def processFile():
global alleleKey, refAssocKey, accKey, noteKey, mgiKey, annotKey
global alleleLookup
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')
#print line
try:
markerID = tokens[0]
symbol = tokens[1]
name = tokens[2]
alleleStatus = tokens[3]
alleleType = tokens[4]
alleleSubtypes = tokens[5]
collectionKey = tokens[6]
germLine = tokens[7]
references = tokens[8]
strainOfOrigin = tokens[9]
mutantCellLine = tokens[10]
molecularNotes = tokens[11]
driverNotes = tokens[12]
ikmcNotes = tokens[13]
mutations = tokens[14]
inheritanceMode = tokens[15]
isMixed = tokens[16]
isExtinct = tokens[17]
createdBy = tokens[18]
createMCL = tokens[19]
createNote = tokens[20]
setStatus = tokens[21]
existingAlleleID = tokens[22]
ikmcSymbol = tokens[23]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
# creator
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if createdByKey == 0:
continue
# processing for IKMC-only
if len(createMCL) > 0 or len(createNote) > 0 or len(setStatus) > 0:
processFileIKMC(createMCL, createNote, setStatus, \
symbol, ikmcSymbol, mutantCellLine, ikmcNotes, \
createdByKey, existingAlleleID)
continue
# marker key
markerKey = loadlib.verifyMarker(markerID, lineNum, errorFile)
# hard-coded
# _vocab_key = 73 (Marker-Allele Association Status)
# _term_key = 4268545 (Curated)
markerStatusKey = 4268545
# _vocab_key = 37 (Allele Status)
alleleStatusKey = loadlib.verifyTerm('', 37, alleleStatus, lineNum, errorFile)
# _vocab_key = 38 (Allele Type)
alleleTypeKey = loadlib.verifyTerm('', 38, alleleType, lineNum, errorFile)
# _vocab_key = 61 (Allele Transmission)
germLineKey = loadlib.verifyTerm('', 61, germLine, lineNum, errorFile)
# _vocab_key = 36 (Allele Molecular Mutation)
allMutations = mutations.split('|')
# _vocab_key = 35 (Allele Status)
inheritanceModeKey = loadlib.verifyTerm('', 35, inheritanceMode, lineNum, errorFile)
# strains
strainOfOriginKey = sourceloadlib.verifyStrain(strainOfOrigin, lineNum, errorFile)
# reference
refKey = loadlib.verifyReference(jnum, lineNum, errorFile)
# if errors, continue to next record
# errors are stored (via loadlib) in the .error log
if markerKey == 0 \
or markerStatusKey == 0 \
or alleleStatusKey == 0 \
or alleleTypeKey == 0 \
or germLineKey == 0 \
or allMutations == 0 \
or inheritanceModeKey == 0 \
or strainOfOriginKey == 0 \
or refKey == 0 \
or createdByKey == 0:
continue
# if no errors, process the allele
# not specified/testing
#collectionKey = 11025586
# allele (master)
alleleFile.write('%d|%s|%s|%s|%s|%s|%s|%s|%s|%s|0|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (alleleKey, markerKey, strainOfOriginKey, inheritanceModeKey, alleleTypeKey, \
alleleStatusKey, germLineKey, collectionKey, symbol, name, \
isExtinct, isMixed, refKey, markerStatusKey, \
createdByKey, createdByKey, createdByKey, loaddate, loaddate, loaddate))
# molecular mutation
for mutation in allMutations:
mutationKey = loadlib.verifyTerm('', 36, mutation, lineNum, errorFile)
mutationFile.write('%s|%s|%s|%s\n' \
% (alleleKey, mutationKey, loaddate, loaddate))
#
# allele references
#
allReferences = references.split('||')
for reference in allReferences:
refType, refID = reference.split('|')
refKey = loadlib.verifyReference(refID, lineNum, errorFile)
if refType == 'Original':
refAssocTypeKey = 1011
elif refType == 'Transmission':
refAssocTypeKey = 1023
elif refType == 'Molecular':
refAssocTypeKey = 1012
refFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (refAssocKey, refKey, alleleKey, mgiTypeKey, refAssocTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
