def main():
"""This is a potentially dangerous script. It took JFD an hour one time
to realize it was called inadvertently by not having it wrappen in a function.
"""
# parameters for doScriptOnEntryList
startDir = os.path.join(cingDirTmp, subdir)
pythonScriptFileName = os.path.join(cingDirScripts, 'getPhiPsi.py')
# entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'PDB.LIS')
# entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'PDB_WI_SELECT_Rfactor0.21_Res2.0_2009-02-28_noObs.LIS')
entryListFileName = os.path.join(
cingDirScripts, DATA_STR,
'PDB_WI_SELECT_Rfactor0.19_Res1.3_2009-02-28_noObs.LIS')
# entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'PDB_todo.txt')
start_entry_id = 0 # default 0
max_entries_todo = 1 # default a ridiculously large number like 999999
doScriptOnEntryList(
pythonScriptFileName,
entryListFileName,
startDir,
max_time_to_wait=240, # 1gkp took over 120
processes_max=8, # default 3
start_entry_id=start_entry_id, # default 0
max_entries_todo=
max_entries_todo # default a ridiculously large number like 999999
)
def runCing(self):
"""On self.entry_list_todo.
Return True on error.
"""
entryListFileName = "entry_list_todo.csv"
writeTextToFile(entryListFileName, toCsv(self.entry_list_todo))
pythonScriptFileName = os.path.join(cingDirScripts, 'validateEntry.py')
# inputDir = 'file://' + self.results_dir + '/recoordSync'
inputDir = 'file:///Users/jd/wattosTestingPlatform/pdb/data/structures/divided/pdb'
outputDir = self.results_dir
extraArgList = (inputDir, outputDir, '.', '.', ARCHIVE_TYPE_BY_CH23,
PROJECT_TYPE_PDB)
if doScriptOnEntryList(
pythonScriptFileName,
entryListFileName,
self.results_dir,
processes_max=self.processes_max,
delay_between_submitting_jobs=
5, # why is this so long? because of time outs at tang?
max_time_to_wait=self.max_time_to_wait,
# <Molecule "2p80" (C:20,R:1162,A:24552,M:20)>
start_entry_id=0, # default.
max_entries_todo=self.max_entries_todo,
extraArgList=extraArgList,
shuffleBeforeSelecting=True):
nTerror("Failed to doScriptOnEntryList")
return True
def runCing(self):
"""On self.entry_list_todo.
Return True on error.
"""
entryListFileName = "entry_list_todo.csv"
writeTextToFile(entryListFileName, toCsv(self.entry_list_todo))
pythonScriptFileName = os.path.join(cingDirScripts, 'validateEntry.py')
# inputDir = 'file://' + self.results_dir + '/recoordSync'
inputDir = 'file:///Users/jd/wattosTestingPlatform/pdb/data/structures/divided/pdb'
outputDir = self.results_dir
extraArgList = (inputDir, outputDir, '.', '.', ARCHIVE_TYPE_BY_CH23, PROJECT_TYPE_PDB)
if doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
self.results_dir,
processes_max = self.processes_max,
delay_between_submitting_jobs = 5, # why is this so long? because of time outs at tang?
max_time_to_wait = self.max_time_to_wait,
# <Molecule "2p80" (C:20,R:1162,A:24552,M:20)>
start_entry_id = 0, # default.
max_entries_todo = self.max_entries_todo,
extraArgList = extraArgList,
shuffleBeforeSelecting = True ):
nTerror("Failed to doScriptOnEntryList")
return True
def runCing(self):
"""On self.entry_list_todo.
Return True on error.
