def processFile():
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
probeID = tokens[0]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
probeKey = loadlib.verifyObject(probeID, mgiTypeKey, None, lineNum,
errorFile)
if probeKey == 0:
continue
if DEBUG:
print deleteSQL % (probeKey)
continue
db.sql(deleteSQL % (probeKey), None)
def processFile():
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
probeID = tokens[0]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
probeKey = loadlib.verifyObject(probeID, mgiTypeKey, None, lineNum, errorFile)
if probeKey == 0:
continue
if DEBUG:
print deleteSQL % (probeKey)
continue
db.sql(deleteSQL % (probeKey), None)
def processSusceptibility():
# do formatted file
doFileName = None
# do file pointer
doFile = None
# insert statement
INSERT_ACCESSION = '''insert into ACC_Accession
values ((select max(_Accession_key) + 1 from ACC_Accession),
'%s', '%s', %s, 15, %s, 13, 0, 0)
'''
doFileName = os.environ['OBO_FILE']
doFile = open(doFileName, 'r')
omimIdValue = 'id: OMIM:'
relValue = 'relationship: RO:0003304'
skipValue = 'OMIM:000000'
foundOMIM = 0
for line in doFile.readlines():
# find [Term]
# find relationship: RO:0003304
if line == '[Term]':
foundOMIM = 0
elif line[:9] == omimIdValue:
omimId = line[4:-1]
if omimId == skipValue:
continue
foundOMIM = 1
elif foundOMIM and line[:24] == relValue:
tokens = line[25:-1].split(' ')
doId = tokens[0]
prefixPart, numericPart = accessionlib.split_accnum(omimId)
objectKey = loadlib.verifyObject(doId, 13, None, None, None)
addSQL = INSERT_ACCESSION % (omimId, prefixPart, numericPart, objectKey)
db.sql(addSQL, None)
else:
continue
doFile.close()
db.commit()
return 0
def process():
global setKey, setMemberKey, setKey
lineNum = 0
sequenceNum = 1
for line in inputFile.readlines():
lineNum = lineNum + 1
tokens = str.split(line[:-1], TAB)
try:
setMember = tokens[0]
setLabel = tokens[1]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
objectKey = loadlib.verifyObject(setMember, mgiTypeKey, "", lineNum,
errorFile)
if objectKey == 0:
continue
outMemberFile.write(str(setMemberKey) + TAB + \
str(setKey) + TAB + \
str(objectKey) + TAB + \
str(setLabel) + TAB + \
str(sequenceNum) + TAB + \
str(createdByKey) + TAB + str(createdByKey) + TAB + \
loaddate + TAB + loaddate + CRT)
setMemberKey = setMemberKey + 1
sequenceNum = sequenceNum + 1
return
def process():
global setKey, setMemberKey, setKey
lineNum = 0
sequenceNum = 1
for line in inputFile.readlines():
lineNum = lineNum + 1
tokens = string.split(line[:-1], TAB)
try:
setMember = tokens[0]
setLabel = tokens[1]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
objectKey = loadlib.verifyObject(setMember, mgiTypeKey, "", lineNum, errorFile)
if objectKey == 0:
continue
outMemberFile.write(str(setMemberKey) + TAB + \
str(setKey) + TAB + \
str(objectKey) + TAB + \
str(setLabel) + TAB + \
str(sequenceNum) + TAB + \
str(createdByKey) + TAB + str(createdByKey) + TAB + \
loaddate + TAB + loaddate + CRT)
setMemberKey = setMemberKey + 1
sequenceNum = sequenceNum + 1
return
def processFile():
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
global refAssocKey
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
accID = tokens[0]
jnum = tokens[1]
refAssocType = tokens[2]
createdBy = tokens[3]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
objectKey = loadlib.verifyObject(accID, mgiTypeKey, None, lineNum, errorFile)
referenceKey = loadlib.verifyReference(jnum, lineNum, errorFile)
refAssocTypeKey = verifyRefAssocType(refAssocType, lineNum)
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if objectKey == 0 or \
referenceKey == 0 or \
refAssocTypeKey == 0 or \
createdByKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process the marker
# could move to verifyDuplicate routine
key = '%s:%s:%s' % (objectKey, referenceKey, refAssocTypeKey)
if refDict.has_key(key):
errorFile.write('Duplicate (%d) %s\n' % (lineNum, line))
continue
refFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (refAssocKey, referenceKey, objectKey, mgiTypeKey, refAssocTypeKey, createdByKey, createdByKey, loaddate, loaddate))
refAssocKey = refAssocKey + 1
def processFile():
'''
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
'''
results = db.sql(
'select maxKey = max(_Translation_key) + 1 from MGI_Translation',
'auto')
transKey = results[0]['maxKey']
if transKey is None:
transKey = 1000
lineNum = 0
# sequence number of bad name in translation list
seq = 1
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
objectID = tokens[0]
objectDescription = tokens[1]
term = tokens[2]
userID = tokens[3]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
continue
if vocabKey > 0:
objectKey = loadlib.verifyTerm(objectID, vocabKey,
objectDescription, lineNum,
errorFile)
else:
objectKey = loadlib.verifyObject(objectID, mgiTypeKey,
objectDescription, lineNum,
errorFile)
userKey = loadlib.verifyUser(userID, lineNum, errorFile)
if objectKey == 0 or userKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
# add term to translation file
bcpWrite(transFile, [