refAssocKey = refAssocKey + 1
#
# allele subtypes
#
allSubtypes = alleleSubtypes.split('|')
for s in allSubtypes:
# _vocab_key = 93 (Allele Subtype)
alleleSubtypeKey = loadlib.verifyTerm('', 93, s, lineNum, errorFile)
annotFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (annotKey, annotTypeKey, alleleKey, alleleSubtypeKey, \
qualifierKey, loaddate, loaddate))
annotKey = annotKey + 1
#
# mutant cell line
#
if len(mutantCellLine) > 0:
addMutantCellLine(alleleKey, mutantCellLine, createdByKey)
# MGI Accession ID for the allelearker
accFile.write('%s|%s%d|%s|%s|1|%d|%d|0|1|%s|%s|%s|%s\n' \
% (accKey, mgiPrefix, mgiKey, mgiPrefix, mgiKey, alleleKey, mgiTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
# storing data in MGI_Note/MGI_NoteChunk
# molecular notes
mgiNoteSeqNum = 1
if len(molecularNotes) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, alleleKey, mgiNoteObjectKey, mgiMolecularNoteTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
noteChunkFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, mgiNoteSeqNum, molecularNotes, createdByKey, createdByKey, loaddate, loaddate))
noteKey = noteKey + 1
# driver notes
# TR12662/MGI_Relationship._Category_key = 1006
# removed noteFile code
# place hodler for MGI_Relationship code
# the IKMC is the only product using this and IKMC does not add any driver note
#mgiNoteSeqNum = 1
#if len(driverNotes) > 0:
# ikmc notes
useIKMCnotekey = 0
if len(ikmcNotes) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, alleleKey, mgiNoteObjectKey, mgiIKMCNoteTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
noteChunkFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, 1, ikmcNotes, createdByKey, createdByKey, loaddate, loaddate))
useIKMCnotekey = noteKey
noteKey = noteKey + 1
# Print out a new text file and attach the new MGI Allele IDs as the last field
if createdBy == 'ikmc_alleleload':
newAlleleFile.write('%s\t%s%s\t%s\n' \
% (mgi_utils.prvalue(ikmcNotes), \
mgi_utils.prvalue(mgiPrefix), mgi_utils.prvalue(mgiKey), \
mgi_utils.prvalue(ikmcSymbol)))
else:
newAlleleFile.write('%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s%s\n' \
% (mgi_utils.prvalue(markerID), \
mgi_utils.prvalue(symbol), \
mgi_utils.prvalue(name), \
mgi_utils.prvalue(alleleStatus), \
mgi_utils.prvalue(alleleType), \
mgi_utils.prvalue(alleleSubtype), \
mgi_utils.prvalue(collection), \
mgi_utils.prvalue(germLine), \
mgi_utils.prvalue(references), \
mgi_utils.prvalue(strainOfOrigin), \
mgi_utils.prvalue(mutantCellLine), \
mgi_utils.prvalue(allMutations), \
mgi_utils.prvalue(inheritanceMode), \
mgi_utils.prvalue(isMixed), \
mgi_utils.prvalue(isExtinct), \
mgi_utils.prvalue(refKey), \
mgi_utils.prvalue(markerStatusKey), \
mgi_utils.prvalue(createdBy), \
mgi_utils.prvalue(mgiPrefix), mgi_utils.prvalue(mgiKey)))
# save symbol/alleleKey/ikmc note key
alleleLookup[symbol] = []
alleleLookup[symbol].append((alleleKey, useIKMCnotekey, mgiPrefix + str(mgiKey)))
accKey = accKey + 1
mgiKey = mgiKey + 1
alleleKey = alleleKey + 1
# end of "for line in inputFile.readlines():"
#
# Update the AccessionMax value
#
if not DEBUG:
db.sql('select * from ACC_setMax(%d)' % (lineNum), None)
db.commit()
def sanityCheck(biotypeVocab, biotypeTerm, mcvTerms, primaryMCVTerm,
markerType, lineNum):
'''
#
# requires:
#
# effects:
#
# returns:
# List [] of error messages if sanity check fails
# Empty list [] if all sanity checks pass
#
'''
global biotypeVocabKey
