def run():
relationName = 'nrgcing_ranges'
fn = os.path.join( '/Users/jd/CMBI/Papers/CING/Data', relationName + '.csv')
nentries = 0
nchains = 0
nsegments = 0
nresidues = 0
nresiduesMin = 999
nresiduesMinEntry = None
r = getRelationFromCsvFile(fn)
columnIdxId = 0
columnIdxRange = 1
for rowIdx in range(r.sizeRows()):
if rowIdx >= 200000:
print "Stopping early."
break
# end if
nentries += 1
pdb_id = r.getValue( rowIdx, columnIdxId)
rangeStr = r.getValue( rowIdx, columnIdxRange)
chain_id = None
# nTdebug( 'pdb_id: %s' % pdb_id)
# nTdebug( 'rangeStr: %s' % rangeStr)
startStopLoL = Molecule.ranges2StartStopLoLStatic(rangeStr)
# nTdebug( 'startStopLoL: %s' % str(startStopLoL) )
nsegments += len(startStopLoL)
for startStopList in startStopLoL:
residueCount = startStopList[2] - startStopList[1] + 1
nresidues += residueCount
if residueCount < nresiduesMin:
nresiduesMin = residueCount
nresiduesMinEntry = pdb_id
# end for
if residueCount < 5:
nTdebug( 'residueCount for %s with range %s and segment %s is %s' % ( pdb_id, rangeStr, str(startStopList), residueCount))
# end for
segmentChainId = startStopList[0]
if segmentChainId != chain_id:
chain_id = segmentChainId
nchains += 1
# end if
# end for
# end for
print "nentries: %s" % nentries
print "nchains: %s" % nchains
print "nsegments: %s" % nsegments
print "nresidues: %s" % nresidues
print "chainsPerEntry: %s" % (nsegments / float(nchains))
print "segmentsPerEntry: %s" % (nsegments / float(nentries))
print "segmentsPerChain: %s" % (nsegments / float(nchains))
print "residuesPerEntry: %s" % (nresidues / float(nentries))
print "residuesPerChain: %s" % (nresidues / float(nchains))
print "residuesPerSegments: %s" % (nresidues / float(nsegments))
print "residuesMin: %s" % nresiduesMin
print "residuesMinEntry: %s" % nresiduesMinEntry
def getBmrbEntries():
'Return None on error.'
r1 = urllib.urlopen(bmrbUrl)
data = r1.read()
fileNameGz = getFileName(bmrbUrl)
writeDataToFile(fileNameGz, data)
fileName = fileNameGz[:-3] # remove .gz
gunzip(fileNameGz, outputFileName=fileName, removeOriginal=True)
bmrbDepRelation = getRelationFromCsvFile(fileName, containsHeaderRow=0)
if not bmrbDepRelation:
nTerror('No relation read from CSV file: %s' % fileName)
return None
bmrbDateList = bmrbDepRelation.getColumnByIdx(0)
bmrbIdList = [int(bmrbData[5:]) for bmrbData in bmrbDateList]
nTmessage("Read %s BMRB entries from DB dump" % len(bmrbIdList))
bmrbIdList.sort()
return bmrbIdList
def getBmrbEntries():
'Return None on error.'
r1 = urllib.urlopen(bmrbUrl)
data = r1.read()
fileNameGz = getFileName(bmrbUrl)
writeDataToFile(fileNameGz, data)
fileName = fileNameGz[:-3] # remove .gz
gunzip(fileNameGz, outputFileName=fileName, removeOriginal=True)
bmrbDepRelation = getRelationFromCsvFile( fileName, containsHeaderRow=0 )
if not bmrbDepRelation:
nTerror('No relation read from CSV file: %s' % fileName )
return None
bmrbDateList = bmrbDepRelation.getColumnByIdx(0)
bmrbIdList = [ int(bmrbData[5:]) for bmrbData in bmrbDateList ]
nTmessage("Read %s BMRB entries from DB dump" % len(bmrbIdList))
bmrbIdList.sort()
return bmrbIdList
def run():
relationName = 'nrgcing_ranges'
fn = os.path.join('/Users/jd/CMBI/Papers/CING/Data', relationName + '.csv')
nentries = 0
nchains = 0
nsegments = 0
nresidues = 0
nresiduesMin = 999
nresiduesMinEntry = None
r = getRelationFromCsvFile(fn)
columnIdxId = 0
columnIdxRange = 1
for rowIdx in range(r.sizeRows()):
if rowIdx >= 200000:
print "Stopping early."
break
# end if
nentries += 1
pdb_id = r.getValue(rowIdx, columnIdxId)
rangeStr = r.getValue(rowIdx, columnIdxRange)
chain_id = None
# nTdebug( 'pdb_id: %s' % pdb_id)
# nTdebug( 'rangeStr: %s' % rangeStr)
startStopLoL = Molecule.ranges2StartStopLoLStatic(rangeStr)
# nTdebug( 'startStopLoL: %s' % str(startStopLoL) )
nsegments += len(startStopLoL)
for startStopList in startStopLoL:
residueCount = startStopList[2] - startStopList[1] + 1
nresidues += residueCount
if residueCount < nresiduesMin:
nresiduesMin = residueCount
nresiduesMinEntry = pdb_id
# end for
if residueCount < 5:
nTdebug(
'residueCount for %s with range %s and segment %s is %s' %
(pdb_id, rangeStr, str(startStopList), residueCount))
# end for
segmentChainId = startStopList[0]
if segmentChainId != chain_id:
chain_id = segmentChainId
nchains += 1
# end if
# end for
# end for
print "nentries: %s" % nentries
print "nchains: %s" % nchains
print "nsegments: %s" % nsegments
print "nresidues: %s" % nresidues
print "chainsPerEntry: %s" % (nsegments / float(nchains))
print "segmentsPerEntry: %s" % (nsegments / float(nentries))
print "segmentsPerChain: %s" % (nsegments / float(nchains))
print "residuesPerEntry: %s" % (nresidues / float(nentries))
print "residuesPerChain: %s" % (nresidues / float(nchains))
print "residuesPerSegments: %s" % (nresidues / float(nsegments))
print "residuesMin: %s" % nresiduesMin
print "residuesMinEntry: %s" % nresiduesMinEntry