTypes, resType,
resTypePrev)
else:
hist1 = getDeepByKeys(hPlot.histd1BySs0AndResTypes,
ssType, resType, resTypePrev)
if hist1 == None:
nTdebug('skipping for hist1 is empty for [%s] [%s]' %
(resType, resTypePrev))
continue
m[r, c] = sum(hist1)
clf()
# axes([.1, .1, .8, .8 ] )
xlabel('resType')
ylabel('resTypePrev')
xlim((0, n))
ylim((0, n))
offset = 0.5
xticks(arange(offset, n), tickList)
yticks(arange(offset, n), tickList)
# print 'just before call to set_ticks_position'
# axis.xaxis.set_ticks_position('top')
# axis.xaxis.set_label_position('top')
# axis.yaxis.set_ticks_position('both')
# axis.yaxis.set_label_position('left')
grid(True)
strTitle = "ssType: [%s]" % ssType
title(strTitle)
plot([0, n], [0, n], 'b-', linewidth=1)
minCount = 300.
maxCount = 1000.
if False:
minCount = 0.
maxCount = 1.
if ssType:
minCount /= 3.
maxCount /= 3.
maxHist = amax(m)
minHist = amin(m)
sumHist = sum(m)
nTmessage('ssType: %s' % ssType)
nTmessage('maxHist: %s' % maxHist) # 9165 of total of ~ 1 M.
nTmessage('minHist: %s' % minHist) # 210
nTmessage('sumHist: %s' % sumHist) # 210
# nTmessage('tickList: %s' % tickList) # 210
# his *= 100./maxHist
his = masked_where(m <= minCount, m, copy=1)
palette = cmapList[i]
palette.set_under(color='red', alpha=1.0) # alpha is 0.0
palette.set_over(
color=colorList[i], alpha=1.0
) # alpha is 1.0 Important to make it a hard alpha; last plotted will rule.
palette.set_bad(color='red', alpha=1.0)
norm = Normalize(vmin=minCount, vmax=maxCount,
clip=True) # clip is False
imshow(
his,
interpolation='nearest',
# interpolation='bicubic',
origin='lower',
extent=extent,
alpha=alpha,
cmap=palette,
norm=norm)
# mr = m[::-1] # reverses the rows, nice!
# nTmessage('mr: %s' % mr)
fn = "plotHistogram_%s_d1d2.%s" % (ssType, graphicsFormat)
savefig(fn)
clf()
a = m.reshape(n * n)
hist(a, 20)
xlabel('pair count')
ylabel('number of occurrences')
title(strTitle)
fn = "plotHistOfHist_%s_d1d2.%s" % (ssType, graphicsFormat)
savefig(fn)
# end loop over ssType
# end over ssType overall
return m
def matchResidue2Cing(self, res):
"""
Match res to CING database using previously defined convention;
Account for 'ill-defined' residues by examining crucial atom names.
Use CYANA (==DIANA) Naming for conversion to INTERNAL (i.e. These names will not likely change)
Return NTdb resDef object None on Error
res is a NTtree object with the following attributes set after this routine:
db
skip
resName and attributes for every atom it includes:
HA2, CD1, ...
