def ImportRefGenome(calculationObject, datasetId, folder, importSettings):
with calculationObject.LogHeader('Importing reference genome data'):
ImportRefGenomeSummaryData(calculationObject, datasetId, folder,
importSettings)
settings = SettingsLoader.SettingsLoader(
os.path.join(folder, 'settings'))
settings.DefineKnownTokens(['AnnotMaxViewportSize', 'RefSequenceSumm'])
print('Settings: ' + str(settings.Get()))
ImpUtils.ImportGlobalSettings(calculationObject, datasetId, settings)
# Import reference genome
if importSettings['ScopeStr'] == 'all':
refsequencefile = os.path.join(folder, 'refsequence.fa')
if os.path.exists(refsequencefile):
with calculationObject.LogHeader(
'Converting reference genome'):
destfolder = config.BASEDIR + '/SummaryTracks/' + datasetId + '/Sequence'
if not os.path.exists(destfolder):
os.makedirs(destfolder)
tempfastafile = destfolder + '/refsequence.fa'
shutil.copyfile(refsequencefile, tempfastafile)
ImpUtils.RunConvertor(calculationObject,
'Fasta2FilterBankData', destfolder,
['refsequence.fa'])
else:
calculationObject.Log(
'WARNING: missing reference sequence file')
else:
calculationObject.Log(
'WARNING: Skipping converting reference genome')
# Import chromosomes
with calculationObject.LogHeader('Loading chromosomes'):
tb = VTTable.VTTable()
tb.allColumnsText = True
try:
tb.LoadFile(os.path.join(folder, 'chromosomes'))
except Exception as e:
raise Exception('Error while reading chromosomes file: ' +
str(e))
tb.RequireColumnSet(['chrom', 'length'])
tb.RenameCol('chrom', 'id')
tb.RenameCol('length', 'len')
tb.ConvertColToValue('len')
with calculationObject.LogDataDump():
tb.PrintRows(0, 99)
sqlfile = ImpUtils.GetTempFileName()
tb.SaveSQLDump(sqlfile, 'chromosomes')
ImpUtils.ExecuteSQL(calculationObject, datasetId,
'DELETE FROM chromosomes')
ImpUtils.ExecuteSQLScript(calculationObject, sqlfile, datasetId)
os.remove(sqlfile)
if importSettings['ScopeStr'] == 'all':
# Import annotation
with calculationObject.LogHeader('Converting annotation'):
tempgfffile = ImpUtils.GetTempFileName()
temppath = os.path.dirname(tempgfffile)
shutil.copyfile(os.path.join(folder, 'annotation.gff'),
tempgfffile)
ImpUtils.RunConvertor(calculationObject, 'ParseGFF', temppath,
[os.path.basename(tempgfffile)])
print('Importing annotation')
ImpUtils.ExecuteSQLScript(
calculationObject,
os.path.join(temppath, 'annotation_dump.sql'), datasetId)
os.remove(tempgfffile)
os.remove(os.path.join(temppath, 'annotation.txt'))
os.remove(os.path.join(temppath, 'annotation_dump.sql'))
os.remove(os.path.join(temppath, 'annotation_create.sql'))
else:
calculationObject.Log('WARNING: Skipping converting annotation')