global biotypeTermKey
global mcvTermKeys
global markerTypeKey
global primaryMCVTermKey
errors = []
mcvTermKeys = []
#
# BioType Vocabularies
#
biotypeVocabKey = 0
if biotypeVocab == 'Ensembl':
biotypeVocabKey = ENSEMBL_VOCAB_KEY
elif biotypeVocab == 'NCBI':
biotypeVocabKey = NCBI_VOCAB_KEY
elif biotypeVocab == 'MGP':
biotypeVocabKey = MGP_VOCAB_KEY
elif biotypeVocab == 'EnsemblR':
biotypeVocabKey = ENSEMBLREG_VOCAB_KEY
elif biotypeVocab == 'VISTA':
biotypeVocabKey = VISTAREG_VOCAB_KEY
else:
errors.append(INVALID_VOCAB_ERROR % (lineNum, biotypeVocab))
# Lookup the biotype _term_key for this vocab/term
if biotypeVocabKey:
biotypeTermKey = loadlib.verifyTerm('', biotypeVocabKey, biotypeTerm,
lineNum, errorFile)
if biotypeTermKey == 0:
errors.append(INVALID_BIOTYPE_TERM_ERROR %
(lineNum, biotypeTerm, biotypeVocab))
# lookup the _marker_type_key
markerTypeKey = loadlib.verifyMarkerType(markerType, lineNum, errorFile)
if markerTypeKey == 0:
errors.append(INVALID_MARKER_TYPE_ERROR % (lineNum, markerType))
#
# mcv/feature types
#
tokens = mcvTerms.split('|')
for r in tokens:
t = loadlib.verifyTerm('', MCV_VOCAB_KEY, r, lineNum, errorFile)
if t == 0:
errors.append(INVALID_MCV_TERM_ERROR % (lineNum, r))
else:
mcvTermKeys.append(t)
# lookup the primary feature type
primaryMCVTermKey = loadlib.verifyTerm('', MCV_VOCAB_KEY, primaryMCVTerm,
lineNum, errorFile)
if primaryMCVTermKey == 0:
errors.append(INVALID_MARKER_TYPE_ERROR % (lineNum, primaryMCVTerm))
return errors
def processFile():
# Purpose: Read the input file, resolve values to keys. Create bcp files
# Returns: 1 if error, else 0
# Assumes: file descriptors have been initialized
# Effects: exits if the line does not have 15 columns
# Throws: Nothing
global alleleKey, refAssocKey, accKey, noteKey, mgiKey, annotKey
global alleleLookup, alleleMutationKey
lineNum = 0
# For each line in the input file
for line in fpInputFile.readlines():
error = 0
lineNum = lineNum + 1
print('%s: %s' % (lineNum, line))
# Split the line into tokens
tokens = line[:-1].split('\t')
try:
markerID = tokens[0]
markerSymbol = tokens[1]
mutationType = tokens[2] # IMPC allele type
description = tokens[3]
colonyID = tokens[4]
strainOfOrigin = tokens[5]
alleleSymbol = tokens[6]
alleleName = tokens[7]
inheritanceMode = tokens[8]
alleleType = tokens[9] # IMPC allele class
alleleSubType = tokens[10]
alleleStatus = tokens[11]
transmission = tokens[12]
collection = tokens[13]
jNum = tokens[14]
createdBy = tokens[15]
except:
print('exiting with invalid line')
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
print('validating data and getting keys')
# marker key
markerKey = loadlib.verifyMarker(markerID, lineNum, fpErrorFile)
# _vocab_key = 36 (Allele Molecular Mutation)
mutationList = str.split(mutationType, ';')
if len(mutationList) > 1:
print('mutationList: %s' % mutationList)
mutationKeyList = []
for m in mutationList:
mutationKey = loadlib.verifyTerm('', 36, m, lineNum, fpErrorFile)
if mutationKey != 0:
mutationKeyList.append(mutationKey)
if len(mutationKeyList) > 1:
print('mutationKeyList: %s' % mutationKeyList)
# strains
strainOfOriginKey = sourceloadlib.verifyStrain(strainOfOrigin, lineNum,
fpErrorFile)
# _vocab_key = 35 (Allele Inheritance Mode)
inheritanceModeKey = loadlib.verifyTerm('', 35, inheritanceMode,
lineNum, fpErrorFile)
# _vocab_key = 38 (Allele Type)
alleleTypeKey = loadlib.verifyTerm('', 38, alleleType, lineNum,
fpErrorFile)
# _vocab_key = 93 (Allele Subtype)
subTypeList = str.split(alleleSubType, ';')
