def setRow_header(self):
self.generalInformationRows.append([0, 0,
cu.safeLength(self.seql_raw.seqlHeader),
cu.safeLength(self.seql.generalInformation.seqlHeader),
cu.TAG_LENGTH_ST26['ST26SequenceListing'],
cu.TAG_LENGTH_ST26['ST26SequenceListing'],
'ST26SequenceListing',
'ST.25 seqlHeader discarded'])
def setRow_header(self):
self.generalInformationRows.append([
0, 0,
cu.safeLength(self.seql_raw.seqlHeader),
cu.safeLength(self.seql.generalInformation.seqlHeader),
cu.TAG_LENGTH_ST26['ST26SequenceListing'],
cu.TAG_LENGTH_ST26['ST26SequenceListing'], 'ST26SequenceListing',
'ST.25 seqlHeader discarded'
])
def createQualifierValue(tag_st25, element_st25, value_st25, msg):
currentRow_INSDQualifier_value = [tag_st25,
currentSeqId, cu.safeLength(element_st25),
cu.safeLength(value_st25),
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
cu.safeLength(value_st25) + cu.TAG_LENGTH_ST26['INSDQualifier_value'],
'INSDQualifier_value',
msg]
res.append(currentRow_INSDQualifier_value)
def _getSt25St26Lengths(self, element_st25_tag, seqIdNo, element_st25,
value_st25, element_st26, comment):
return [
element_st25_tag, seqIdNo,
cu.safeLength(element_st25),
cu.safeLength(value_st25),
0 if element_st26 == '-' else cu.TAG_LENGTH_ST26[element_st26],
0 if element_st26 == '-' else cu.TAG_LENGTH_ST26[element_st26] +
cu.safeLength(value_st25), element_st26, comment
]
def createQualifierValue(tag_st25, element_st25, value_st25, msg):
currentRow_INSDQualifier_value = [
tag_st25, currentSeqId,
cu.safeLength(element_st25),
cu.safeLength(value_st25),
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
cu.safeLength(value_st25) +
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
'INSDQualifier_value', msg
]
res.append(currentRow_INSDQualifier_value)
def _getSt25St26Lengths(self,
element_st25_tag,
seqIdNo,
element_st25,
value_st25,
element_st26, comment):
return [element_st25_tag,
seqIdNo,
cu.safeLength(element_st25),
cu.safeLength(value_st25),
0 if element_st26 == '-' else cu.TAG_LENGTH_ST26[element_st26],
0 if element_st26 == '-' else cu.TAG_LENGTH_ST26[element_st26] +
cu.safeLength(value_st25),
element_st26,
comment
]
def setRow_prio(self):
res = ['prio', 0, cu.safeLength(self.seql_raw.priorities)]
priority_clean = self.seql.generalInformation.priority
pr_length = 0
if priority_clean:
pr = priority_clean[0]
pr_applNr = pr[0]
pr_filingDate = pr[1]
pr_length = cu.safeLength(pr_applNr) + cu.safeLength(pr_filingDate)
res.append(pr_length)
res.append(cu.TAG_LENGTH_ST26['EarliestPriorityApplicationIdentification'] +
cu.TAG_LENGTH_ST26['IPOfficeCode'] +
cu.TAG_LENGTH_ST26['ApplicationNumberText'] +
cu.TAG_LENGTH_ST26['FilingDate'])
res.append(pr_length + res[4])
res.append('EarliestPriorityApplicationIdentification')
res.append('only first ST.25 priority retained, if any')
self.generalInformationRows.append(res)
def setRow_prio(self):
res = ['prio', 0, cu.safeLength(self.seql_raw.priorities)]
priority_clean = self.seql.generalInformation.priority
pr_length = 0
if priority_clean:
pr = priority_clean[0]
pr_applNr = pr[0]
pr_filingDate = pr[1]
pr_length = cu.safeLength(pr_applNr) + cu.safeLength(pr_filingDate)
res.append(pr_length)
res.append(
cu.TAG_LENGTH_ST26['EarliestPriorityApplicationIdentification'] +
cu.TAG_LENGTH_ST26['IPOfficeCode'] +
cu.TAG_LENGTH_ST26['ApplicationNumberText'] +
cu.TAG_LENGTH_ST26['FilingDate'])
res.append(pr_length + res[4])
res.append('EarliestPriorityApplicationIdentification')