"""
entryListFileName = "entry_list_todo.csv"
writeTextToFile(entryListFileName, toCsv(self.entry_list_todo))
pythonScriptFileName = os.path.join(cingDirScripts, 'validateEntry.py')
# inputDir = 'file://' + self.results_dir + '/recoordSync'
inputDir = 'http://www.bmrb.wisc.edu/ftp/pub/bmrb/nmr_pdb_integrated_data/coordinates_restraints_chemshifts/all/ccpn/'
outputDir = self.results_dir
extraArgList = (inputDir, outputDir, '.', '.', ARCHIVE_TYPE_BY_CH23, PROJECT_TYPE_PDB)
if doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
self.results_dir,
processes_max = self.processes_max,
delay_between_submitting_jobs = 5, # why is this so long? because of time outs at tang?
max_time_to_wait = self.max_time_to_wait,
# <Molecule "2p80" (C:20,R:1162,A:24552,M:20)>
start_entry_id = 0, # default.
max_entries_todo = self.max_entries_todo,
extraArgList = extraArgList,
shuffleBeforeSelecting = True ):
nTerror("Failed to doScriptOnEntryList")
return True
def test_DoScriptOnEntryList(self):
cingDirTmpTest = os.path.join(cingDirTmp, getCallerName())
mkdirs(cingDirTmpTest)
self.failIf(os.chdir(cingDirTmpTest),
msg="Failed to change to test directory for files: " +
cingDirTmpTest)
entryListFileName = "entry_list_todo.csv"
entry_list_todo = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
writeTextToFile(entryListFileName, toCsv(entry_list_todo))
pythonScriptFileName = os.path.join(cingDirScripts, 'doNothing.py')
extraArgList = ('.', '.', '.', '.', ARCHIVE_TYPE_BY_CH23,
PROJECT_TYPE_PDB)
self.assertFalse(
doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
'.',
processes_max=8,
delay_between_submitting_jobs=5,
max_time_to_wait=20,
start_entry_id=0,
max_entries_todo=1,
extraArgList=extraArgList,
shuffleBeforeSelecting=True))
def main():
"""This is a potentially dangerous script. It took JFD an hour one time
to realize it was called inadvertently by not having it wrappen in a function.
"""
# parameters for doScriptOnEntryList
startDir = os.path.join(cingDirTmp, subdir)
pythonScriptFileName = os.path.join(cingDirScripts, 'getPhiPsi.py')
# entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'PDB.LIS')
# entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'PDB_WI_SELECT_Rfactor0.21_Res2.0_2009-02-28_noObs.LIS')
entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'PDB_WI_SELECT_Rfactor0.19_Res1.3_2009-02-28_noObs.LIS')
# entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'PDB_todo.txt')
start_entry_id =0 # default 0
max_entries_todo =1 # default a ridiculously large number like 999999
doScriptOnEntryList(pythonScriptFileName, entryListFileName, startDir,
max_time_to_wait = 240, # 1gkp took over 120
processes_max = 8, # default 3
start_entry_id = start_entry_id, # default 0
max_entries_todo = max_entries_todo # default a ridiculously large number like 999999
)
def refine(self):
"""On self.entry_list_todo.
Return True on error.
NB. On 2012-08-09 a cloud based method was implemented using nrgCing.py
"""
entryListFileName = "entry_list_todo.csv"
writeTextToFile(entryListFileName, toCsv(self.entry_list_todo))
pythonScriptFileName = os.path.join(cingDirScripts, 'refineEntry.py')
# inputDir = 'file://' + self.nrgCing.results_dir + '/' + self.inputDir # NB input is from NrgCing.
inputDir = 'file://' + self.nrgCing.results_dir + '/' + DATA_STR
outputDir = self.results_dir
storeCING2db = "1" # DEFAULT: '1' All arguments need to be strings.