transKey, transTypeKey, objectKey, term, seq, userKey, userKey,
loaddate, loaddate
])
transKey = transKey + 1
seq = seq + 1
# end of "for line in inputFile.readlines():"
if newTransType:
bcpWrite(transTypeFile, [
transTypeKey, mgiTypeKey, vocabKey, transTypeName,
transCompression, 0, userKey, userKey, loaddate, loaddate
])
def getGenotypes():
global genotypeOrderDict
lineNum = 0
genotypeOrder = 1
# annotations organized by order/mpID
# 'order' indicates uniq genotype
# key = order + '|' + mpID
# value = list of lines
annotDict = {}
for line in fpHTMPInput.readlines():
if DEBUG:
print '\nNEW LINE: ', line
error = 0
lineNum = lineNum + 1
tokens = line[:-1].split('\t')
# sc 2/6/2016 - a subtlety:
# if genotypeID remains '', the genotype is not in the database
# if it is assigned an ID from the database, it is still written to
# the genotypeload input file because this file is used as input to the
# annotation load. The genotypeload will only create
# a genotype if the genotypeID field is ''
genotypeID = ''
phenotypingCenter = tokens[0]
annotationCenter = tokens[1]
mutantID = tokens[2]
mutantID2 = mutantID
mpID = tokens[3]
alleleID = tokens[4]
alleleID2 = alleleID
alleleState = tokens[5]
alleleSymbol = tokens[6]
markerID = tokens[7]
strainName = tokens[9]
gender = tokens[10]
colonyID = tokens[11]
# marker
if len(markerID) > 0:
markerKey = loadlib.verifyMarker(markerID, lineNum, fpLogDiag)
else:
markerKey = 0
if markerKey == 0:
logit = errorDisplay % (markerID, lineNum, '8', line)
fpLogDiag.write(logit)
fpLogCur.write(logit)
error = 1
if DEBUG:
print ' markerID: %s markerKey: %s' % (markerID, markerKey)
# allele
if len(alleleID) > 0:
alleleKey = loadlib.verifyObject(alleleID, 11, None, lineNum, fpLogDiag)
else:
alleleKey = 0
if alleleKey == 0:
logit = errorDisplay % (alleleID, lineNum, '5', line)
fpLogDiag.write(logit)
fpLogCur.write(logit)
error = 1
if DEBUG:
print ' alleleID: %s alleleKey: %s' % (alleleID, alleleKey)
# mutant
if len(mutantID) > 0:
mutantKey = alleleloadlib.verifyMutnatCellLine(mutantID, lineNum, fpLogDiag)
mutantKey2 = mutantKey
mutantSQL = mutantSQL2 = '='
else:
mutantSQL = 'is'
mutantKey = 'null'
#
# if the MCL in the input file does not match the Allele/MCL association in MGD,
# (i.e. the mutantKey returned from the alleleloadlib lookup is null),
# then add the Genotype with null MCLs (see TR12508).
#
if mutantKey == 0:
mutantID = ''
mutantID2 = ''
#logit = errorDisplay % (mutantID, lineNum, '3', line)
#fpLogDiag.write(logit)
#fpLogCur.write(logit)
#error = 1
if DEBUG:
print ' mutantID: %s mutantKey: %s' % (mutantID, mutantKey)
# strain should have been added by the previous makeStrains.sh
# wrapper but in case it was not...
strainID = ''
strainKey = 0
# NS strain does not have colony ID, so don't check
if strainName == 'Not Specified':
results = db.sql(''' select * from strains where strain = '%s' ''' % strainName, 'auto')
else:
results = db.sql(''' select * from strains where strain = '%s' and colonyID like'%%%s%%' ''' % (strainName, colonyID), 'auto')
for r in results:
strainID = r['strainID']
strainKey = r['_Strain_key']
if strainKey == 0:
logit = errorDisplay % (strainName + '|' + colonyID, lineNum, '10', line)
fpLogDiag.write(logit)
fpLogCur.write(logit)
if DEBUG:
print ' strainName: %s strainID %s strainKey: %s\n' % (strainName, strainID, strainKey)
# if allele is Heterzygous, then marker must have a wild-type allele
if alleleState == 'Heterozygous':
if DEBUG:
print ' if allele is Heterzygous, then marker must have a wild-type allele, get it'
#
# for heterzygous, allele 2 = the wild type allele
# (marker symbol + '<+>')
# find the wild type allele accession id
#
querySQL = '''
select awt.accID
from ALL_Allele wt, ACC_Accession awt
where wt._Marker_key = %s
and wt.name = 'wild type'
and wt._Allele_key = awt._Object_key
and awt._MGIType_key = 11
and awt._LogicalDB_key = 1
and awt.preferred = 1
''' % (markerKey)
if DEBUG:
print querySQL
results = db.sql(querySQL, 'auto')
for r in results:
# found the wild type, so set it
alleleID2 = r['accID']
mutantID2 = ''
if DEBUG:
print ' found wild type and alleleID2: %s mutantID2: %s' % (alleleID2, mutantID2)
if alleleID == alleleID2:
logit = errorDisplay % (markerID, lineNum, '8', line)
logit = logit + 'no wild type allele exists for this marker'
fpLogDiag.write(logit)
fpLogCur.write(logit)
error = 1
# if error, continue to next line
if error:
fpHTMPError.write(line)
continue
#
# check alleleState
#
if DEBUG:
print '\n Check AlleleState:'
if alleleState == 'Homozygous':
if DEBUG:
print ' Homozygous : querying to find genotype'
querySQL = '''
select g.accID
from genotypes g
where g._Marker_key = %s
and g._Allele_key_1 = %s
and g._Allele_key_2 = %s
and g._MutantCellLine_key_1 %s %s
and g._MutantCellLine_key_2 %s %s
and g.term = '%s'
and g._Strain_key = %s
''' % (markerKey, alleleKey, alleleKey, mutantSQL, mutantKey, mutantSQL, mutantKey, alleleState, strainKey)
if DEBUG:
print querySQL
results = db.sql(querySQL, 'auto')
if len(results) > 1:
if DEBUG:
print ' More than one genotype - last one wins'