"""
# nTdebug("Now in _matchResidue2Cing: %s" % res)
res.db = None
res.skip = False
# Residue names that are ambiguously defined by different PDB file formats
if res.resName[0:3] == 'ARG':
if 'HH1' in res:
res.db = NTdb.getResidueDefByName('ARG', convention = CYANA)
elif '1HH' in res: # Second set for CYANA 1.x, AMBER
res.db = NTdb.getResidueDefByName('ARG', convention = CYANA)
else:
# Default protonated; this also assures most common for X-ray without protons
res.db = NTdb.getResidueDefByName('ARG+', convention = CYANA)
#end if
#end if
elif res.resName[0:3] == 'ASP':
if 'HD2' in res:
#print 'ASPH'
res.db = NTdb.getResidueDefByName('ASP', convention = CYANA)
else:
# Default deprot; this also assures most common for X-ray without protons
#print 'ASP'
res.db = NTdb.getResidueDefByName('ASP-', convention = CYANA)
#end if
elif res.resName[0:3] == 'GLU':
if 'HE2' in res:
#print 'GLUH'
res.db = NTdb.getResidueDefByName('GLU', convention = CYANA)
else:
# Default deprot; this also assures most common for X-ray without protons
#print 'GLU'
res.db = NTdb.getResidueDefByName('GLU-', convention = CYANA)
#end if
elif res.resName[0:3] == 'HIS':
if 'HD1' in res and 'HE2' in res:
#print 'HISH'
res.db = NTdb.getResidueDefByName('HIS+', convention = CYANA)
elif not 'HD1' in res and 'HE2' in res:
# print HISE
res.db = NTdb.getResidueDefByName('HIST', convention = CYANA)
else:
# Default HD1
#print 'HIS'
res.db = NTdb.getResidueDefByName('HIS', convention = CYANA)
#end if
elif res.resName[0:3] == 'LYS':
if ('HZ1' in res and not 'HZ3' in res):
res.db = NTdb.getResidueDefByName('LYS', convention = CYANA)
elif ('1HZ' in res and not '3HZ' in res): # Second set for CYANA 1.x
res.db = NTdb.getResidueDefByName('LYS', convention = CYANA)
else:
# Default prot; this also assures most common for X-ray without protons
res.db = NTdb.getResidueDefByName('LYS+', convention = CYANA)
#end if
elif res.resName in CYANA_NON_RESIDUES:
res.skip = True
elif res.resName == 'HOH' and self.skipWaters:
res.skip = True
else:
res.db = NTdb.getResidueDefByName(res.resName, convention = self.convention)
#end if
# Only continue the search if not found and non-standard residues are allowed.
if res.db:
return res.db
if not self.allowNonStandardResidue:
res.skip = True
return res.db
# Try to match the residue using INTERNAL convention.
res.db = NTdb.getResidueDefByName(res.resName)
if res.db:
return res.db
# insert new residue.
res.db = NTdb.appendResidueDef(name = res.resName, shortName = '_', comment='From parsing PDB file')
if not res.db:
nTcodeerror("Adding a non-standard residue should have been possible.")
return None
res.db.nameDict[self.convention] = res.resName
# Just a check, disable for speed.
_x = NTdb.getResidueDefByName(res.resName)
if not _x:
nTcodeerror("Added residue but failed to find it again in pdbParser#_matchResidue2Cing")
return res.db
def plotHistogramOverall():
graphicsFormat = "png"
alpha = 0.8 # was 0.8; looks awful with alpha = 1
n = 20
# d = 3 # number of ss types.
extent = (0, n) + (0, n)
cmapList = [ green_inv, blue_inv, yellow_inv ]
colorList = [ 'green', 'blue', 'yellow']
i = 1 # decides on color picked.
# If set it will do a single ssType otherwise the overall.
for doOverall in [ False, True ]:
# for doOverall in [ True ]:
if doOverall:
ssTypeList = [ None ]
else:
ssTypeList = [' ', 'S', 'H']
for ssType in ssTypeList:
m = zeros((n * n), dtype=int).reshape(n, n)
# mBySs = zeros((n,n,d), dtype=int).reshape(n,n,d)
tickList = [ NTdb.getResidueDefByName(resType).shortName for resType in common20AAList]
# tickListRev = tickList[:]
# tickListRev.reverse()
for r, resTypePrev in enumerate(common20AAList):
for c, resType in enumerate(common20AAList):
if doOverall:
hist1 = getDeepByKeys(hPlot.histd1ByResTypes, resType, resTypePrev)
else:
hist1 = getDeepByKeys(hPlot.histd1BySs0AndResTypes, ssType, resType, resTypePrev)
if hist1 == None:
nTdebug('skipping for hist1 is empty for [%s] [%s]' % (resType, resTypePrev))
continue
m[r, c] = sum(hist1)
clf()
# axes([.1, .1, .8, .8 ] )
xlabel('resType')
ylabel('resTypePrev')
xlim((0, n))
ylim((0, n))
offset = 0.5
xticks(arange(offset, n), tickList)
yticks(arange(offset, n), tickList)
# print 'just before call to set_ticks_position'
# axis.xaxis.set_ticks_position('top')
# axis.xaxis.set_label_position('top')
# axis.yaxis.set_ticks_position('both')
# axis.yaxis.set_label_position('left')
grid(True)
strTitle = "ssType: [%s]" % ssType
title(strTitle)
plot([0, n], [0, n], 'b-', linewidth=1)
minCount = 300.