res.append('only first ST.25 priority retained, if any')
self.generalInformationRows.append(res)
def test_safeLength(self):
self.assertEqual(0, cu.safeLength(None))
self.assertEqual(3, cu.safeLength('abc'))
self.assertEqual(20, cu.safeLength('<400> 40\r\n\r\nMet Ser'))
def setSequenceRows(self):
res = []
parsedSequences = []
for s in self.seql.generateSequence():
parsedSequences.append(s)
# TODO: test
if s.molType == 'PRT':
self.seql.quantity_prt += 1
else:
self.seql.quantity_nuc += 1
if s.mixedMode:
self.seql.quantity_mix += 1
for seq in self.seql_raw.raw_sequences:
currentIndex = self.seql_raw.raw_sequences.index(seq)
parsedSequence = parsedSequences[currentIndex]
currentSeqId = parsedSequence.seqIdNo
# ====================== 210 ======================
currentRow_SequenceData = self._getSt25St26Lengths(0, currentSeqId,
'-', '-', 'SequenceData',
'ST.26 specific element')
res.append(currentRow_SequenceData)
currentRow210 = self._getSt25St26Lengths(210, currentSeqId,
seq.seqIdNo, parsedSequence.seqIdNo, 'sequenceIDNumber', '-')
res.append(currentRow210)
currentRow_INSDSeq = self._getSt25St26Lengths(0, currentSeqId,
'-', '-', 'INSDSeq', 'ST.26 specific element')
res.append(currentRow_INSDSeq)
# ====================== 211 ======================
currentRow211 = self._getSt25St26Lengths(211, currentSeqId,
seq.length, parsedSequence.length, 'INSDSeq_length', cu.BLANK_PLACEHOLDER)
res.append(currentRow211)
# ====================== 212 ======================
moltypeValue = 'AA' if parsedSequence.molType == 'PRT' else parsedSequence.molType
currentRow212 = [212, currentSeqId, cu.safeLength(seq.molType),
cu.safeLength(parsedSequence.molType),
cu.TAG_LENGTH_ST26['INSDSeq_moltype'],
cu.safeLength(moltypeValue) + cu.TAG_LENGTH_ST26['INSDSeq_moltype'],
'INSDSeq_moltype',
'PRT replaced by AA for protein raw_sequences' if moltypeValue == 'AA' else cu.BLANK_PLACEHOLDER]
res.append(currentRow212)
# ====================== INSDSeq_division ======================
INSDSeq_division_val = 'PAT'
currentRow_INSDSeq_division = self._getSt25St26Lengths(0, currentSeqId,
'-', INSDSeq_division_val, 'INSDSeq_division',
'ST.26 specific element')
res.append(currentRow_INSDSeq_division)
# ====================== INSDSeq_other-seqids ======================
# optional element, therefore not included in calculations
# ====================== INSDSeq_feature-table ======================
currentRow_INSDSeq_feature_table = self._getSt25St26Lengths(0,
currentSeqId,
'-', '-', 'INSDSeq_feature-table',
'ST.26 specific element')
res.append(currentRow_INSDSeq_feature_table)
# ====================== 213 ======================
# create ST.26 feature source
currentRow_INSDFeature = [0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDFeature'],
cu.TAG_LENGTH_ST26['INSDFeature'],
'INSDFeature',
'ST.26 mandatory feature source']
res.append(currentRow_INSDFeature)
currentRow_INSDFeature_key = [0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDFeature_key'],
len('source') + cu.TAG_LENGTH_ST26['INSDFeature_key'],
'INSDFeature_key',
'ST.26 mandatory feature source']
res.append(currentRow_INSDFeature_key)
sourceLocation = '1..%s' % parsedSequence.length
currentRow_INSDFeature_location = [0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDFeature_location'],
len(sourceLocation) + cu.TAG_LENGTH_ST26['INSDFeature_location'],
'INSDFeature_location',
'ST.26 mandatory feature source']
res.append(currentRow_INSDFeature_location)
def append_INSDFeature_quals(msg):