print ' %s' % results
for r in results:
genotypeID = r['accID']
if DEBUG:
print ' genotypeID: %s' % genotypeID
elif alleleState == 'Heterozygous':
#
# for heterzygous, allele 2 = the wild type allele
# (marker symbol + '<+>')
# find the wild type allele accession id
#
if DEBUG:
print ' Heterozygous : querying to find genotype'
querySQL = '''
select g.accID
from genotypes g
where g._Marker_key = %s
and g._Allele_key_1 = %s
and g._Allele_key_2 != %s
and g._MutantCellLine_key_1 %s %s
and g._MutantCellLine_key_2 is null
and g.term = '%s'
and g._Strain_key = %s
''' % (markerKey, alleleKey, alleleKey, mutantSQL, mutantKey, alleleState, strainKey)
if DEBUG:
print querySQL
results = db.sql(querySQL, 'auto')
if len(results) > 1:
if DEBUG:
print ' More than one genotype - last one wins'
print ' %s' % results
for r in results:
genotypeID = r['accID']
if DEBUG:
print ' genotypeID: %s' % genotypeID
elif alleleState in ('Hemizygous', 'Indeterminate'):
if DEBUG:
print ' querying to find genotype : ', alleleState
alleleID2 = ''
mutantID2 = ''
if alleleState == 'Hemizygous':
querySQL = '''
select chromosome
from MRK_Marker
where _Marker_key = %s''' % markerKey
results = db.sql(querySQL, 'auto')
for r in results:
if r['chromosome'] == 'X':
alleleState = 'Hemizygous X-linked'
if DEBUG:
print ' ', alleleState
elif r['chromosome'] == 'Y':
alleleState = 'Hemizygous Y-linked'
if DEBUG:
print ' ', alleleState
else:
logit = errorDisplay % (alleleState, lineNum, '6', line)
logit = logit + 'pair state %s does not match chromosome %s' % (alleleState, r['chromosome'])
if DEBUG:
print ' ', logit
fpLogDiag.write(logit)
fpLogCur.write(logit)
error = 1
break
querySQL = '''
select g.accID
from genotypes g
where g._Marker_key = %s
and g._Allele_key_1 = %s
and g._Allele_key_2 is null
and g._MutantCellLine_key_1 %s %s
and g._MutantCellLine_key_2 is null
and g.term = '%s'
and g._Strain_key = %s
''' % (markerKey, alleleKey, mutantSQL, mutantKey, alleleState, strainKey)
if DEBUG:
print querySQL
results = db.sql(querySQL, 'auto')
if len(results) > 1:
if DEBUG:
print ' More than one genotype - last one wins'
print ' %s' % results
for r in results:
genotypeID = r['accID']
if DEBUG:
print ' genotypeID: %s' % genotypeID
else:
logit = errorDisplay % (alleleState, lineNum, '6', line)
if DEBUG:
print ' logging error:'
print ' ' + errorDisplay % (alleleState, lineNum, '6', line)
fpLogDiag.write(logit)
fpLogCur.write(logit)
error = 1
# if error, continue to next line
if error:
fpHTMPError.write(line)
continue
#
# check genotype unique-ness
#
# duplicate genotypes WITHIN the input file, doesn't mean the genotype
# isn't in the database
dupGeno = 0
useOrder = str(genotypeOrder)
if DEBUG:
print ' check genotype uniqueness'
#
# set uniqueness
# isConditional is always 0, so we do not need to specify this value
#
key = str(markerKey) + str(alleleKey) + str(alleleState) + str(strainKey) + str(mutantKey)
if DEBUG:
print ' unique key is: %s' % key
if genotypeOrderDict.has_key(key):
dupGeno = 1
useOrder = str(genotypeOrderDict[key])
if DEBUG:
print ' duplicate genotype and order is: %s' % useOrder
# uniq genotype/mpID key
currentMP = useOrder + '|' + mpID
#### new code HDP-2 US161 support TR11792 ####
# add line to dictionary by currentMP key for later processing
if not annotDict.has_key(currentMP):
annotDict[currentMP] = []
annotDict[currentMP].append(line)
if dupGeno:
fpHTMPDup.write(line)
continue
#
# save genotype order
#
if DEBUG:
print ' saving genotype order genotypeOrderDict[%s] = %s' % (key, genotypeOrder)
genotypeOrderDict[key] = genotypeOrder
#
# add to genotype mgi-format file
#
if DEBUG:
print ' writing genotype to genotype file'
fpGenotype.write(genotypeLine % (\
genotypeOrder, genotypeID, strainID, strainName, \
markerID, alleleID, mutantID, alleleID2, mutantID2, \
conditional, existsAs, generalNote, privateNote, alleleState, \
compound, createdBy))
genotypeOrder = genotypeOrder + 1
#### new code HDP-2 US161 support TR11792 ####
# iterate through annotDict
for key in annotDict.keys():
order, mpID = key.split('|')
lineList = annotDict[key]
genderSet = set([])
# get the gender for each line and add to the set
for line in lineList:
tokens = line.split('\t')
genderSet.add(tokens[10])
# if multi lines, the only difference is gender
# just get the last (or only) line in the list; prepend the order number
line = order + '\t' + line
# if there are multi gender values in the set, update line to 'Both'
if len(genderSet) > 1:
# Don't bother to look at values. If already 'Both', we're golden
# otherwise just update the line to 'Both'
line = line.replace('Male', 'Both')
line = line.replace('Female', 'Both')
# now write out the line
fpHTMP.write(line)
return 0
def processFile():
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
global refAssocKey
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
accID = tokens[0]
jnum = tokens[1]
refAssocType = tokens[2]
createdBy = tokens[3]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
objectKey = loadlib.verifyObject(accID, mgiTypeKey, None, lineNum,