maxCount = 1000.
if False:
minCount = 0.
maxCount = 1.
if ssType:
minCount /= 3.
maxCount /= 3.
maxHist = amax(m)
minHist = amin(m)
sumHist = sum(m)
nTmessage('ssType: %s' % ssType)
nTmessage('maxHist: %s' % maxHist) # 9165 of total of ~ 1 M.
nTmessage('minHist: %s' % minHist) # 210
nTmessage('sumHist: %s' % sumHist) # 210
# nTmessage('tickList: %s' % tickList) # 210
# his *= 100./maxHist
his = masked_where(m <= minCount, m, copy=1)
palette = cmapList[i]
palette.set_under(color='red', alpha=1.0) # alpha is 0.0
palette.set_over(color=colorList[i], alpha=1.0) # alpha is 1.0 Important to make it a hard alpha; last plotted will rule.
palette.set_bad(color='red', alpha=1.0)
norm = Normalize(vmin=minCount, vmax=maxCount, clip=True) # clip is False
imshow(his,
interpolation='nearest',
# interpolation='bicubic',
origin='lower',
extent=extent,
alpha=alpha,
cmap=palette,
norm=norm)
# mr = m[::-1] # reverses the rows, nice!
# nTmessage('mr: %s' % mr)
fn = "plotHistogram_%s_d1d2.%s" % (ssType, graphicsFormat)
savefig(fn)
clf()
a = m.reshape(n * n)
hist(a, 20)
xlabel('pair count')
ylabel('number of occurrences')
title(strTitle)
fn = "plotHistOfHist_%s_d1d2.%s" % (ssType, graphicsFormat)
savefig(fn)
# end loop over ssType
# end over ssType overall
return m
def main():
'See above.'
cvs_file_abs_name_gz = os.path.join(cingDirData, 'PluginCode', 'Whatif', cvs_file_abs_name + '.gz')
gunzip(cvs_file_abs_name_gz)
reader = csv.reader(open(cvs_file_abs_name, "rb"), quoting=csv.QUOTE_NONE)
valueBySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
valueBySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
valueByResTypes = {}
valueBySs0 = {} # keys are SSi
valueBySs1 = {} # keys are SSi-1
histd1CtupleBySsAndResTypes = {}
value = [] # NB is an array without being keyed.
histd1BySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
histd1BySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
histd1ByResTypes = {}
histd1BySs0 = {}
histd1BySs1 = {}
linesByEntry = {}
lineCount = 0
for row in reader:
lineCount += 1
if lineCount > lineCountMax:
break
entryId = row[0]
if not linesByEntry.has_key(entryId):
linesByEntry[ entryId ] = []
linesByEntry[ entryId ].append( row )
skippedResTypes = []
entryIdList = linesByEntry.keys()
entryIdList.sort()
# Do some pre filtering.
for entryId2 in entryIdList:
lineList = linesByEntry[ entryId2 ]
for idx,line in enumerate(lineList):
line.append(idx)
lineListSorted = NTsort(lineList,BFACTOR_COLUMN,inplace=False)
# Now throw away the worst 10 % of residues.
n = len(lineListSorted)
bad_count = int(round((n * DEFAULT_BFACTOR_PERCENTAGE_FILTER) / 100.))
to_remove_count = n-bad_count
# nTmessage("Removing at least %d from %d residues" % (bad_count,n))
badIdxList = [lineItem[IDX_COLUMN] for lineItem in lineListSorted[to_remove_count:n]]
iList = range(n)
iList.reverse()
for i in iList:
lineItem = lineList[i]
max_bfactor = float(lineItem[BFACTOR_COLUMN])
if max_bfactor > DEFAULT_MAX_BFACTOR:
# nTdebug('Skipping because max bfactor in dihedral %.3f is above %.3f %s' % (max_bfactor, DEFAULT_MAX_BFACTOR, lineItem))
del lineList[i] # TODO: check if indexing is still right or we shoot in the foot.
