def maf2Dict(multipleAlignment, id = None):
"""
store multiple-alignment information
in a dictionary
"""
data = dict()
chrom = multipleAlignment[0].id.split(".")[1]
genome_start = multipleAlignment[0].annotations['start']
genome_stop = genome_start + multipleAlignment[0].annotations['size']
data['key'] = chrom + "." + str(genome_start)
data['genome_start'] = genome_start
data['genome_stop'] = genome_stop
data['chromosome'] = chrom
data['speciesAligned'] = list(set(record.id.split(".")[0] \
for record in multipleAlignment))
data['nSpeciesAligned'] = len(data['speciesAligned'])
data['maf'] = encoding.dumps(multipleAlignment.format("maf").replace( \
"# generated by Biopython\n", "")[:-2]) #save some space
return data
def maf2Dict(multipleAlignment, id=None):
"""
store multiple-alignment information
in a dictionary
"""
data = dict()
chrom = multipleAlignment[0].id.split(".")[1]
genome_start = multipleAlignment[0].annotations['start']
genome_stop = genome_start + multipleAlignment[0].annotations['size']
data['key'] = chrom + "." + str(genome_start)
data['genome_start'] = genome_start
data['genome_stop'] = genome_stop
data['chromosome'] = chrom
data['speciesAligned'] = list(set(record.id.split(".")[0] \
for record in multipleAlignment))
data['nSpeciesAligned'] = len(data['speciesAligned'])
data['maf'] = encoding.dumps(multipleAlignment.format("maf").replace( \
"# generated by Biopython\n", "")[:-2]) #save some space
return data
in a dictionary
"""
data = dict()
chrom = multipleAlignment[0].id.split(".")[1]
genome_start = multipleAlignment[0].annotations['start']
genome_stop = genome_start + multipleAlignment[0].annotations['size']
data['key'] = chrom + "." + str(genome_start)
data['genome_start'] = genome_start
data['genome_stop'] = genome_stop
data['chromosome'] = chrom
data['speciesAligned'] = list(set(record.id.split(".")[0] \
for record in multipleAlignment))
data['nSpeciesAligned'] = len(data['speciesAligned'])
data['maf'] = encoding.dumps(multipleAlignment.format("maf").replace( \
"# generated by Biopython\n", "")[:-2]) #save some space
return data
def maf_dict_generator(mafFile):
with open(mafFile, 'r') as mafFileHandle:
for blockN, multipleAlignment in enumerate(Bio.AlignIO.parse(mafFileHandle, "maf")):
yield maf2Dict(multipleAlignment, blockN)
if __name__ == "__main__":
mafFiles = sys.argv[1:]
for mafFile in mafFiles:
for converted in maf_dict_generator(mafFile):
print encoding.dumps(converted)
data = dict()
chrom = multipleAlignment[0].id.split(".")[1]
genome_start = multipleAlignment[0].annotations['start']
genome_stop = genome_start + multipleAlignment[0].annotations['size']
data['key'] = chrom + "." + str(genome_start)
data['genome_start'] = genome_start
data['genome_stop'] = genome_stop
data['chromosome'] = chrom
data['speciesAligned'] = list(set(record.id.split(".")[0] \
for record in multipleAlignment))
data['nSpeciesAligned'] = len(data['speciesAligned'])
data['maf'] = encoding.dumps(multipleAlignment.format("maf").replace( \
"# generated by Biopython\n", "")[:-2]) #save some space
return data
def maf_dict_generator(mafFile):
with open(mafFile, 'r') as mafFileHandle:
for blockN, multipleAlignment in enumerate(
Bio.AlignIO.parse(mafFileHandle, "maf")):
yield maf2Dict(multipleAlignment, blockN)
if __name__ == "__main__":
mafFiles = sys.argv[1:]
for mafFile in mafFiles:
for converted in maf_dict_generator(mafFile):
print encoding.dumps(converted)