if len(subTypeList) > 1:
print('subTypeList: %s' % subTypeList)
subTypeKeyList = []
for s in subTypeList:
if s != '': # if we have a subtype, get it's key
subTypeKey = loadlib.verifyTerm('', 93, s, lineNum,
fpErrorFile)
if subTypeKey != 0:
subTypeKeyList.append(subTypeKey)
if len(subTypeKeyList) > 1:
print('subTypeKeyList: %s' % subTypeKeyList)
# _vocab_key = 37 (Allele Status)
alleleStatusKey = loadlib.verifyTerm('', 37, alleleStatus, lineNum,
fpErrorFile)
# _vocab_key = 61 (Allele Transmission)
transmissionKey = loadlib.verifyTerm('', 61, transmission, lineNum,
fpErrorFile)
# _vocab_key = 92
collectionKey = loadlib.verifyTerm('', 92, collection, lineNum,
fpErrorFile)
# _vocab_key = 73 (Marker-Allele Association Status)
# _term_key = 4268545 (Curated)
markerStatusKey = 4268545
# reference
refKey = loadlib.verifyReference(jNum, lineNum, fpErrorFile)
# creator
createdByKey = loadlib.verifyUser(createdBy, lineNum, fpErrorFile)
if createdByKey == 0:
continue
print('checking for missing data')
# if errors, continue to next record
# errors are stored (via loadlib) in the .error log
if markerKey == 0 \
or mutationKeyList == [] \
or strainOfOriginKey == 0 \
or inheritanceModeKey == 0 \
or alleleTypeKey == 0 \
or alleleStatusKey == 0 \
or transmissionKey == 0 \
or collectionKey == 0 \
or refKey == 0 \
or createdByKey == 0:
print('missing data, skipping this line')
continue
# if no errors, process the allele
print('writing to allele file')
# allele (isWildType = 0)
fpAlleleFile.write('%d|%s|%s|%s|%s|%s|%s|%s|%s|%s|0|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (alleleKey, markerKey, strainOfOriginKey, inheritanceModeKey, alleleTypeKey, \
alleleStatusKey, transmissionKey, collectionKey, alleleSymbol, alleleName, \
isExtinct, isMixed, refKey, markerStatusKey, \
createdByKey, createdByKey, createdByKey, loaddate, loaddate, loaddate))
# molecular mutation
for mutationKey in mutationKeyList:
fpMutationFile.write('%s|%s|%s|%s|%s\n' \
% (alleleMutationKey, alleleKey, mutationKey, loaddate, loaddate))
alleleMutationKey += 1
# reference associations
# Original
fpRefFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (refAssocKey, refKey, alleleKey, mgiTypeKey, origRefTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
refAssocKey = refAssocKey + 1
# Molecular
fpRefFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (refAssocKey, refKey, alleleKey, mgiTypeKey, molRefTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
refAssocKey = refAssocKey + 1
# allele subtype
for subTypeKey in subTypeKeyList:
fpAnnotFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (annotKey, annotTypeKey, alleleKey, subTypeKey, \
qualifierKey, loaddate, loaddate))
annotKey = annotKey + 1
# MGI Accession ID for the allele
alleleID = '%s%s' % (mgiPrefix, mgiKey)
fpAccFile.write('%s|%s|%s|%s|1|%d|%d|0|1|%s|%s|%s|%s\n' \
% (accKey, alleleID, mgiPrefix, mgiKey, alleleKey, mgiTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
# storing data in MGI_Note
# molecular note
fpNoteFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, alleleKey, mgiTypeKey, molecularNoteTypeKey, description,\
createdByKey, createdByKey, loaddate, loaddate))
noteKey = noteKey + 1
# colony ID note
fpNoteFile.write('%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, alleleKey, mgiTypeKey, colonyIdNoteTypeKey, colonyID, \
createdByKey, createdByKey, loaddate, loaddate))
noteKey = noteKey + 1
# Print out a new text file and attach the new MGI Allele IDs
# as the last field
fpNewAlleleRptFile.write('%s\t%s\t%s\t%s\t%s\t%s\n' \