continue
if i in badIdxList:
# nTdebug('Skipping because bfactor worst %.3f %s' % (max_bfactor, lineItem))
del lineList[i]
continue
removed_count = n - len(lineList)
# nTdebug("Reduced list by %d" % removed_count)
if removed_count < bad_count:
nTwarning("Failed to remove at least %d residues" % bad_count)
for entryId2 in entryIdList:
prevChainId = None
prevResType = None
prevResNum = None
prevSsType = None
for _r, row in enumerate(linesByEntry[ entryId2 ]):
#1zzk,A,GLN , 17,E, 205.2, 193.6
#1zzk,A,VAL , 18,E, 193.6, 223.2
#1zzk,A,THR , 19,E, 223.2, 190.1
(entryId, chainId, resType, resNum, ssType, d1, _d2, _max_bfactor, _idx) = row
resNum = int(resNum)
ssType = to3StateDssp(ssType)[0]
resType = resType.strip()
db = NTdb.getResidueDefByName( resType )
if not db:
nTerror("resType not in db: %s" % resType)
return
resType = db.nameDict['IUPAC']
d1 = d1.strip()
d1 = floatParse(d1)
if isNaN(d1):
# nTdebug("d1 %s is a NaN on row: %s" % (d1,row))
continue
if not inRange(d1):
nTerror("d1 not in range for row: %s" % str(row))
return
if not (resType in common20AAList):
# nTmessage("Skipping uncommon residue: %s" % resType)
if not ( resType in skippedResTypes):
skippedResTypes.append( resType )
continue
if isSibling(chainId, resNum, prevChainId, prevResNum):
appendDeepByKeys(valueBySs0AndResTypes, d1, ssType, resType, prevResType)
appendDeepByKeys(valueBySs1AndResTypes, d1, prevSsType, resType, prevResType)
appendDeepByKeys(valueByResTypes, d1, resType, prevResType)
appendDeepByKeys(valueBySs0, d1, ssType)
appendDeepByKeys(valueBySs1, d1, prevSsType)
value.append( d1 )
prevResType = resType
prevResNum = resNum
prevChainId = chainId
prevSsType = ssType
os.unlink(cvs_file_abs_name)
nTmessage("Skipped skippedResTypes: %r" % skippedResTypes )
nTmessage("Got count of values: %r" % len(value) )
# fill FOUR types of hist.
# TODO: filter differently for pro/gly
keyListSorted1 = valueBySs0AndResTypes.keys()
keyListSorted1.sort()
for isI in (True, False):
if isI:
valueBySs = valueBySs0
valueBySsAndResTypes = valueBySs0AndResTypes
histd1BySs = histd1BySs0
histd1BySsAndResTypes = histd1BySs0AndResTypes
else:
valueBySs = valueBySs1
valueBySsAndResTypes = valueBySs1AndResTypes
histd1BySs = histd1BySs1
histd1BySsAndResTypes = histd1BySs1AndResTypes
for ssType in keyListSorted1:
# keyListSorted1b = deepcopy(keyListSorted1)
# for ssTypePrev in keyListSorted1b:
d1List = valueBySs[ssType]
if not d1List:
nTerror("Expected d1List from valueBySs[%s]" % (ssType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
nTmessage("Count %6d in valueBySs[%s]" % (sum(hist1d), ssType))
setDeepByKeys(histd1BySs, hist1d, ssType)
keyListSorted2 = valueBySsAndResTypes[ssType].keys()
keyListSorted2.sort()
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySsAndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for prevResType in keyListSorted3:
# nTmessage("Working on valueBySsAndResTypes[%s][%s][%s]" % (ssType, resType, prevResType))
d1List = valueBySsAndResTypes[ssType][resType][prevResType]
if not d1List:
nTerror("Expected d1List from valueBySsAndResTypes[%s][%s][%s]" % (ssType, resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
# nTmessage("Count %6d in valueBySsAndResTypes[%s][%s][%s]" % (sum(hist1d), ssType, resType, prevResType))
setDeepByKeys(histd1BySsAndResTypes, hist1d, ssType, resType, prevResType)