errorFile)
referenceKey = loadlib.verifyReference(jnum, lineNum, errorFile)
refAssocTypeKey = verifyRefAssocType(refAssocType, lineNum)
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if objectKey == 0 or \
referenceKey == 0 or \
refAssocTypeKey == 0 or \
createdByKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process the marker
# could move to verifyDuplicate routine
key = '%s:%s:%s' % (objectKey, referenceKey, refAssocTypeKey)
if refDict.has_key(key):
errorFile.write('Duplicate (%d) %s\n' % (lineNum, line))
continue
refFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (refAssocKey, referenceKey, objectKey, mgiTypeKey, refAssocTypeKey, createdByKey, createdByKey, loaddate, loaddate))
refAssocKey = refAssocKey + 1
def processFile():
global strainKey, strainmarkerKey, accKey, mgiKey, annotKey, noteKey
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = line[:-1].split('\t')
try:
id = tokens[0]
externalPrefix = id
externalNumeric = ''
#(externalPrefix, externalNumeric) = id.split(':')
name = tokens[1]
alleleIDs = tokens[2]
strainType = tokens[3]
species = tokens[4]
isStandard = tokens[5]
sooNote = tokens[6]
externalLDB = tokens[7]
externalTypeKey = tokens[8]
annotations = tokens[9]
createdBy = tokens[10]
mutantNote = tokens[11]
isPrivate = tokens[12]
impcColonyNote = tokens[13]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
strainExistKey = verifyStrain(name, lineNum)
strainTypeKey = verifyStrainType(strainType, lineNum)
speciesKey = verifySpecies(species, lineNum)
createdByKey = loadlib.verifyUser(createdBy, 0, errorFile)
if strainExistKey > 0 or strainTypeKey == 0 or speciesKey == 0 or createdByKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
strainFile.write('%d|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainKey, speciesKey, strainTypeKey, name, isStandard, isPrivate, isGeneticBackground,
createdByKey, createdByKey, cdate, cdate))
# if Allele found, resolve to Marker
if len(alleleIDs) > 0:
allAlleles = alleleIDs.split('|')
for a in allAlleles:
alleleKey = loadlib.verifyObject(a, alleleTypeKey, None, lineNum, errorFile)
if alleleKey == 0:
continue
results = db.sql('select _Marker_key from ALL_Allele where _Allele_key = %s' % (alleleKey), 'auto')
markerKey = results[0]['_Marker_key']
markerFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainmarkerKey, strainKey, markerKey, alleleKey, qualifierKey,
createdByKey, createdByKey, cdate, cdate))
strainmarkerKey = strainmarkerKey + 1
# MGI Accession ID for all strain
accFile.write('%d|%s%d|%s|%s|1|%d|%d|0|1|%s|%s|%s|%s\n' \
% (accKey, mgiPrefix, mgiKey, mgiPrefix, mgiKey, strainKey, mgiTypeKey,
createdByKey, createdByKey, cdate, cdate))
accKey = accKey + 1
# external accession id
# % (accKey, id, '', id, externalLDB, strainKey, externalTypeKey,
#for ids that contain prefix:numeric
accFile.write('%d|%s|%s|%s|%s|%s|%s|0|1|%s|%s|%s|%s\n' \
% (accKey, id, externalPrefix, externalNumeric, externalLDB, strainKey, externalTypeKey,
createdByKey, createdByKey, cdate, cdate))
accKey = accKey + 1
# storing data in MGI_Note/MGI_NoteChunk
# Strain of Origin Note
if len(sooNote) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, strainKey, mgiNoteObjectKey, mgiStrainOriginTypeKey, \
createdByKey, createdByKey, cdate, cdate))
noteChunkFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, 1, sooNote, createdByKey, createdByKey, cdate, cdate))
noteKey = noteKey + 1
# storing data in MGI_Note/MGI_NoteChunk
# Mutant Cell Line of Origin Note
if len(mutantNote) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, strainKey, mgiNoteObjectKey, mgiMutantOriginTypeKey, \
createdByKey, createdByKey, cdate, cdate))
if len(mutantNote) > 0:
noteChunkFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, 1, mutantNote, createdByKey, createdByKey, cdate, cdate))
noteKey = noteKey + 1
# storing data in MGI_Note/MGI_NoteChunk
# IMPC Colony Note
if len(impcColonyNote) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, strainKey, mgiNoteObjectKey, mgiIMPCColonyTypeKey, \
createdByKey, createdByKey, cdate, cdate))
noteChunkFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, 1, sooNote, createdByKey, createdByKey, cdate, cdate))
noteKey = noteKey + 1
#
# Annotations
#
# _AnnotType_key = 1009
# _Qualifier_ke = 1614158
#
if len(annotations) > 0:
annotations = annotations.split('|')
for a in annotations:
# strain annotation type
annotTypeKey = 1009
# this is a null qualifier key
annotQualifierKey = 1614158
annotTermKey = loadlib.verifyTerm('', 27, a, lineNum, errorFile)
if annotTermKey == 0:
continue
annotFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (annotKey, annotTypeKey, strainKey, annotTermKey, annotQualifierKey, cdate, cdate))
annotKey = annotKey + 1
mgiKey = mgiKey + 1
strainKey = strainKey + 1
# end of "for line in inputFile.readlines():"
#
# Update the AccessionMax value
#
db.sql('select * from ACC_setMax (%d)' % (lineNum), None)
db.commit()
# update prb_strain_marker_seq auto-sequence
db.sql(''' select setval('prb_strain_marker_seq', (select max(_StrainMarker_key) from PRB_Strain_Marker)) ''', None)