% (mgi_utils.prvalue(alleleID), \
mgi_utils.prvalue(alleleSymbol), \
mgi_utils.prvalue(alleleName), \
mgi_utils.prvalue(markerID), \
mgi_utils.prvalue(markerSymbol), \
mgi_utils.prvalue(colonyID)))
accKey = accKey + 1
mgiKey = mgiKey + 1
alleleKey = alleleKey + 1
#
# Update the AccessionMax value
#
print('DEBUG: %s' % DEBUG)
if DEBUG == 'false':
db.sql('select * from ACC_setMax(%d)' % (lineNum), None)
db.commit()
return 0
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
#
'''
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 processImageFile():
global imageKey, accKey, mgiKey
global imagePix
global referenceKey
lineNum = 0
# For each line in the input file
for line in inImageFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], '\t')
try:
jnum = tokens[0]
fullsizeKey = tokens[1]
imageClass = tokens[2]
pixID = tokens[3]
xdim = tokens[4]
ydim = tokens[5]
figureLabel = tokens[6]
copyrightNote = tokens[7]
imageNote = tokens[8]
imageInfo = tokens[9]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
imageClassKey = loadlib.verifyTerm('', imageVocabClassKey, imageClass, lineNum, errorFile)
if imageClassKey == 0:
error = 1
referenceKey = loadlib.verifyReference(jnum, lineNum, errorFile)
if referenceKey == 0:
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
imageTypeKey = FSimageTypeKey
outImageFile.write(str(imageKey) + TAB + \
str(gxdMgiTypeKey) + TAB + \
str(imageClassKey) + TAB + \
str(imageTypeKey) + TAB + \
str(referenceKey) + TAB + \
TAB + \
xdim + TAB + \
ydim + TAB + \
figureLabel + TAB + \
str(createdByKey) + TAB + \
str(createdByKey) + TAB + \
loaddate + TAB + loaddate + CRT)
# MGI Accession ID for the image
mgiAccID = mgiPrefix + str(mgiKey)
outAccFile.write(str(accKey) + TAB + \
mgiPrefix + str(mgiKey) + TAB + \
mgiPrefix + TAB + \
str(mgiKey) + TAB + \
accLogicalDBKey + TAB + \
str(imageKey) + TAB + \
imageMgiTypeKey + TAB + \
accPrivate + TAB + \
accPreferred + TAB + \
str(createdByKey) + TAB + \
str(createdByKey) + TAB + \
loaddate + TAB + loaddate + CRT)
accKey = accKey + 1
mgiKey = mgiKey + 1
if pixID.find('GUDMAP') < 0 and len(pixID) > 0:
outAccFile.write(str(accKey) + TAB + \
pixPrefix + str(pixID) + TAB + \
pixPrefix + TAB + \
pixID + TAB + \
pixLogicalDBKey + TAB + \
str(imageKey) + TAB + \
imageMgiTypeKey + TAB + \
pixPrivate + TAB + \
accPreferred + TAB + \
str(createdByKey) + TAB + \
str(createdByKey) + TAB + \
loaddate + TAB + loaddate + CRT)
accKey = accKey + 1
if len(imageInfo) > 0:
imageLogicalDBKey, imageID = imageInfo.split('|')
outAccFile.write(str(accKey) + TAB + \
imageID + TAB + \
imageID + TAB + \
TAB + \
imageLogicalDBKey + TAB + \
str(imageKey) + TAB + \
imageMgiTypeKey + TAB + \
accPrivate + TAB + \
accPreferred + TAB + \
str(createdByKey) + TAB + \
str(createdByKey) + TAB + \
loaddate + TAB + loaddate + CRT)
accKey = accKey + 1
# Copyrights
if len(copyrightNote) > 0:
outCopyrightFile.write(mgiAccID + TAB + copyrightNote + CRT)
# Notes
if len(imageNote) > 0:
outCaptionFile.write(mgiAccID + TAB + imageNote + CRT)
imagePix[pixID] = imageKey
imageKey = imageKey + 1
# end of "for line in inImageFile.readlines():"
return lineNum
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 processResultsFile(referenceKey):
global resultKey
global imagePaneLookup
prevAssay = 0
prevSpecimen = 0
prevResult = 0
lineNum = 0
#
# build imagePaneLookup lookup of figure label|pane label keys
# J:226028/227123
#
results = db.sql('''
select i.figureLabel, p.paneLabel, p._ImagePane_key