# Now that they are all in we can redo this.
# Delete the reference -not- the object.
valueBySs = None
valueBySsAndResTypes = None
histd1BySs = None
histd1BySsAndResTypes = None
for ssType in keyListSorted1:
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySs0AndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for resTypePrev in keyListSorted3:
keyListSorted4 = keyListSorted3[:] # take a copy
for resTypeNext in keyListSorted4:
hist1 = getDeepByKeys(histd1BySs0AndResTypes, ssType, resType, resTypePrev) # x-axis
# This was bug! It needs to be hashed on the ssType of resType -not- on resTypeNext
hist2 = getDeepByKeys(histd1BySs1AndResTypes, ssType, resTypeNext, resType)
if hist1 == None:
nTdebug('skipping for hist1 is empty for [%s] [%s] [%s]' % (ssType, resTypePrev, resType))
continue
if hist2 == None:
nTdebug('skipping for hist2 is empty for [%s] [%s] [%s]' % (ssType, resType, resTypeNext))
continue
m1 = mat(hist1,dtype='float')
m2 = mat(hist2,dtype='float')
m2 = m2.transpose() # pylint: disable=E1101
hist2d = multiply(m1,m2)
cTuple = getEnsembleAverageAndSigmaHis( hist2d )
(_c_av, c_sd, _hisMin, _hisMax) = cTuple #@UnusedVariable
cTuple += tuple([str([ssType, resType, resTypePrev, resTypeNext])]) # append the hash keys as a way of id.
# nTdebug("For ssType %s residue types %s %s %s found (av/sd/min/max) %8.0f %8.0f %8.0f %8.0f" % (
# ssType, resType, resTypePrev, resTypeNext, c_av, c_sd, hisMin, hisMax))
if c_sd == None:
nTdebug('Failed to get c_sd when testing not all residues are present in smaller sets.')
continue
if c_sd == 0.:
nTdebug('Got zero c_sd, ignoring histogram. This should only occur in smaller sets. Not setting values.')
continue
setDeepByKeys( histd1CtupleBySsAndResTypes, cTuple, ssType, resType, resTypePrev, resTypeNext)
# end for isI
keyListSorted1 = valueByResTypes.keys()
keyListSorted1.sort()
for resType in keyListSorted1:
keyListSorted2 = valueByResTypes[resType].keys()
keyListSorted2.sort()
for prevResType in keyListSorted2:
d1List = valueByResTypes[resType][prevResType]
if not d1List:
nTerror("Expected d1List from valueByResTypes[%s][%s]" % (resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
# nTmessage("Count %6d in valueByResTypes[%s][%s]" % (sum(hist1d), resType, prevResType))
setDeepByKeys(histd1ByResTypes, hist1d, resType, prevResType)
histd1, _bins, _patches = hist(value, bins=binCount, range=xRange)
nTmessage("Count %6d in value" % sum(histd1))
# setDeepByKeys(histd1, hist1d, resType, prevResType)
if os.path.exists(dbase_file_abs_name):
os.unlink(dbase_file_abs_name)
output = open(dbase_file_abs_name, 'wb')
dbase = {}
dbase[ 'histd1BySs0AndResTypes' ] = histd1BySs0AndResTypes # 92 kb uncompressed in the case of ~1000 lines only
dbase[ 'histd1BySs1AndResTypes' ] = histd1BySs1AndResTypes
dbase[ 'histd1CtupleBySsAndResTypes' ] = histd1CtupleBySsAndResTypes
dbase[ 'histd1ByResTypes' ] = histd1ByResTypes # 56 kb
dbase[ 'histd1BySs0' ] = histd1BySs0 # 4 kb
dbase[ 'histd1BySs1' ] = histd1BySs1
dbase[ 'histd1' ] = histd1 # 4 kb
cPickle.dump(dbase, output, 2)
output.close()
def main():
'See above.'
cvs_file_abs_name_gz = os.path.join(cingDirData, 'PluginCode', 'Whatif',
cvs_file_abs_name + '.gz')
gunzip(cvs_file_abs_name_gz)
reader = csv.reader(open(cvs_file_abs_name, "rb"), quoting=csv.QUOTE_NONE)
valueBySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
valueBySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
valueByResTypes = {}
valueBySs0 = {} # keys are SSi
valueBySs1 = {} # keys are SSi-1
histd1CtupleBySsAndResTypes = {}
value = [] # NB is an array without being keyed.
histd1BySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
histd1BySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
histd1ByResTypes = {}
histd1BySs0 = {}
histd1BySs1 = {}
linesByEntry = {}
lineCount = 0
for row in reader:
lineCount += 1
if lineCount > lineCountMax:
break
entryId = row[0]
if not linesByEntry.has_key(entryId):
linesByEntry[entryId] = []
linesByEntry[entryId].append(row)
skippedResTypes = []
entryIdList = linesByEntry.keys()
entryIdList.sort()
# Do some pre filtering.
for entryId2 in entryIdList:
lineList = linesByEntry[entryId2]
for idx, line in enumerate(lineList):
line.append(idx)
lineListSorted = NTsort(lineList, BFACTOR_COLUMN, inplace=False)
# Now throw away the worst 10 % of residues.
n = len(lineListSorted)
bad_count = int(round((n * DEFAULT_BFACTOR_PERCENTAGE_FILTER) / 100.))