db.commit()
# update voc_annot_seq auto-sequence
db.sql(''' select setval('voc_annot_seq', (select max(_Annot_key) from VOC_Annot)) ''', None)
db.commit()
def processFile():
global strainKey, strainmarkerKey, accKey, mgiKey, annotKey, noteKey
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
lineNum = lineNum + 1
#print line
# Split the line into tokens
tokens = line[:-1].split('\t')
try:
name = tokens[0]
alleleIDs = tokens[1]
strainType = tokens[2]
species = tokens[3]
isStandard = tokens[4]
createdBy = tokens[5]
mutantNote = tokens[6]
colonyNote = tokens[7]
annotations = tokens[8].split('|')
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
strainExistKey = verifyStrain(name, lineNum)
strainTypeKey = verifyStrainType(strainType, lineNum)
speciesKey = verifySpecies(species, lineNum)
createdByKey = loadlib.verifyUser(createdBy, 0, errorFile)
# if the strain exist, but with no colony id note, create one
if strainExistKey > 0:
print 'strain in database checking colony note : %s' % line
if (not checkColonyNote(strainExistKey) ):
#print 'colony note not in the database: %s' % colonyNote
createNote(strainExistKey, colonyNote, mgiColonyNoteTypeKey, createdByKey)
else:
print 'colony note in database: %s' % colonyNote
continue
else:
print 'strain not in database : %s' % line
# if strain does not exist and verification failed on strain type,
# species or createdBy, skip the record
if strainTypeKey == 0 or speciesKey == 0 \
or createdByKey == 0:
#print 'verification failed on strain type, species or createdBy: %s %s %s ' % (strainTypeKey, speciesKey, createdByKey)
continue
# if no errors, process
strainFile.write('%d|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainKey, speciesKey, strainTypeKey, name, isStandard,
isPrivate, isGeneticBackground, createdByKey, createdByKey,
cdate, cdate))
# if Allele found, resolve to Marker
allAlleles = alleleIDs.split('|')
for a in allAlleles:
alleleKey = loadlib.verifyObject(a, alleleTypeKey, None, lineNum, errorFile)
#print 'makeStrains.py allele: %s marker key: %s' % (a, alleleKey)
results = db.sql('select _Marker_key from ALL_Allele where _Allele_key = %s' % (alleleKey), 'auto')
markerKey = results[0]['_Marker_key']
markerFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainmarkerKey, strainKey, markerKey, alleleKey,
qualifierKey, createdByKey, createdByKey, cdate, cdate))
strainmarkerKey = strainmarkerKey + 1
# MGI Accession ID for the strain
if isStandard == '1':
accFile.write('%d|%s%d|%s|%s|1|%d|%d|0|1|%s|%s|%s|%s\n' \
% (accKey, mgiPrefix, mgiKey, mgiPrefix, mgiKey, strainKey, mgiTypeKey,
createdByKey, createdByKey, cdate, cdate))
accKey = accKey + 1
# storing data in MGI_Note/MGI_NoteChunk
# Colony ID Note
if len(colonyNote) > 0:
createNote(strainKey, colonyNote, mgiColonyNoteTypeKey, createdByKey)
# storing data in MGI_Note/MGI_NoteChunk
# Mutant Cell Line of Origin Note
if len(mutantNote) > 0:
createNote(strainKey, mutantNote, mgiMutOrigNoteTypeKey, createdByKey)
#
# Annotations
#
# _AnnotType_key = 1009 = "Strain/Attributes"
# _Qualifier_key = 1614158 = null
#
for a in annotations:
# strain annotation type
annotTypeKey = 1009
# this is a null qualifier key
annotQualifierKey = 1614158
annotTermKey = loadlib.verifyTerm('', 27, a, lineNum, errorFile)
if annotTermKey == 0:
continue
annotFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (annotKey, annotTypeKey, strainKey, annotTermKey, annotQualifierKey, cdate, cdate))
annotKey = annotKey + 1
mgiKey = mgiKey + 1
strainKey = strainKey + 1
# end of "for line in inputFile.readlines():"
#
# Update the AccessionMax value
#
if not DEBUG:
db.sql('select * from ACC_setMax (%d)' % (lineNum), None)
def processFile():
'''
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
'''
results = db.sql('select maxKey = max(_Translation_key) + 1 from MGI_Translation', 'auto')
transKey = results[0]['maxKey']
if transKey is None:
transKey = 1000
lineNum = 0
# sequence number of bad name in translation list
seq = 1
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
objectID = tokens[0]
objectDescription = tokens[1]
term = tokens[2]
userID = tokens[3]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
continue
if vocabKey > 0:
objectKey = loadlib.verifyTerm(objectID, vocabKey, objectDescription, lineNum, errorFile)
else:
objectKey = loadlib.verifyObject(objectID, mgiTypeKey, objectDescription, lineNum, errorFile)
userKey = loadlib.verifyUser(userID, lineNum, errorFile)
if objectKey == 0 or userKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
# add term to translation file
bcpWrite(transFile, [transKey, transTypeKey, objectKey, term, seq, userKey, userKey, loaddate, loaddate])
transKey = transKey + 1
seq = seq + 1
# end of "for line in inputFile.readlines():"
if newTransType:
bcpWrite(transTypeFile, [transTypeKey, mgiTypeKey, vocabKey, transTypeName, transCompression, 0, userKey, userKey, loaddate, loaddate])
def processFile():
global refKey, aliasKey
global execProbeSQL
global execAssaySQL
global execRefSQL