from IMG_Image i, IMG_ImagePane p
where i._Image_key = p._Image_key
and i._Refs_key = %s
''' % (referenceKey), 'auto')
for r in results:
paneLabel = r['paneLabel']
if paneLabel == None:
paneLabel = ''
key = r['figureLabel'] + '|' + paneLabel
value = r['_ImagePane_key']
imagePaneLookup[key] = []
imagePaneLookup[key].append(value)
#print imagePaneLookup['Zmiz1_b41_E11.5b_JL|']
# For each line in the input file
for line in inResultsFile.readlines():
error = 0
lineNum = lineNum + 1
# Split the line into tokens
tokens = string.split(line[:-1], TAB)
try:
assayID = tokens[0]
specimenID = tokens[1]
resultID = tokens[2]
strength = tokens[3]
pattern = tokens[4]
emapaID = tokens[5]
structureTS = tokens[6]
resultNote = tokens[7]
imagePanes = tokens[8]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
strengthKey = gxdloadlib.verifyStrength(strength, lineNum, errorFile)
patternKey = gxdloadlib.verifyPattern(pattern, lineNum, errorFile)
structureKey = loadlib.verifyTerm(emapaID, 90, '', lineNum, errorFile)
if strengthKey == 0 or patternKey == 0 or structureKey == 0:
# set error flag to true
error = 1
# if errors, continue to next record
if error:
continue
# if no errors, process
key = '%s:%s' % (assayID, specimenID)
if not assaySpecimen.has_key(key):
errorFile.write('Cannot find Assay:Speciman key "%s"\n' % (key))
errorFile.write(str(tokens) + '\n\n')
continue
specimenKey = assaySpecimen[key]
if prevAssay != assayID:
prevSpecimen = 0
if prevSpecimen != specimenKey:
prevResult = 0
if prevResult != resultID:
resultKey = resultKey + 1
outResultFile.write(
str(resultKey) + TAB + \
str(specimenKey) + TAB + \
str(strengthKey) + TAB + \
str(patternKey) + TAB + \
resultID + TAB + \
mgi_utils.prvalue(resultNote) + TAB + \
loaddate + TAB + loaddate + CRT)
for image in string.split(imagePanes,','):
if image in imagePaneLookup:
imageKey = imagePaneLookup[image][0]
outResultImageFile.write(str(resultKey) + TAB + \
str(imageKey) + TAB + \
loaddate + TAB + loaddate + CRT)
#else:
#print image
outResultStFile.write(
str(resultKey) + TAB + \
str(structureKey) + TAB + \
str(structureTS) + TAB + \
loaddate + TAB + loaddate + CRT)
prevAssay = assayID
prevSpecimen = specimenKey
prevResult = resultID
# end of "for line in inResultsFile.readlines():"
return
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 alleleKey, refAssocKey, accKey, noteKey, mgiKey, annotKey, mutationKey
global alleleLookup
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')
#print line
try:
markerID = tokens[0]
symbol = tokens[1]
name = tokens[2]
alleleStatus = tokens[3]
alleleType = tokens[4]
alleleSubtypes = tokens[5]
collectionKey = tokens[6]
germLine = tokens[7]
references = tokens[8]
strainOfOrigin = tokens[9]
mutantCellLine = tokens[10]
molecularNotes = tokens[11]
driverNotes = tokens[12]
ikmcNotes = tokens[13]
mutations = tokens[14]
inheritanceMode = tokens[15]
isMixed = tokens[16]
isExtinct = tokens[17]
createdBy = tokens[18]
createMCL = tokens[19]
createNote = tokens[20]
setStatus = tokens[21]
existingAlleleID = tokens[22]
ikmcSymbol = tokens[23]
except:
exit(1, 'Invalid Line (%d): %s\n' % (lineNum, line))
# creator
createdByKey = loadlib.verifyUser(createdBy, lineNum, errorFile)
if createdByKey == 0:
continue
# processing for IKMC-only
if len(createMCL) > 0 or len(createNote) > 0 or len(setStatus) > 0:
processFileIKMC(createMCL, createNote, setStatus, \
symbol, ikmcSymbol, mutantCellLine, ikmcNotes, \
createdByKey, existingAlleleID)
continue