res.append([0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDFeature_quals'],
cu.TAG_LENGTH_ST26['INSDFeature_quals'],
'INSDFeature_quals',
msg])
# add first the parent element INSDFeature_quals
append_INSDFeature_quals('ST.26 mandatory feature source')
def createQualifier(name, msg):
currentRow_INSDQualifier = [0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDQualifier'],
cu.TAG_LENGTH_ST26['INSDQualifier'],
'INSDQualifier',
msg]
res.append(currentRow_INSDQualifier)
currentRow_INSDQualifier_name = [0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDQualifier_name'],
len(name) + cu.TAG_LENGTH_ST26['INSDQualifier_name'],
'INSDQualifier_name',
msg]
res.append(currentRow_INSDQualifier_name)
def createQualifierValue(tag_st25, element_st25, value_st25, msg):
currentRow_INSDQualifier_value = [tag_st25,
currentSeqId, cu.safeLength(element_st25),
cu.safeLength(value_st25),
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
cu.safeLength(value_st25) + cu.TAG_LENGTH_ST26['INSDQualifier_value'],
'INSDQualifier_value',
msg]
res.append(currentRow_INSDQualifier_value)
# qualifier organism
createQualifier('organism', 'ST.26 mandatory qualifier organism')
createQualifierValue(213, seq.organism,
parsedSequence.organism,
'ST.26 mandatory qualifier organism')
# qualifier mol_type
mol_typeValue = 'protein' if parsedSequence.molType == 'PRT' else 'genomic DNA'
createQualifier('mol_type', 'ST.26 mandatory qualifier mol_type')
# createQualifierValue(0, 0, mol_typeValue, 'ST.26 mandatory qualifier mol_type')
res.append([0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
cu.safeLength(mol_typeValue) + cu.TAG_LENGTH_ST26['INSDQualifier_value'],
'INSDQualifier_value',
'ST.26 mandatory qualifier mol_type'])
# end create ST.26 feature source
# ====================== other features ======================
parsedFeatures = parsedSequence.features
for feat in seq.features:
currentFeatureIndex = seq.features.index(feat)
parsedFeature = parsedFeatures[currentFeatureIndex]
isSimpleFeature = False
if parsedFeature.key == cu.BLANK_PLACEHOLDER and parsedFeature.location == cu.BLANK_PLACEHOLDER:
isSimpleFeature = True
if not isSimpleFeature:
# ====================== 220 ======================
currentRow220 = self._getSt25St26Lengths(220, currentSeqId,
feat.featureHeader, parsedFeature.featureHeader,
'INSDFeature', cu.BLANK_PLACEHOLDER)
res.append(currentRow220)
# ====================== 221 ======================
currentRow221 = self._getSt25St26Lengths(221, currentSeqId,
feat.key, parsedFeature.key,
'INSDFeature_key', cu.BLANK_PLACEHOLDER)
res.append(currentRow221)
# ====================== add row for mixed mode translation qualifier ======================
if parsedFeature.key == 'CDS':
createQualifier('translation', 'ST.26 specific element translation')
translationRow = [400, currentSeqId,
0,
cu.safeLength(parsedFeature.translation),
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
(cu.TAG_LENGTH_ST26['INSDQualifier_value'] +
len(cu.oneLetterCode(parsedFeature.translation))),
'INSDQualifier_value', '3-to-1 letter code']
res.append(translationRow)
# ====================== 222 ======================
currentRow222 = self._getSt25St26Lengths(222, currentSeqId,
feat.location, parsedFeature.location,
'INSDFeature_location', cu.BLANK_PLACEHOLDER)
res.append(currentRow222)
# ====================== 223 ======================
if parsedFeature.description != cu.BLANK_PLACEHOLDER: #do not add row if 223 missing!