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
fromID = tokens[0]
name = tokens[1]
toID = tokens[2]
jnum = tokens[3]
createdBy = tokens[4]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
fromKey = loadlib.verifyObject(fromID, mgiTypeKey, None, lineNum,
errorFile)
toKey = loadlib.verifyObject(toID, mgiTypeKey, None, lineNum,
errorFile)
referenceKey = loadlib.verifyReference(jnum, lineNum, errorFile)
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if fromKey == 0:
errorFile.write('Invalid Probe "From": %s\n' % (fromID))
error = 1
if toKey == 0:
errorFile.write('Invalid Probe "To": %s\n' % (toID))
error = 1
if referenceKey == 0:
errorFile.write('Invalid Reference: %s\n' % (jnum))
error = 1
if createdByKey == 0:
errorFile.write('Invalid Creator: %s\n\n' % (createdBy))
error = 1
# check that all genes are the same
checkGenesSQL = '''
select f.*
from PRB_Marker f, PRB_Marker t, GXD_ProbePrep p, GXD_Assay a
where f._Probe_key = %s
and t._Probe_key = %s
and p._Probe_key = %s
and p._ProbePrep_key = a._ProbePrep_key
and f._Marker_key = t._Marker_key
and f._Marker_key = a._Marker_key
''' % (fromKey, toKey, fromKey)
checkGenes = db.sql(checkGenesSQL, 'auto')
if len(checkGenes) == 0:
errorFile.write(
'Gene of GenePaint, Eurexpress and Assay are not the same: %s, %s\n'
% (fromID, toID))
error = 1
# check that the J: is on at least one Assay
checkJAssaySQL = '''
select a.*
from GXD_ProbePrep p, GXD_Assay a
where p._Probe_key = %s
and p._ProbePrep_key = a._ProbePrep_key
and a._Refs_key = %s
''' % (fromKey, referenceKey)
checkJAssay = db.sql(checkJAssaySQL, 'auto')
if len(checkJAssay) == 0:
errorFile.write(
'J: is not on any Assays attached to the probe: %s\n' %
(fromID))
error = 1
# if errors, continue to next record
if error:
continue
# add alias using fromID name (from) to toID
refFile.write('%s\t%s\t%s\t0\t0\t%s\t%s\t%s\t%s\n' \
% (refKey, toKey, referenceKey, createdByKey, createdByKey, loaddate, loaddate))
aliasFile.write('%s\t%s\t%s\t%s\t%s\t%s\t%s\n' \
% (aliasKey, refKey, name, createdByKey, createdByKey, loaddate, loaddate))
refKey = refKey + 1
aliasKey = aliasKey + 1
# move assay information from fromID to toID
execAssaySQL.append(updateAssaySQL % (toKey, fromKey))
# move fromID (from) references to toID
execRefSQL.append(updateRefSQL % (toKey, fromKey, referenceKey))
# delete fromID (from)
execProbeSQL.append(deleteProbeSQL % (fromKey))
def processFile():
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
global synKey
mgiIdsWithSynonyms = synDict.keys()
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
accID = tokens[0]
synonym = tokens[1]
synType = tokens[2]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
objectKey = loadlib.verifyObject(accID, mgiTypeKey, None, lineNum, errorFile)
if accID in mgiIdsWithSynonyms:
if synonym in synDict[accID]:
errorFile.write('Duplicate synonym: %s for %s\n' % (synonym, accID))
continue
synTypeKey = verifySynonymType(synType, lineNum)
if len(synonym) == 0:
errorFile.write('Invalid Synonym:Empty (%d) %s\n' % (lineNum, synonym))
if objectKey == 0 or \
synTypeKey == 0 or \
len(synonym) == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
synFile.write('%d|%d|%d|%d|%s|%s|%s|%s|%s|%s\n' \
% (synKey, objectKey, mgiTypeKey, synTypeKey, referenceKey, synonym, createdByKey, createdByKey, loaddate, loaddate))
synKey = synKey + 1
def processFile():
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
global strainalleleKey
lineNum = 0
notDeleted = 1
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
strainID = tokens[0]
alleleID = tokens[1]
qualifier = tokens[2]
createdBy = tokens[3]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
if len(strainID) == 4:
strainID = '00' + strainID
if len(strainID) == 3:
strainID = '000' + strainID
if len(strainID) == 2:
strainID = '0000' + strainID
if len(strainID) == 1:
strainID = '00000' + strainID
strainKey = loadlib.verifyObject(strainID, strainTypeKey, None, lineNum, errorFile)
# this could generate an error because the ID is a marker, not an allele
# just ignore the error in the error file if it gets resolved later
alleleKey = loadlib.verifyObject(alleleID, alleleTypeKey, None, lineNum, errorFile)
markerKey = 0
if alleleKey == 0:
markerKey = loadlib.verifyObject(alleleID, markerTypeKey, None, lineNum, errorFile)
qualifierKey = verifyQualifier(qualifier, lineNum)
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if notDeleted:
db.sql('delete PRB_Strain_Marker where _CreatedBy_key = %s' % (createdByKey), None)
notDeleted = 0
# if Allele found, resolve to Marker
if alleleKey > 0:
results = db.sql('select _Marker_key from ALL_Allele where _Allele_key = %s' % (alleleKey), 'auto')
if len(results) > 0:
markerKey = results[0]['_Marker_key']
elif markerKey == 0:
errorFile.write('Invalid Allele (%s): %s\n' % (lineNum, alleleID))
error = 1
if strainKey == 0 or markerKey == 0 or qualifierKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
if alleleKey == 0:
alleleKey = ''
strainFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainalleleKey, strainKey, markerKey, alleleKey, qualifierKey, createdByKey, createdByKey, loaddate, loaddate))