# marker key
markerKey = loadlib.verifyMarker(markerID, lineNum, errorFile)
# hard-coded
# _vocab_key = 73 (Marker-Allele Association Status)
# _term_key = 4268545 (Curated)
markerStatusKey = 4268545
# _vocab_key = 37 (Allele Status)
alleleStatusKey = loadlib.verifyTerm('', 37, alleleStatus, lineNum,
errorFile)
# _vocab_key = 38 (Allele Type)
alleleTypeKey = loadlib.verifyTerm('', 38, alleleType, lineNum,
errorFile)
# _vocab_key = 61 (Allele Transmission)
germLineKey = loadlib.verifyTerm('', 61, germLine, lineNum, errorFile)
# _vocab_key = 36 (Allele Molecular Mutation)
allMutations = mutations.split('|')
# _vocab_key = 35 (Allele Status)
inheritanceModeKey = loadlib.verifyTerm('', 35, inheritanceMode,
lineNum, errorFile)
# strains
strainOfOriginKey = sourceloadlib.verifyStrain(strainOfOrigin, lineNum,
errorFile)
# reference
refKey = loadlib.verifyReference(jnum, lineNum, errorFile)
# if errors, continue to next record
# errors are stored (via loadlib) in the .error log
if markerKey == 0 \
or markerStatusKey == 0 \
or alleleStatusKey == 0 \
or alleleTypeKey == 0 \
or germLineKey == 0 \
or allMutations == 0 \
or inheritanceModeKey == 0 \
or strainOfOriginKey == 0 \
or refKey == 0 \
or createdByKey == 0:
continue
# if no errors, process the allele
# not specified/testing
#collectionKey = 11025586
# allele (master)
alleleFile.write('%d|%s|%s|%s|%s|%s|%s|%s|%s|%s|0|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (alleleKey, markerKey, strainOfOriginKey, inheritanceModeKey, alleleTypeKey, \
alleleStatusKey, germLineKey, collectionKey, symbol, name, \
isExtinct, isMixed, refKey, markerStatusKey, \
createdByKey, createdByKey, createdByKey, loaddate, loaddate, loaddate))
# molecular mutation
for mutation in allMutations:
mutationTermKey = loadlib.verifyTerm('', 36, mutation, lineNum,
errorFile)
mutationFile.write('%s|%s|%s|%s|%s\n' \
% (mutationKey, alleleKey, mutationTermKey, loaddate, loaddate))
mutationKey = mutationKey + 1
#
# allele references
#
allReferences = references.split('||')
for reference in allReferences:
refType, refID = reference.split('|')
refKey = loadlib.verifyReference(refID, lineNum, errorFile)
if refType == 'Original':
refAssocTypeKey = 1011
elif refType == 'Transmission':
refAssocTypeKey = 1023
elif refType == 'Molecular':
refAssocTypeKey = 1012
refFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (refAssocKey, refKey, alleleKey, mgiTypeKey, refAssocTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
refAssocKey = refAssocKey + 1
#
# allele subtypes
#
allSubtypes = alleleSubtypes.split('|')
for s in allSubtypes:
# _vocab_key = 93 (Allele Subtype)
alleleSubtypeKey = loadlib.verifyTerm('', 93, s, lineNum,
errorFile)
annotFile.write('%s|%s|%s|%s|%s|%s|%s\n' \
% (annotKey, annotTypeKey, alleleKey, alleleSubtypeKey, \
qualifierKey, loaddate, loaddate))
annotKey = annotKey + 1
#
# mutant cell line
#
if len(mutantCellLine) > 0:
addMutantCellLine(alleleKey, mutantCellLine, createdByKey)
# MGI Accession ID for the allelearker
accFile.write('%s|%s%d|%s|%s|1|%d|%d|0|1|%s|%s|%s|%s\n' \
% (accKey, mgiPrefix, mgiKey, mgiPrefix, mgiKey, alleleKey, mgiTypeKey, \
createdByKey, createdByKey, loaddate, loaddate))
# storing data in MGI_Note
# molecular notes
mgiNoteSeqNum = 1
if len(molecularNotes) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, alleleKey, mgiNoteObjectKey, mgiMolecularNoteTypeKey, \
molecularNotes, createdByKey, createdByKey, loaddate, loaddate))
noteKey = noteKey + 1