append_INSDFeature_quals('ST.26 mandatory element')
createQualifier('note', cu.BLANK_PLACEHOLDER)
createQualifierValue(223, feat.description,
parsedFeature.description,
cu.BLANK_PLACEHOLDER)
# ====================== 400 ======================
if parsedSequence.molType == 'PRT':
parsedResidues = parsedSequence.residues_prt
currentRow400 = [400, currentSeqId,
cu.safeLength(seq.residues),
cu.safeLength(parsedResidues),
cu.TAG_LENGTH_ST26['INSDSeq_sequence'],
(cu.TAG_LENGTH_ST26['INSDSeq_sequence'] +
len(cu.oneLetterCode(parsedResidues))),
'INSDSeq_sequence', '3-to-1 letter code']
else:
parsedResidues = parsedSequence.residues_nuc
currentRow400 = self._getSt25St26Lengths(400, currentSeqId,
seq.residues, parsedResidues,
'INSDSeq_sequence', cu.BLANK_PLACEHOLDER)
res.append(currentRow400)
return res
def setSequenceRows(self):
res = []
parsedSequences = []
for s in self.seql.generateSequence():
parsedSequences.append(s)
# TODO: test
if s.molType == 'PRT':
self.seql.quantity_prt += 1
else:
self.seql.quantity_nuc += 1
if s.mixedMode:
self.seql.quantity_mix += 1
for seq in self.seql_raw.raw_sequences:
currentIndex = self.seql_raw.raw_sequences.index(seq)
parsedSequence = parsedSequences[currentIndex]
currentSeqId = parsedSequence.seqIdNo
# ====================== 210 ======================
currentRow_SequenceData = self._getSt25St26Lengths(
0, currentSeqId, '-', '-', 'SequenceData',
'ST.26 specific element')
res.append(currentRow_SequenceData)
currentRow210 = self._getSt25St26Lengths(210, currentSeqId,
seq.seqIdNo,
parsedSequence.seqIdNo,
'sequenceIDNumber', '-')
res.append(currentRow210)
currentRow_INSDSeq = self._getSt25St26Lengths(
0, currentSeqId, '-', '-', 'INSDSeq', 'ST.26 specific element')
res.append(currentRow_INSDSeq)
# ====================== 211 ======================
currentRow211 = self._getSt25St26Lengths(211, currentSeqId,
seq.length,
parsedSequence.length,
'INSDSeq_length',
cu.BLANK_PLACEHOLDER)
res.append(currentRow211)
# ====================== 212 ======================
moltypeValue = 'AA' if parsedSequence.molType == 'PRT' else parsedSequence.molType
currentRow212 = [
212, currentSeqId,
cu.safeLength(seq.molType),
cu.safeLength(parsedSequence.molType),
cu.TAG_LENGTH_ST26['INSDSeq_moltype'],
cu.safeLength(moltypeValue) +
cu.TAG_LENGTH_ST26['INSDSeq_moltype'], 'INSDSeq_moltype',
'PRT replaced by AA for protein raw_sequences'
if moltypeValue == 'AA' else cu.BLANK_PLACEHOLDER
]
res.append(currentRow212)
# ====================== INSDSeq_division ======================
INSDSeq_division_val = 'PAT'
currentRow_INSDSeq_division = self._getSt25St26Lengths(
0, currentSeqId, '-', INSDSeq_division_val, 'INSDSeq_division',
'ST.26 specific element')
res.append(currentRow_INSDSeq_division)
# ====================== INSDSeq_other-seqids ======================
# optional element, therefore not included in calculations
# ====================== INSDSeq_feature-table ======================
currentRow_INSDSeq_feature_table = self._getSt25St26Lengths(
0, currentSeqId, '-', '-', 'INSDSeq_feature-table',
'ST.26 specific element')
res.append(currentRow_INSDSeq_feature_table)
# ====================== 213 ======================
# create ST.26 feature source
currentRow_INSDFeature = [
0, currentSeqId, 0, 0, cu.TAG_LENGTH_ST26['INSDFeature'],
cu.TAG_LENGTH_ST26['INSDFeature'], 'INSDFeature',
'ST.26 mandatory feature source'
]
res.append(currentRow_INSDFeature)
currentRow_INSDFeature_key = [
0, currentSeqId, 0, 0, cu.TAG_LENGTH_ST26['INSDFeature_key'],
len('source') + cu.TAG_LENGTH_ST26['INSDFeature_key'],
'INSDFeature_key', 'ST.26 mandatory feature source'
]
res.append(currentRow_INSDFeature_key)
sourceLocation = '1..%s' % parsedSequence.length
currentRow_INSDFeature_location = [
0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDFeature_location'],
len(sourceLocation) +
cu.TAG_LENGTH_ST26['INSDFeature_location'],
'INSDFeature_location', 'ST.26 mandatory feature source'
]
res.append(currentRow_INSDFeature_location)
def append_INSDFeature_quals(msg):
res.append([
0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDFeature_quals'],
cu.TAG_LENGTH_ST26['INSDFeature_quals'],
'INSDFeature_quals', msg
