def getCasdNmrProjectInfo(casdNmrRefFile=None):
"""
Code to get list of CASD-NMR projects info
"""
result = []
# This file is customisable!
if not casdNmrRefFile:
casdNmrRefFile = os.path.join(allDataDir, 'dataPage.html')
# Get the web page...
text = ''.join(
getReferenceTextFileFromHttp(casdNmrDataUrl,
casdNmrRefFile,
refText="CASD-NMR data",
isGzipped=False))
table, links = casdUtil.parseHtmlTable(text)
tags = table[0]
for ii in range(1, len(table)):
dd = {}
result.append(dd)
ll = table[ii]
for jj, val in enumerate(table[ii]):
dd[tags[jj]] = val
dd['DataLink'] = links[ii][0]
#
return result
def getBmrbPdbMappingInfo(dataFilePath=None):
# NOTE: this gives UNIQUE mappings between PDB and BMRB ID!
# Use getBmrbDatabaseMatches for list of all mappings.
if not dataFilePath:
dataFilePath = bmrbPdbMappingFilePath
dataLines = getReferenceTextFileFromHttp(bmrbPdbMappingUrl,
dataFilePath,
refText="BMRB to PDB mappings")
bmrbPdbMappingDict = {}
for dataLine in dataLines:
if dataLine:
(bmrbId, pdbCode) = dataLine.strip().split(',')
bmrbId = int(bmrbId)
if not bmrbPdbMappingDict.has_key(bmrbId):
bmrbPdbMappingDict[bmrbId] = pdbCode.lower()
else:
# This should never happen... raise it?
print "MULTIPLE MATCH FOR %d!!" % bmrbId
return bmrbPdbMappingDict
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 getPdbEntryType(dataFilePath=None,updateFile=False):
"""
Read info on experiment type of PDB entries
"""
pdbEntryTypeDict = {}
if not dataFilePath:
dataFilePath = pdbEntryTypeFilePath
if updateFile or not os.path.exists(dataFilePath):
dataLines = getReferenceTextFileFromHttp(pdbEntryTypeUrl,dataFilePath,refText = "PDB entry experiment type information")
else:
fin = open(dataFilePath)
dataLines = fin.readlines()
fin.close()
for dataLine in dataLines:
cols = dataLine.split()
if len(cols) == 3:
(pdbCode,molType,expType) = cols
# molType is prot, nuc or prot-nuc
# expType is diffraction, NMR, or EM
pdbEntryTypeDict[pdbCode] = (molType,expType)
return pdbEntryTypeDict
def getCasdNmrProjectInfo(casdNmrRefFile=None):
"""
Code to get list of CASD-NMR projects info
"""
hrefPatt = re.compile('\<a href\=\"([^\"]+)\"')
hrefNamePatt = re.compile('[^ ]\"\>([^\>]+)\<\/a')
pdbCodePatt = re.compile('\>\s*([A-Za-z0-9]{4})\s*\<\/a')
# This file is customisable!
if not casdNmrRefFile:
casdNmrRefFile = os.path.join(casdNmrDataDir, 'reference',
'dataPage.html')
# Get the web page...
dataLines = getReferenceTextFileFromHttp(casdNmrDataUrl,
casdNmrRefFile,
refText="CASD-NMR data",
isGzipped=False)
# Now get the info out...
projectInfo = []
for dataLine in dataLines:
if dataLine.count('href'):
if dataLine.count("assignment-software"):
continue
# Some custum hacking here - content of href lines with data not dependable enough...
if dataLine.count("rutgers") or dataLine.count(
'Data for') or dataLine.count('/wenmr/files/files/'):
hrefSearch = hrefPatt.search(dataLine)
dataLine = dataLine.replace("<span>", "")
dataLine = dataLine.replace("</span>", "")
projectNameSearch = hrefNamePatt.search(dataLine)
if hrefSearch:
urlName = projectNameSearch.group(1)
if urlName.count("/wenmr"):
urlName = urlName.replace("/wenmr", eNmrUrl)
projectInfo.append([urlName, hrefSearch.group(1), []])
elif dataLine.count("structureId="):
pdbCodeSearch = pdbCodePatt.search(dataLine)
if pdbCodeSearch:
projectInfo[-1][-1].append(pdbCodeSearch.group(1))
if not projectInfo:
raise CasdNmrError("No files found, probably web page change!")
return projectInfo
def getBmrbDatabaseMatches(dataFilePath=None):
"""
Read info on relation between BMRB and other database entries...
"""
if not dataFilePath:
dataFilePath = bmrbDatabaseMatchFilePath
dataLines = getReferenceTextFileFromHttp(bmrbDatabaseMatchUrl,
dataFilePath,
refText="BMRB database matches")
bmrbDatabaseDict = {}
for dataLine in dataLines:
if dataLine:
dataLine = dataLine.strip()
values = dataLine.split(',')
# Ignore lines with inconsistent length
if len(values) != 11:
continue
(bmrbId, dbName, dbCode, matchData, matchScore, unknown, unknown,
method, resolution, unknown, unknown) = values
bmrbId = bmrbId.strip('"')
if not bmrbId:
continue
bmrbId = int(bmrbId)
dbName = dbName.strip('"')
dbCode = dbCode.strip('"')
if not bmrbDatabaseDict.has_key(bmrbId):
bmrbDatabaseDict[bmrbId] = {}
if not bmrbDatabaseDict[bmrbId].has_key(dbName):
bmrbDatabaseDict[bmrbId][dbName] = []
bmrbDatabaseDict[bmrbId][dbName].append(dbCode)
return bmrbDatabaseDict
def getBmrbNmrGridDict(dataFilePath=None, skipCodes=None):
"""
Read info on DOCR/FRED from BMRB...