strainalleleKey = strainalleleKey + 1
# end of "for line in inputFile.readlines():"
#
# Update the AccessionMax value
#
db.sql('select * from ACC_setMax (%d);' % (lineNum), None)
db.commit()
# update prb_strain_marker_seq auto-sequence
db.sql(''' select setval('prb_strain_marker_seq', (select max(_StrainMarker_key) from PRB_Strain_Marker)) ''', None)
db.commit()
def processFile():
global refKey, aliasKey
global execProbeSQL
global execAssaySQL
global execRefSQL
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
fromID = tokens[0]
name = tokens[1]
toID = tokens[2]
jnum = tokens[3]
createdBy = tokens[4]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
fromKey = loadlib.verifyObject(fromID, mgiTypeKey, None, lineNum, errorFile)
toKey = loadlib.verifyObject(toID, mgiTypeKey, None, lineNum, errorFile)
referenceKey = loadlib.verifyReference(jnum, lineNum, errorFile)
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if fromKey == 0:
errorFile.write('Invalid Probe "From": %s\n' % (fromID))
error = 1
if toKey == 0:
errorFile.write('Invalid Probe "To": %s\n' % (toID))
error = 1
if referenceKey == 0:
errorFile.write('Invalid Reference: %s\n' % (jnum))
error = 1
if createdByKey == 0:
errorFile.write('Invalid Creator: %s\n\n' % (createdBy))
error = 1
# check that all genes are the same
checkGenesSQL = '''
select f.*
from PRB_Marker f, PRB_Marker t, GXD_ProbePrep p, GXD_Assay a
where f._Probe_key = %s
and t._Probe_key = %s
and p._Probe_key = %s
and p._ProbePrep_key = a._ProbePrep_key
and f._Marker_key = t._Marker_key
and f._Marker_key = a._Marker_key
''' % (fromKey, toKey, fromKey)
checkGenes = db.sql(checkGenesSQL, 'auto')
if len(checkGenes) == 0:
errorFile.write('Gene of GenePaint, Eurexpress and Assay are not the same: %s, %s\n' % (fromID, toID))
error = 1
# check that the J: is on at least one Assay
checkJAssaySQL = '''
select a.*
from GXD_ProbePrep p, GXD_Assay a
where p._Probe_key = %s
and p._ProbePrep_key = a._ProbePrep_key
and a._Refs_key = %s
''' % (fromKey, referenceKey)
checkJAssay = db.sql(checkJAssaySQL, 'auto')
if len(checkJAssay) == 0:
errorFile.write('J: is not on any Assays attached to the probe: %s\n' % (fromID))
error = 1
# if errors, continue to next record
if error:
continue
# add alias using fromID name (from) to toID
refFile.write('%s\t%s\t%s\t0\t0\t%s\t%s\t%s\t%s\n' \
% (refKey, toKey, referenceKey, createdByKey, createdByKey, loaddate, loaddate))
aliasFile.write('%s\t%s\t%s\t%s\t%s\t%s\t%s\n' \
% (aliasKey, refKey, name, createdByKey, createdByKey, loaddate, loaddate))
refKey = refKey + 1
aliasKey = aliasKey + 1
# move assay information from fromID to toID
execAssaySQL.append(updateAssaySQL % (toKey, fromKey))
# move fromID (from) references to toID
execRefSQL.append(updateRefSQL % (toKey, fromKey, referenceKey))
# delete fromID (from)
execProbeSQL.append(deleteProbeSQL % (fromKey))
def processFile():
global lineNum
global strainKey, strainmarkerKey, accKey, mgiKey, annotKey, noteKey
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = line[:-1].split('\t')
try:
id = tokens[0]
externalPrefix = id
externalNumeric = ''
#(externalPrefix, externalNumeric) = id.split(':')
name = tokens[1]
alleleIDs = tokens[2]
strainType = tokens[3]
species = tokens[4]
isStandard = tokens[5]
sooNote = tokens[6]
externalLDB = tokens[7]
externalTypeKey = tokens[8]
annotations = tokens[9]
createdBy = tokens[10]
mutantNote = tokens[11]
isPrivate = tokens[12]
impcColonyNote = tokens[13]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
strainExistKey = verifyStrain(name, lineNum)
strainTypeKey = verifyStrainType(strainType, lineNum)
speciesKey = verifySpecies(species, lineNum)
createdByKey = loadlib.verifyUser(createdBy, 0, errorFile)
if strainExistKey > 0 or strainTypeKey == 0 or speciesKey == 0 or createdByKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
strainFile.write('%d|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainKey, speciesKey, strainTypeKey, name, isStandard, isPrivate, isGeneticBackground,
createdByKey, createdByKey, cdate, cdate))
# if Allele found, resolve to Marker
if len(alleleIDs) > 0:
allAlleles = alleleIDs.split('|')
for a in allAlleles:
alleleKey = loadlib.verifyObject(a, alleleTypeKey, None, lineNum, errorFile)
if alleleKey == 0:
continue
if alleleKey == None:
continue
results = db.sql('select _Marker_key from ALL_Allele where _Allele_key = %s' % (alleleKey), 'auto')
markerKey = results[0]['_Marker_key']
if markerKey != None:
markerFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainmarkerKey, strainKey, markerKey, alleleKey, qualifierKey,
createdByKey, createdByKey, cdate, cdate))
else:
markerFile.write('%s|%s||%s|%s|%s|%s|%s|%s\n' \
% (strainmarkerKey, strainKey, alleleKey, qualifierKey,
createdByKey, createdByKey, cdate, cdate))
strainmarkerKey = strainmarkerKey + 1
# MGI Accession ID for all strain
# all private = 0 (false)
accFile.write('%d|%s%d|%s|%s|1|%d|%d|%s|1|%s|%s|%s|%s\n' \
% (accKey, mgiPrefix, mgiKey, mgiPrefix, mgiKey, strainKey, mgiTypeKey,