filterTopViolations = '1' # DEFAULT: '1'
filterVasco = '0'
singleCoreOperation = '1'
# Tune this to:
# verbosity inputDir outputDir
# pdbConvention restraintsConvention archiveType projectType
# storeCING2db ranges filterTopViolations filterVasco
# singleCoreOperation
extraArgList = (str(cing.verbosity), inputDir, outputDir, '.', '.',
ARCHIVE_TYPE_BY_CH23_BY_ENTRY, PROJECT_TYPE_CING,
storeCING2db, CV_RANGES_STR, filterTopViolations,
filterVasco, singleCoreOperation)
if doScriptOnEntryList(
pythonScriptFileName,
entryListFileName,
self.results_dir,
processes_max=self.processes_max,
delay_between_submitting_jobs=
5, # why is this so long? because of time outs at tang?
max_time_to_wait=self.max_time_to_wait,
start_entry_id=0,
max_entries_todo=self.max_entries_todo,
extraArgList=extraArgList):
nTerror("Failed to doScriptOnEntryList")
return True
def refine(self):
"""On self.entry_list_todo.
Return True on error.
NB. On 2012-08-09 a cloud based method was implemented using nrgCing.py
"""
entryListFileName = "entry_list_todo.csv"
writeTextToFile(entryListFileName, toCsv(self.entry_list_todo))
pythonScriptFileName = os.path.join(cingDirScripts, 'refineEntry.py')
# inputDir = 'file://' + self.nrgCing.results_dir + '/' + self.inputDir # NB input is from NrgCing.
inputDir = 'file://' + self.nrgCing.results_dir + '/' + DATA_STR
outputDir = self.results_dir
storeCING2db = "1" # DEFAULT: '1' All arguments need to be strings.
filterTopViolations = '1' # DEFAULT: '1'
filterVasco = '0'
singleCoreOperation = '1'
# Tune this to:
# verbosity inputDir outputDir
# pdbConvention restraintsConvention archiveType projectType
# storeCING2db ranges filterTopViolations filterVasco
# singleCoreOperation
extraArgList = ( str(cing.verbosity), inputDir, outputDir,
'.', '.', ARCHIVE_TYPE_BY_CH23_BY_ENTRY, PROJECT_TYPE_CING,
storeCING2db, CV_RANGES_STR, filterTopViolations, filterVasco, singleCoreOperation)
if doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
self.results_dir,
processes_max = self.processes_max,
delay_between_submitting_jobs = 5, # why is this so long? because of time outs at tang?
max_time_to_wait = self.max_time_to_wait,
start_entry_id = 0,
max_entries_todo = self.max_entries_todo,
extraArgList=extraArgList):
nTerror("Failed to doScriptOnEntryList")
return True
def test_DoScriptOnEntryList(self):
cingDirTmpTest = os.path.join( cingDirTmp, getCallerName() )
mkdirs( cingDirTmpTest )
self.failIf(os.chdir(cingDirTmpTest), msg =
"Failed to change to test directory for files: " + cingDirTmpTest)
entryListFileName = "entry_list_todo.csv"
entry_list_todo = [ 0,1,2,3,4,5,6,7,8,9 ]
writeTextToFile(entryListFileName, toCsv(entry_list_todo))
pythonScriptFileName = os.path.join(cingDirScripts, 'doNothing.py')
extraArgList = ('.', '.', '.', '.', ARCHIVE_TYPE_BY_CH23, PROJECT_TYPE_PDB)
self.assertFalse(
doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
'.',
processes_max = 8,
delay_between_submitting_jobs = 5,
max_time_to_wait = 20,
start_entry_id = 0,
max_entries_todo = 1,
extraArgList = extraArgList,
shuffleBeforeSelecting = True ))
# parameters for validateEntry
#inputDir = '/Volumes/proteins/var/www/html/Education/Validation/HTML/Exercise_1/Data/'
#inputDir = '/Users/jd/Sites/cing/in/Tests/data/cyana'
inputDir = os.path.join(cingDirTestsData, "cing" )
outputDir = startDir
pdbConvention = '.'
restraintsConvention = '.'