to_remove_count = n - bad_count
# nTmessage("Removing at least %d from %d residues" % (bad_count,n))
badIdxList = [
lineItem[IDX_COLUMN]
for lineItem in lineListSorted[to_remove_count:n]
]
iList = range(n)
iList.reverse()
for i in iList:
lineItem = lineList[i]
max_bfactor = float(lineItem[BFACTOR_COLUMN])
if max_bfactor > DEFAULT_MAX_BFACTOR:
# nTdebug('Skipping because max bfactor in dihedral %.3f is above %.3f %s' % (max_bfactor, DEFAULT_MAX_BFACTOR, lineItem))
del lineList[
i] # TODO: check if indexing is still right or we shoot in the foot.
continue
if i in badIdxList:
# nTdebug('Skipping because bfactor worst %.3f %s' % (max_bfactor, lineItem))
del lineList[i]
continue
removed_count = n - len(lineList)
# nTdebug("Reduced list by %d" % removed_count)
if removed_count < bad_count:
nTwarning("Failed to remove at least %d residues" % bad_count)
for entryId2 in entryIdList:
prevChainId = None
prevResType = None
prevResNum = None
prevSsType = None
for _r, row in enumerate(linesByEntry[entryId2]):
#1zzk,A,GLN , 17,E, 205.2, 193.6
#1zzk,A,VAL , 18,E, 193.6, 223.2
#1zzk,A,THR , 19,E, 223.2, 190.1
(entryId, chainId, resType, resNum, ssType, d1, _d2, _max_bfactor,
_idx) = row
resNum = int(resNum)
ssType = to3StateDssp(ssType)[0]
resType = resType.strip()
db = NTdb.getResidueDefByName(resType)
if not db:
nTerror("resType not in db: %s" % resType)
return
resType = db.nameDict['IUPAC']
d1 = d1.strip()
d1 = floatParse(d1)
if isNaN(d1):
# nTdebug("d1 %s is a NaN on row: %s" % (d1,row))
continue
if not inRange(d1):
nTerror("d1 not in range for row: %s" % str(row))
return
if not (resType in common20AAList):
# nTmessage("Skipping uncommon residue: %s" % resType)
if not (resType in skippedResTypes):
skippedResTypes.append(resType)
continue
if isSibling(chainId, resNum, prevChainId, prevResNum):
appendDeepByKeys(valueBySs0AndResTypes, d1, ssType, resType,
prevResType)
appendDeepByKeys(valueBySs1AndResTypes, d1, prevSsType,
resType, prevResType)
appendDeepByKeys(valueByResTypes, d1, resType, prevResType)
appendDeepByKeys(valueBySs0, d1, ssType)
appendDeepByKeys(valueBySs1, d1, prevSsType)
value.append(d1)
prevResType = resType
prevResNum = resNum
prevChainId = chainId
prevSsType = ssType
os.unlink(cvs_file_abs_name)
nTmessage("Skipped skippedResTypes: %r" % skippedResTypes)
nTmessage("Got count of values: %r" % len(value))