"""
bmrbNmrGridDict = {}
#1047 1017 classified 1a51 2004-12-02
#26561 1064 parsed 1ajw 2004-12-03
#39888 1263 filtered 1c54 2004-12-03
#39889 1266 converted 1c7v 2004-12-03
# Where classified means there is a constraint file, but it's not been parsed
# rest is obvious: converted DOCR, filtered FRED.
if not dataFilePath:
dataFilePath = os.path.join(nmrGridReferenceDir, nmrGridInfoFile)
dataLines = getReferenceTextFileFromHttp(nmrGridInfoUrl,
dataFilePath,
refText="NMR GRID information")
for dataLine in dataLines:
if dataLine:
(gridId, bmrbId, statusCode, pdbCode, date) = dataLine.split()
if skipCodes and pdbCode in skipCodes:
continue
if statusCode in statusConvert:
if not bmrbNmrGridDict.has_key(pdbCode):
bmrbNmrGridDict[pdbCode] = {}
status = statusConvert[statusCode]
if not bmrbNmrGridDict[pdbCode].has_key(status):
webLink = '%s?pdb_id=%s&min_items=0&block_text_type=%s' % (
nmrGridServletUrl, pdbCode, statusCode)
bmrbNmrGridDict[pdbCode][status] = webLink
return bmrbNmrGridDict
def getXrayResolution():
"""
Read info on X-ray resolution PDB entries
"""
resolutionDict = {}
dataLines = getReferenceTextFileFromHttp(xrayResolutionUrl,xrayResolutionFilePath,refText = "PDB x-ray resolution information")
for dataLine in dataLines:
cols = dataLine.split()
if len(cols) == 3 and cols[1] == ';':
pdbCode = cols[0].lower()
resolution = float(cols[2])
if resolution != -1.0:
resolutionDict[pdbCode] = resolution
return resolutionDict
def getBmrbInfo(dataType=None):
if not dataType:
return None
elif dataType == 'rdc':
bmrbQueryFile = "query_1_67.html"
valueNames = ('bmrbId', 'name', 'numRdcs', 'hasProtein', 'hasDNA',
'hasRNA')
elif dataType == 'coupling':
bmrbQueryFile = "query_1_29.html"
valueNames = ('bmrbId', 'name', 'numCouplings', 'hasProtein', 'hasDNA',
'hasRNA')
elif dataType == 't1':
bmrbQueryFile = "query_1_33.html"
valueNames = ('bmrbId', 'name', 'numT1s', 'hasProtein', 'hasDNA',
'hasRNA')
elif dataType == 't2':
bmrbQueryFile = "query_1_38.html"
valueNames = ('bmrbId', 'name', 'numT2s', 'hasProtein', 'hasDNA',
'hasRNA')
elif dataType == 'hetNuclNoe':
bmrbQueryFile = "query_1_41.html"
valueNames = ('bmrbId', 'name', 'numHetNuclNoes', 'hasProtein',
'hasDNA', 'hasRNA')
elif dataType == 'shift':
bmrbQueryFile = "query_1_5_4.html"
valueNames = ('bmrbId', 'name', 'numShifts_1H', 'numShifts_13C',
'numShifts_15N', 'numShifts_31P', 'hasProtein', 'hasDNA',
'hasRNA')
elif dataType == 'orderParam':
bmrbQueryFile = "query_1_45.html"
valueNames = ('bmrbId', 'name', 'numOrderParams', 'hasProtein',
'hasDNA', 'hasRNA')
elif dataType == 'hExchange':
bmrbQueryFile = "query_1_49.html"
valueNames = ('bmrbId', 'name', 'numHExchangeValues', 'hasProtein',
'hasDNA', 'hasRNA')
elif dataType == 'hProtection':
bmrbQueryFile = "query_1_53.html"
valueNames = ('bmrbId', 'name', 'numHProtectionValues', 'hasProtein',
'hasDNA', 'hasRNA')
else:
print "Unknown data type %s, aborting..." % dataType
return None
bmrbQueryUrl = "%s/search/query_grid/%s" % (bmrbUrl, bmrbQueryFile)
bmrbQueryFilePath = os.path.join(bmrbReferenceDir, bmrbQueryFile)
entryLinePatt = re.compile("data_library/generate_summary")
valuePatt = re.compile("\>([^\<\>]+)\<")
bmrbValuesDict = {}
dataLines = getReferenceTextFileFromHttp(bmrbQueryUrl,
bmrbQueryFilePath,
refText="BMRB %s information" %
dataType)
ln = 0
while (ln < len(dataLines)):
dataLine = dataLines[ln]
if entryLinePatt.search(dataLine):
infoDict = {}
for valueName in valueNames:
valueSearch = valuePatt.search(dataLine)
if not valueSearch:
print dataLine
value = valueSearch.group(1)
if value in (' ', ' '):
value = False
elif value == 'X':
value = True
elif valueName[:3] == 'num':
value = int(value)
infoDict[valueName] = value
ln += 1
dataLine = dataLines[ln]
bmrbId = int(infoDict['bmrbId'])
del (infoDict['bmrbId'])
bmrbValuesDict[bmrbId] = infoDict
ln += 1
return bmrbValuesDict