def _add_gDNA_summary( summary, gDNA_hits ):
"""
Summarize the gDNA hits for a consensus sequence
"""
if len( gDNA_hits ) == 1:
hit = gDNA_hits[0]
summary['gDNA_Type'] = HlaType.from_string( hit.tname )
summary['gLen'] = hit.qlength
if hasattr( hit, 'pctsimilarity' ):
summary['gDNA_PctId'] = round(float( hit.pctsimilarity ), 2)
summary['gDNA_Mismatch'] = 'N/A'
summary['gDNA_Indel'] = 'N/A'
elif hasattr( hit , 'nmat' ):
similarity = float(hit.nmat) / (int(hit.nmat) + int(hit.nmis) + int(hit.nins) + int(hit.ndel))
summary['gDNA_PctId'] = round(100*similarity, 2)
summary['gDNA_Mismatch'] = str(hit.nmis)
summary['gDNA_Indel'] = str(int(hit.nins) + int(hit.ndel))
else:
msg = 'Invalid alignment type!'
log.error( msg )
raise TypeError( msg )
else:
summary['Notes'].append('Multiple gDNA Matches')
summary['gDNA_Type'] = 'N/A'
summary['gDNA_PctId'] = 'N/A'
return summary
def _add_gDNA_summary(summary, gDNA_hits):
"""
Summarize the gDNA hits for a consensus sequence
"""
if len(gDNA_hits) == 1:
hit = gDNA_hits[0]
summary['gDNA_Type'] = HlaType.from_string(hit.tname)
summary['gLen'] = hit.qlength
if hasattr(hit, 'pctsimilarity'):
summary['gDNA_PctId'] = round(float(hit.pctsimilarity), 2)
summary['gDNA_Mismatch'] = 'N/A'
summary['gDNA_Indel'] = 'N/A'
elif hasattr(hit, 'nmat'):
similarity = float(hit.nmat) / (int(hit.nmat) + int(hit.nmis) +
int(hit.nins) + int(hit.ndel))
summary['gDNA_PctId'] = round(100 * similarity, 2)
summary['gDNA_Mismatch'] = str(hit.nmis)
summary['gDNA_Indel'] = str(int(hit.nins) + int(hit.ndel))
else:
msg = 'Invalid alignment type!'
log.error(msg)
raise TypeError(msg)
else:
summary['Notes'].append('Multiple gDNA Matches')
summary['gDNA_Type'] = 'N/A'
summary['gDNA_PctId'] = 'N/A'
return summary
def _combine_cDNA_hits(cDNA_hits):
"""
Combine a series of cDNA hits at the 3-digit level
"""
types = [HlaType.from_string(hit.tname) for hit in cDNA_hits]
genes = list(set([t.gene for t in types]))
field1s = list(set([t.field1 for t in types]))
field2s = list(set([t.field2 for t in types]))
field3s = list(set([t.field3 for t in types]))
if len(field3s) == 1:
return HlaType(gene=genes[0],
field1=field1s[0],
field2=field2s[0],
field3=field3s[0])
elif len(field2s) == 1:
return HlaType(gene=genes[0], field1=field1s[0], field2=field2s[0])
elif len(field1s) == 1:
return HlaType(gene=genes[0], field1=field1s[0])
return 'N/A'
def select_references( reference_file, refs ):
for i, ref in enumerate(refs):
for record in FastaReader( reference_file ):
if record.name.startswith( ref ):
hla_type = HlaType.from_string(record.name)
if i == 0:
first = ref
first_type = hla_type
elif first_type.field1 != hla_type.field1:
return (first, ref)
def select_references(reference_file, refs):
for i, ref in enumerate(refs):
for record in FastaReader(reference_file):
if record.name.startswith(ref):
hla_type = HlaType.from_string(record.name)
if i == 0:
first = ref
first_type = hla_type
elif first_type.field1 != hla_type.field1:
return (first, ref)
def _combine_cDNA_hits( cDNA_hits ):
"""
Combine a series of cDNA hits at the 3-digit level
"""
types = [HlaType.from_string( hit.tname ) for hit in cDNA_hits]
genes = list( set( [t.gene for t in types] ))
field1s = list( set( [t.field1 for t in types] ))
field2s = list( set( [t.field2 for t in types] ))
field3s = list( set( [t.field3 for t in types] ))
if len(field3s) == 1:
return HlaType( gene=genes[0], field1=field1s[0],
field2=field2s[0],
field3=field3s[0] )
elif len(field2s) == 1:
return HlaType( gene=genes[0], field1=field1s[0],
field2=field2s[0] )
elif len(field1s) == 1:
return HlaType( gene=genes[0], field1=field1s[0] )
return 'N/A'
def _add_cDNA_summary( summary, cDNA_data, query ):
"""
Summarize the cDNA hits for a consensus sequence
"""
if query in cDNA_data:
cDNA_hits = cDNA_data[query]
summary['cLen'] = cDNA_hits[0].qlength
if len( cDNA_hits ) == 1:
summary['cDNA_Type'] = HlaType.from_string( cDNA_hits[0].tname ).cDNA_type
summary['cDNA_PctId'] = round(float(cDNA_hits[0].pctsimilarity), 2)
elif len( cDNA_hits ) >= 2:
summary['cDNA_Type'] = _combine_cDNA_hits( cDNA_hits )
summary['cDNA_PctId'] = round(float(cDNA_hits[0].pctsimilarity), 2)
else:
summary['cDNA_Type'] = 'N/A'
summary['cDNA_PctId'] = 'N/A'
else:
summary['cLen'] = 'N/A'
summary['cDNA_Type'] = 'N/A'
summary['cDNA_PctId'] = 'N/A'
return summary
def _add_cDNA_summary(summary, cDNA_data, query):
"""
Summarize the cDNA hits for a consensus sequence
"""
if query in cDNA_data:
cDNA_hits = cDNA_data[query]
summary['cLen'] = cDNA_hits[0].qlength
if len(cDNA_hits) == 1:
summary['cDNA_Type'] = HlaType.from_string(
cDNA_hits[0].tname).cDNA_type
summary['cDNA_PctId'] = round(float(cDNA_hits[0].pctsimilarity), 2)
elif len(cDNA_hits) >= 2:
summary['cDNA_Type'] = _combine_cDNA_hits(cDNA_hits)
summary['cDNA_PctId'] = round(float(cDNA_hits[0].pctsimilarity), 2)
else:
summary['cDNA_Type'] = 'N/A'
summary['cDNA_PctId'] = 'N/A'
else:
summary['cLen'] = 'N/A'
summary['cDNA_Type'] = 'N/A'
summary['cDNA_PctId'] = 'N/A'
return summary
