def split_target_sequence(target_chroms, target_fasta_name, inter_files):
Faidx(target_fasta_name)
genome_size =0
target_fasta = Fasta(target_fasta_name, key_function = lambda x: x.split()[0])
for value in target_fasta.values():
genome_size += len(value)
for chrm in target_chroms:
if chrm != target_fasta_name:
out=open( inter_files + "/" + chrm+".fa", 'w')
out.write(">" + chrm + "\n" + str(target_fasta[chrm]))
return genome_size
class FastaFile(SequentialData):
def __init__(self, filename):
self.filename = filename
self.instance()
def instance(self):
self.fasta = Fasta(self.filename, as_raw=True)
def get(self, seqname, coord_start, coord_end):
return self.fasta[seqname][coord_start:coord_end]
@property
def seqnames(self):
return list(self.fasta.keys())
@property
def starts(self):
return [0] * len(self.fasta.keys())
@property
def ends(self):
return [len(seq) for seq in self.fasta.values()]