# driver notes
# TR12662/MGI_Relationship._Category_key = 1006
# removed noteFile code
# place hodler for MGI_Relationship code
# the IKMC is the only product using this and IKMC does not add any driver note
#mgiNoteSeqNum = 1
#if len(driverNotes) > 0:
# ikmc notes
useIKMCnotekey = 0
if len(ikmcNotes) > 0:
noteFile.write('%s|%s|%s|%s|%s|%s|%s|%s\n' \
% (noteKey, alleleKey, mgiNoteObjectKey, mgiIKMCNoteTypeKey, \
ikmcNotes, createdByKey, createdByKey, loaddate, loaddate))
useIKMCnotekey = noteKey
noteKey = noteKey + 1
# Print out a new text file and attach the new MGI Allele IDs as the last field
if createdBy == 'ikmc_alleleload':
newAlleleFile.write('%s\t%s%s\t%s\n' \
% (mgi_utils.prvalue(ikmcNotes), \
mgi_utils.prvalue(mgiPrefix), mgi_utils.prvalue(mgiKey), \
mgi_utils.prvalue(ikmcSymbol)))
else:
newAlleleFile.write('%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s%s\n' \
% (mgi_utils.prvalue(markerID), \
mgi_utils.prvalue(symbol), \
mgi_utils.prvalue(name), \
mgi_utils.prvalue(alleleStatus), \
mgi_utils.prvalue(alleleType), \
mgi_utils.prvalue(alleleSubtype), \
mgi_utils.prvalue(collection), \
mgi_utils.prvalue(germLine), \
mgi_utils.prvalue(references), \
mgi_utils.prvalue(strainOfOrigin), \
mgi_utils.prvalue(mutantCellLine), \
mgi_utils.prvalue(allMutations), \
mgi_utils.prvalue(inheritanceMode), \
mgi_utils.prvalue(isMixed), \
mgi_utils.prvalue(isExtinct), \
mgi_utils.prvalue(refKey), \
mgi_utils.prvalue(markerStatusKey), \
mgi_utils.prvalue(createdBy), \
mgi_utils.prvalue(mgiPrefix), mgi_utils.prvalue(mgiKey)))
# save symbol/alleleKey/ikmc note key
alleleLookup[symbol] = []
alleleLookup[symbol].append(
(alleleKey, useIKMCnotekey, mgiPrefix + str(mgiKey)))
accKey = accKey + 1
mgiKey = mgiKey + 1
alleleKey = alleleKey + 1
# end of "for line in inputFile.readlines():"
#
# Update the AccessionMax value
#
if not DEBUG:
db.sql('select * from ACC_setMax(%d)' % (lineNum), None)
db.commit()
def sanityCheck(biotypeVocab, biotypeTerm, mcvTerms, primaryMCVTerm, markerType, lineNum):
'''
#
# requires:
#
# effects:
#
# returns:
# List [] of error messages if sanity check fails
# Empty list [] if all sanity checks pass
#
'''
global biotypeVocabKey
global biotypeTermKey
global mcvTermKeys
global markerTypeKey
global primaryMCVTermKey
errors = []
mcvTermKeys = []
#
# BioType Vocabularies
#
biotypeVocabKey = 0
if biotypeVocab == 'Ensembl':
biotypeVocabKey = ENSEMBL_VOCAB_KEY
elif biotypeVocab == 'NCBI':
biotypeVocabKey = NCBI_VOCAB_KEY
elif biotypeVocab == 'MGP':
biotypeVocabKey = MGP_VOCAB_KEY
else:
errors.append( INVALID_VOCAB_ERROR % (lineNum, biotypeVocab) )
# Lookup the biotype _term_key for this vocab/term
if biotypeVocabKey:
biotypeTermKey = loadlib.verifyTerm('', biotypeVocabKey, biotypeTerm, lineNum, errorFile)
if biotypeTermKey == 0:
errors.append( INVALID_BIOTYPE_TERM_ERROR % (lineNum, biotypeTerm, biotypeVocab) )
# lookup the _marker_type_key
markerTypeKey = loadlib.verifyMarkerType(markerType, lineNum, errorFile)
if markerTypeKey == 0:
errors.append( INVALID_MARKER_TYPE_ERROR % (lineNum, markerType) )
#
# mcv/feature types
#
tokens = mcvTerms.split('|')
for r in tokens:
t = loadlib.verifyTerm('', MCV_VOCAB_KEY, r, lineNum, errorFile)
if t == 0:
errors.append( INVALID_MCV_TERM_ERROR % (lineNum, r) )
else:
mcvTermKeys.append(t)
# lookup the primary feature type
primaryMCVTermKey = loadlib.verifyTerm('', MCV_VOCAB_KEY, primaryMCVTerm, lineNum, errorFile)
if primaryMCVTermKey == 0:
errors.append( INVALID_MARKER_TYPE_ERROR % (lineNum, primaryMCVTerm) )
return errors