# fill FOUR types of hist.
# TODO: filter differently for pro/gly
keyListSorted1 = valueBySs0AndResTypes.keys()
keyListSorted1.sort()
for isI in (True, False):
if isI:
valueBySs = valueBySs0
valueBySsAndResTypes = valueBySs0AndResTypes
histd1BySs = histd1BySs0
histd1BySsAndResTypes = histd1BySs0AndResTypes
else:
valueBySs = valueBySs1
valueBySsAndResTypes = valueBySs1AndResTypes
histd1BySs = histd1BySs1
histd1BySsAndResTypes = histd1BySs1AndResTypes
for ssType in keyListSorted1:
# keyListSorted1b = deepcopy(keyListSorted1)
# for ssTypePrev in keyListSorted1b:
d1List = valueBySs[ssType]
if not d1List:
nTerror("Expected d1List from valueBySs[%s]" % (ssType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
nTmessage("Count %6d in valueBySs[%s]" % (sum(hist1d), ssType))
setDeepByKeys(histd1BySs, hist1d, ssType)
keyListSorted2 = valueBySsAndResTypes[ssType].keys()
keyListSorted2.sort()
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySsAndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for prevResType in keyListSorted3:
# nTmessage("Working on valueBySsAndResTypes[%s][%s][%s]" % (ssType, resType, prevResType))
d1List = valueBySsAndResTypes[ssType][resType][prevResType]
if not d1List:
nTerror(
"Expected d1List from valueBySsAndResTypes[%s][%s][%s]"
% (ssType, resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List,
bins=binCount,
range=xRange)
# nTmessage("Count %6d in valueBySsAndResTypes[%s][%s][%s]" % (sum(hist1d), ssType, resType, prevResType))
setDeepByKeys(histd1BySsAndResTypes, hist1d, ssType,
resType, prevResType)
# Now that they are all in we can redo this.
# Delete the reference -not- the object.
valueBySs = None
valueBySsAndResTypes = None
histd1BySs = None
histd1BySsAndResTypes = None
for ssType in keyListSorted1:
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySs0AndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for resTypePrev in keyListSorted3:
keyListSorted4 = keyListSorted3[:] # take a copy
for resTypeNext in keyListSorted4:
hist1 = getDeepByKeys(histd1BySs0AndResTypes, ssType,
resType, resTypePrev) # x-axis
# This was bug! It needs to be hashed on the ssType of resType -not- on resTypeNext
hist2 = getDeepByKeys(histd1BySs1AndResTypes, ssType,
resTypeNext, resType)
if hist1 == None:
nTdebug(
'skipping for hist1 is empty for [%s] [%s] [%s]' %
(ssType, resTypePrev, resType))
continue
if hist2 == None:
nTdebug(
'skipping for hist2 is empty for [%s] [%s] [%s]' %
(ssType, resType, resTypeNext))
continue
m1 = mat(hist1, dtype='float')
m2 = mat(hist2, dtype='float')
m2 = m2.transpose() # pylint: disable=E1101
hist2d = multiply(m1, m2)
cTuple = getEnsembleAverageAndSigmaHis(hist2d)
(_c_av, c_sd, _hisMin, _hisMax) = cTuple #@UnusedVariable
cTuple += tuple([
str([ssType, resType, resTypePrev, resTypeNext])
]) # append the hash keys as a way of id.
# nTdebug("For ssType %s residue types %s %s %s found (av/sd/min/max) %8.0f %8.0f %8.0f %8.0f" % (
# ssType, resType, resTypePrev, resTypeNext, c_av, c_sd, hisMin, hisMax))
if c_sd == None:
nTdebug(
'Failed to get c_sd when testing not all residues are present in smaller sets.'
)
continue
if c_sd == 0.:
nTdebug(
'Got zero c_sd, ignoring histogram. This should only occur in smaller sets. Not setting values.'
)
continue
setDeepByKeys(histd1CtupleBySsAndResTypes, cTuple, ssType,
resType, resTypePrev, resTypeNext)
# end for isI
keyListSorted1 = valueByResTypes.keys()
keyListSorted1.sort()
for resType in keyListSorted1:
keyListSorted2 = valueByResTypes[resType].keys()
keyListSorted2.sort()
for prevResType in keyListSorted2:
d1List = valueByResTypes[resType][prevResType]
if not d1List:
nTerror("Expected d1List from valueByResTypes[%s][%s]" %
(resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
# nTmessage("Count %6d in valueByResTypes[%s][%s]" % (sum(hist1d), resType, prevResType))
setDeepByKeys(histd1ByResTypes, hist1d, resType, prevResType)
histd1, _bins, _patches = hist(value, bins=binCount, range=xRange)
nTmessage("Count %6d in value" % sum(histd1))
# setDeepByKeys(histd1, hist1d, resType, prevResType)
if os.path.exists(dbase_file_abs_name):
os.unlink(dbase_file_abs_name)
output = open(dbase_file_abs_name, 'wb')
dbase = {}
dbase[
'histd1BySs0AndResTypes'] = histd1BySs0AndResTypes # 92 kb uncompressed in the case of ~1000 lines only
dbase['histd1BySs1AndResTypes'] = histd1BySs1AndResTypes
dbase['histd1CtupleBySsAndResTypes'] = histd1CtupleBySsAndResTypes
dbase['histd1ByResTypes'] = histd1ByResTypes # 56 kb
dbase['histd1BySs0'] = histd1BySs0 # 4 kb
dbase['histd1BySs1'] = histd1BySs1
dbase['histd1'] = histd1 # 4 kb
cPickle.dump(dbase, output, 2)
output.close()
def matchResidue2Cing(self, res):
"""
Match res to CING database using previously defined convention;
Account for 'ill-defined' residues by examining crucial atom names.