storeCING2db = "0"
filterTopViolations = '0'
filterVasco = '0'
extraArgList = ( str(cing.verbosity),
inputDir,
outputDir,
pdbConvention,
restraintsConvention,
repr(ARCHIVE_TYPE_FLAT),
repr(PROJECT_TYPE_CING),
storeCING2db, CV_RANGES_STR, filterTopViolations, filterVasco
)
doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
startDir,
processes_max = 8,
max_time_to_wait = 12000, # 1y4o took more than 600. This is one of the optional arguments.
start_entry_id = 0,
max_entries_todo = 10,
extraArgList=extraArgList)
cingDirNRG = os.path.join(cingPythonDir, 'cing', 'NRG' )
pythonScriptFileName = os.path.join(cingDirNRG, 'doAnnotateCasdNmr.py')
if False:
entryListFileName = os.path.join(startDir, 'list', 'entry_list_all.csv')
# entryListFileName = os.path.join(startDir, 'list', 'entry_list_redo.csv')
else:
entryListFileName = os.path.join(startDir, 'list', 'entry_list_single.csv')
entryList = 'VpR247Cheshire'.split()
writeEntryListToFile(entryListFileName, entryList)
extraArgList = ()
doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
startDir,
processes_max = 2,
delay_between_submitting_jobs = 2,
max_time_to_wait = 6000,
start_entry_id = 0,
max_entries_todo = 100,
expectPdbEntryList = False,
extraArgList = extraArgList)
def annotateLoop():
"""
Alternatively to the strategy above use a simple loop that
does not put the log files nicely into separate directories etc.
NOT USED AFTER MOVED HERE.
"""
maxCities = 100
maxEntries = 100
entryList = ['CGR26A']
# cityList = [ 'Cheshire', 'Frankfurt', 'Lyon', 'Paris', 'Piscataway', 'Seattle', 'Utrecht' ]
from cing.NRG.CaspNmrMassageCcpnProject import baseDir
from cing.NRG.PDBEntryLists import writeEntryListToFile
from cing.Scripts.doScriptOnEntryList import doScriptOnEntryList
cing.verbosity = cing.verbosityDebug
cingDirNRG = os.path.join(cingPythonDir, 'cing', 'NRG' )
pythonScriptFileName = os.path.join(cingDirNRG, 'doAnnotateCaspNmr.py')
if False:
entryListFileName = os.path.join(baseDir, 'list', 'entry_list_all.csv')
# entryListFileName = os.path.join(startDir, 'list', 'entry_list_redo.csv')
else:
entryListFileName = os.path.join(baseDir, 'list', 'entry_list_single.csv')
# entryList = 'T0538Org T0538TS001 T0538TS039'.split()
# entryList = 'T0538Org'.split()
# entryList = 'T0538TS001 T0538TS002 T0538TS257'.split()
entryList = 'T0538TS328'.split()
writeEntryListToFile(entryListFileName, entryList)
extraArgList = ()
doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
baseDir,
processes_max = 2,
delay_between_submitting_jobs = 2,
max_time_to_wait = 6000,
start_entry_id = 0,
max_entries_todo = 100,
expectPdbEntryList = False,
extraArgList = extraArgList)
#entryList = list(calcData.keys())
#
entryList = [
tt[0] for tt in sorted(calcData.items()) if tt[1].get('PDBcode') == '2M5O'
]
#entryList.remove('2m2e_Lyon_263')
#entryList = ['2m2e_Lyon_263',]
outputDir = startDir
extraArgList = (inputDirCASD_NMR, outputDir, '.', '.',
ARCHIVE_TYPE_BY_CH23_BY_ENTRY, PROJECT_TYPE_CCPN)
max_time_to_wait = 60 * 60 * 6 # 2p80 took the longest: 5.2 hours.
doScriptOnEntryList(
pythonScriptFileName,
None,
startDir,
processes_max=2,
delay_between_submitting_jobs=
5, # why is this so long? because of time outs at tang?
max_time_to_wait=
max_time_to_wait, # 1y4o took more than 600. This is one of the optional arguments.