isPrivate, createdByKey, createdByKey, cdate, cdate))
accKey = accKey + 1
# external accession id
# % (accKey, id, '', id, externalLDB, strainKey, externalTypeKey,
#for ids that contain prefix:numeric
accFile.write('%d|%s|%s|%s|%s|%s|%s|0|1|%s|%s|%s|%s\n' \
% (accKey, id, externalPrefix, externalNumeric, externalLDB, strainKey, externalTypeKey,
createdByKey, createdByKey, cdate, cdate))
accKey = accKey + 1
# storing data in MGI_Note
# Strain of Origin Note
if len(sooNote) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, strainKey, mgiNoteObjectKey, mgiStrainOriginTypeKey, sooNote, \
createdByKey, createdByKey, cdate, cdate))
noteKey = noteKey + 1
# storing data in MGI_Note
# Mutant Cell Line of Origin Note
if len(mutantNote) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, strainKey, mgiNoteObjectKey, mgiMutantOriginTypeKey, mutantNote, \
createdByKey, createdByKey, cdate, cdate))
noteKey = noteKey + 1
# storing data in MGI_Note
# IMPC Colony Note
if len(impcColonyNote) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, strainKey, mgiNoteObjectKey, mgiIMPCColonyTypeKey, impcColonyNote, \
createdByKey, createdByKey, cdate, cdate))
noteKey = noteKey + 1
#
# Annotations
#
# _AnnotType_key = 1009
# _Qualifier_ke = 1614158
#
if len(annotations) > 0:
annotations = annotations.split('|')
for a in annotations:
# strain annotation type
annotTypeKey = 1009
# this is a null qualifier key
annotQualifierKey = 1614158
annotTermKey = loadlib.verifyTerm('', 27, a, lineNum, errorFile)
if annotTermKey == 0:
continue
annotFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (annotKey, annotTypeKey, strainKey, annotTermKey, annotQualifierKey, cdate, cdate))
annotKey = annotKey + 1
mgiKey = mgiKey + 1
strainKey = strainKey + 1
def processFile():
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
global synKey
mgiIdsWithSynonyms = synDict.keys()
lineNum = 0
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
accID = tokens[0]
synonym = tokens[1]
synType = tokens[2]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
objectKey = loadlib.verifyObject(accID, mgiTypeKey, None, lineNum, errorFile)
if accID in mgiIdsWithSynonyms:
if synonym in synDict[accID]:
errorFile.write('Duplicate synonym: %s for %s\n' % (synonym, accID))
continue
synTypeKey = verifySynonymType(synType, lineNum)
if len(synonym) == 0:
errorFile.write('Invalid Synonym:Empty (%d) %s\n' % (lineNum, synonym))
if objectKey == 0 or \
synTypeKey == 0 or \
len(synonym) == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
synFile.write('%d|%d|%d|%d|%s|%s|%s|%s|%s|%s\n' \
% (synKey, objectKey, mgiTypeKey, synTypeKey, referenceKey, synonym, createdByKey, createdByKey, loaddate, loaddate))
synKey = synKey + 1
def processFile():
# requires:
#
# effects:
# Reads input file
# Verifies and Processes each line in the input file
#
# returns:
# nothing
#
global strainalleleKey
lineNum = 0
notDeleted = 1
# For each line in the input file
for line in inputFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = str.split(line[:-1], '\t')
try:
strainID = tokens[0]
alleleID = tokens[1]
qualifier = tokens[2]
createdBy = tokens[3]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
if len(strainID) == 4:
strainID = '00' + strainID
if len(strainID) == 3:
strainID = '000' + strainID
if len(strainID) == 2:
strainID = '0000' + strainID
if len(strainID) == 1:
strainID = '00000' + strainID
strainKey = loadlib.verifyObject(strainID, strainTypeKey, None,
lineNum, errorFile)
# this could generate an error because the ID is a marker, not an allele
# just ignore the error in the error file if it gets resolved later
alleleKey = loadlib.verifyObject(alleleID, alleleTypeKey, None,
lineNum, errorFile)
markerKey = 0
if alleleKey == 0:
markerKey = loadlib.verifyObject(alleleID, markerTypeKey, None,
lineNum, errorFile)
qualifierKey = verifyQualifier(qualifier, lineNum)
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if notDeleted:
db.sql(
'delete PRB_Strain_Marker where _CreatedBy_key = %s' %
(createdByKey), None)
notDeleted = 0
# if Allele found, resolve to Marker
if alleleKey > 0:
results = db.sql(
'select _Marker_key from ALL_Allele where _Allele_key = %s' %
(alleleKey), 'auto')
if len(results) > 0:
markerKey = results[0]['_Marker_key']
elif markerKey == 0:
errorFile.write('Invalid Allele (%s): %s\n' % (lineNum, alleleID))
error = 1
if strainKey == 0 or markerKey == 0 or qualifierKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
if alleleKey == 0:
alleleKey = ''
strainFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (strainalleleKey, strainKey, markerKey, alleleKey, qualifierKey, createdByKey, createdByKey, loaddate, loaddate))
strainalleleKey = strainalleleKey + 1
# end of "for line in inputFile.readlines():"
#
# Update the AccessionMax value
#
db.sql('select * from ACC_setMax (%d);' % (lineNum), None)
db.commit()
# update prb_strain_marker_seq auto-sequence
db.sql(
''' select setval('prb_strain_marker_seq', (select max(_StrainMarker_key) from PRB_Strain_Marker)) ''',
None)
db.commit()