Use CYANA (==DIANA) Naming for conversion to INTERNAL (i.e. These names will not likely change)
Return NTdb resDef object None on Error
res is a NTtree object with the following attributes set after this routine:
db
skip
resName and attributes for every atom it includes:
HA2, CD1, ...
"""
# nTdebug("Now in _matchResidue2Cing: %s" % res)
res.db = None
res.skip = False
# Residue names that are ambiguously defined by different PDB file formats
if res.resName[0:3] == 'ARG':
if 'HH1' in res:
res.db = NTdb.getResidueDefByName('ARG', convention=CYANA)
elif '1HH' in res: # Second set for CYANA 1.x, AMBER
res.db = NTdb.getResidueDefByName('ARG', convention=CYANA)
else:
# Default protonated; this also assures most common for X-ray without protons
res.db = NTdb.getResidueDefByName('ARG+', convention=CYANA)
#end if
#end if
elif res.resName[0:3] == 'ASP':
if 'HD2' in res:
#print 'ASPH'
res.db = NTdb.getResidueDefByName('ASP', convention=CYANA)
else:
# Default deprot; this also assures most common for X-ray without protons
#print 'ASP'
res.db = NTdb.getResidueDefByName('ASP-', convention=CYANA)
#end if
elif res.resName[0:3] == 'GLU':
if 'HE2' in res:
#print 'GLUH'
res.db = NTdb.getResidueDefByName('GLU', convention=CYANA)
else:
# Default deprot; this also assures most common for X-ray without protons
#print 'GLU'
res.db = NTdb.getResidueDefByName('GLU-', convention=CYANA)
#end if
elif res.resName[0:3] == 'HIS':
if 'HD1' in res and 'HE2' in res:
#print 'HISH'
res.db = NTdb.getResidueDefByName('HIS+', convention=CYANA)
elif not 'HD1' in res and 'HE2' in res:
# print HISE
res.db = NTdb.getResidueDefByName('HIST', convention=CYANA)
else:
# Default HD1
#print 'HIS'
res.db = NTdb.getResidueDefByName('HIS', convention=CYANA)
#end if
elif res.resName[0:3] == 'LYS':
if ('HZ1' in res and not 'HZ3' in res):
res.db = NTdb.getResidueDefByName('LYS', convention=CYANA)
elif ('1HZ' in res
and not '3HZ' in res): # Second set for CYANA 1.x
res.db = NTdb.getResidueDefByName('LYS', convention=CYANA)
else:
# Default prot; this also assures most common for X-ray without protons
res.db = NTdb.getResidueDefByName('LYS+', convention=CYANA)
#end if
elif res.resName in CYANA_NON_RESIDUES:
res.skip = True
elif res.resName == 'HOH' and self.skipWaters:
res.skip = True
else:
res.db = NTdb.getResidueDefByName(res.resName,
convention=self.convention)
#end if
# Only continue the search if not found and non-standard residues are allowed.
if res.db:
return res.db
if not self.allowNonStandardResidue:
res.skip = True
return res.db
# Try to match the residue using INTERNAL convention.
res.db = NTdb.getResidueDefByName(res.resName)
if res.db:
return res.db
# insert new residue.
res.db = NTdb.appendResidueDef(name=res.resName,
shortName='_',
comment='From parsing PDB file')
if not res.db:
nTcodeerror(
"Adding a non-standard residue should have been possible.")
return None
res.db.nameDict[self.convention] = res.resName
# Just a check, disable for speed.
_x = NTdb.getResidueDefByName(res.resName)
if not _x:
nTcodeerror(
"Added residue but failed to find it again in pdbParser#_matchResidue2Cing"
)
return res.db