# 1ai0 took over 20 min; let's set this to 1 hour
start_entry_id=0,
max_entries_todo=200,
expectPdbEntryList=False,
entryList=entryList,
extraArgList=extraArgList)
# get master results file
calcDataFile = os.path.join(inputDirCASD_NMR, 'calcData.json')
calcData = json.load(open(calcDataFile))
# Get all entries for CASD 2013
#entryList = list(calcData.keys())
#
entryList = [tt[0] for tt in sorted(calcData.items())
if tt[1].get('PDBcode') == '2M5O']
#entryList.remove('2m2e_Lyon_263')
#entryList = ['2m2e_Lyon_263',]
outputDir = startDir
extraArgList = (inputDirCASD_NMR, outputDir, '.', '.', ARCHIVE_TYPE_BY_CH23_BY_ENTRY, PROJECT_TYPE_CCPN)
max_time_to_wait = 60 * 60 * 6 # 2p80 took the longest: 5.2 hours.
doScriptOnEntryList(pythonScriptFileName,
None,
startDir,
processes_max = 2,
delay_between_submitting_jobs = 5, # why is this so long? because of time outs at tang?
max_time_to_wait = max_time_to_wait, # 1y4o took more than 600. This is one of the optional arguments.
# 1ai0 took over 20 min; let's set this to 1 hour
start_entry_id = 0,
max_entries_todo = 200,
expectPdbEntryList = False,
entryList = entryList,
extraArgList = extraArgList)
pythonScriptFileName = os.path.join(cingDirScripts, 'validateEntry.py')
#entryListFileName = os.path.join('/Users/jd', 'entryCodeList.csv')
entryListFileName = os.path.join(cingDirScripts, DATA_STR, 'entryCodeListProteinsSite1')
# parameters for validateEntry
#inputDir = '/Volumes/proteins/var/www/html/Education/Validation/HTML/Exercise_1/Data/'
#inputDir = '/Users/jd/Sites/cing/in/Tests/data/cyana'
inputDir = os.path.join(cingDirTestsData, "cyana" )
outputDir = startDir
#pdbConvention = PDB before using Yasara to update.
pdbConvention = IUPAC
restraintsConvention = CYANA
extraArgList = ( inputDir,
outputDir,
pdbConvention,
restraintsConvention,
repr(ARCHIVE_TYPE_BY_ENTRY),
repr(PROJECT_TYPE_CYANA)
)
doScriptOnEntryList(pythonScriptFileName,
entryListFileName,
startDir,
processes_max = 2,
max_time_to_wait = 12000, # 1y4o took more than 600. This is one of the optional arguments.
start_entry_id = 0,
max_entries_todo = 10,
extraArgList=extraArgList)
for entryCode in entryCodeList:
fileNameZipped = os.path.join(PDBZ2, entryCode[1:3], "pdb" + entryCode + ".ent.gz")
outputFileName = os.path.join(inputDir, entryCode + ".pdb")
dstDir = os.path.join(inputDir, entryCode)
dst = os.path.join(dstDir, entryCode + ".pdb")
cmd = "/Users/jd/BMRB/PdbArchive/getPdb.csh " + entryCode
exit_code = os.system(cmd)
if exit_code:
nTerror("failed to get pdb file")
continue
if gunzip(fileNameZipped, outputFileName=outputFileName):
nTerror("Failed gunzip for entry: " + entryCode)
# Unusual path hierarchy by symlink only.
if not os.path.exists(dstDir):
os.mkdir(dstDir)
if os.path.exists(dst):
os.unlink(dst)
if os.symlink(outputFileName, dst):
nTerror("failed to symlink pdb file")
continue
doScriptOnEntryList(
pythonScriptFileName,
entryListFileName,
startDir,
processes_max=2,
max_time_to_wait=12000, # 1y4o took more than 600. This is one of the optional arguments.
extraArgList=extraArgList,
)