])
# add first the parent element INSDFeature_quals
append_INSDFeature_quals('ST.26 mandatory feature source')
def createQualifier(name, msg):
currentRow_INSDQualifier = [
0, currentSeqId, 0, 0, cu.TAG_LENGTH_ST26['INSDQualifier'],
cu.TAG_LENGTH_ST26['INSDQualifier'], 'INSDQualifier', msg
]
res.append(currentRow_INSDQualifier)
currentRow_INSDQualifier_name = [
0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDQualifier_name'],
len(name) + cu.TAG_LENGTH_ST26['INSDQualifier_name'],
'INSDQualifier_name', msg
]
res.append(currentRow_INSDQualifier_name)
def createQualifierValue(tag_st25, element_st25, value_st25, msg):
currentRow_INSDQualifier_value = [
tag_st25, currentSeqId,
cu.safeLength(element_st25),
cu.safeLength(value_st25),
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
cu.safeLength(value_st25) +
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
'INSDQualifier_value', msg
]
res.append(currentRow_INSDQualifier_value)
# qualifier organism
createQualifier('organism', 'ST.26 mandatory qualifier organism')
createQualifierValue(213, seq.organism, parsedSequence.organism,
'ST.26 mandatory qualifier organism')
# qualifier mol_type
mol_typeValue = 'protein' if parsedSequence.molType == 'PRT' else 'genomic DNA'
createQualifier('mol_type', 'ST.26 mandatory qualifier mol_type')
# createQualifierValue(0, 0, mol_typeValue, 'ST.26 mandatory qualifier mol_type')
res.append([
0, currentSeqId, 0, 0,
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
cu.safeLength(mol_typeValue) +
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
'INSDQualifier_value', 'ST.26 mandatory qualifier mol_type'
])
# end create ST.26 feature source
# ====================== other features ======================
parsedFeatures = parsedSequence.features
for feat in seq.features:
currentFeatureIndex = seq.features.index(feat)
parsedFeature = parsedFeatures[currentFeatureIndex]
isSimpleFeature = False
if parsedFeature.key == cu.BLANK_PLACEHOLDER and parsedFeature.location == cu.BLANK_PLACEHOLDER:
isSimpleFeature = True
if not isSimpleFeature:
# ====================== 220 ======================
currentRow220 = self._getSt25St26Lengths(
220, currentSeqId, feat.featureHeader,
parsedFeature.featureHeader, 'INSDFeature',
cu.BLANK_PLACEHOLDER)
res.append(currentRow220)
# ====================== 221 ======================
currentRow221 = self._getSt25St26Lengths(
221, currentSeqId, feat.key, parsedFeature.key,
'INSDFeature_key', cu.BLANK_PLACEHOLDER)
res.append(currentRow221)
# ====================== add row for mixed mode translation qualifier ======================
if parsedFeature.key == 'CDS':
createQualifier('translation',
'ST.26 specific element translation')
translationRow = [
400, currentSeqId, 0,
cu.safeLength(parsedFeature.translation),
cu.TAG_LENGTH_ST26['INSDQualifier_value'],
(cu.TAG_LENGTH_ST26['INSDQualifier_value'] +
len(cu.oneLetterCode(parsedFeature.translation))),
'INSDQualifier_value', '3-to-1 letter code'
]
res.append(translationRow)
# ====================== 222 ======================
currentRow222 = self._getSt25St26Lengths(
222, currentSeqId, feat.location,
parsedFeature.location, 'INSDFeature_location',
cu.BLANK_PLACEHOLDER)
res.append(currentRow222)
# ====================== 223 ======================
if parsedFeature.description != cu.BLANK_PLACEHOLDER: #do not add row if 223 missing!
append_INSDFeature_quals('ST.26 mandatory element')
createQualifier('note', cu.BLANK_PLACEHOLDER)
createQualifierValue(223, feat.description,
parsedFeature.description,
cu.BLANK_PLACEHOLDER)
# ====================== 400 ======================
if parsedSequence.molType == 'PRT':
parsedResidues = parsedSequence.residues_prt
currentRow400 = [
400, currentSeqId,
cu.safeLength(seq.residues),
cu.safeLength(parsedResidues),
cu.TAG_LENGTH_ST26['INSDSeq_sequence'],
(cu.TAG_LENGTH_ST26['INSDSeq_sequence'] +
len(cu.oneLetterCode(parsedResidues))),
'INSDSeq_sequence', '3-to-1 letter code'
]
else:
parsedResidues = parsedSequence.residues_nuc
currentRow400 = self._getSt25St26Lengths(
400, currentSeqId, seq.residues, parsedResidues,
'INSDSeq_sequence', cu.BLANK_PLACEHOLDER)
res.append(currentRow400)
return res