def get_fastx_entries(fastx_filename,
fasta=False,
fastq=False):
"""
Get entries of FASTQ/FASTA file.
if fasta=True, read file as fasta regardless of extension.
if fastq=True, read file as fastq regardless of extension
"""
entries = []
fastx_type = get_fastx_type(fastx_filename)
if (fastx_type == "fasta") or fasta:
# It's a FASTA file
entries = fasta_utils.read_fasta(fastx_filename)
elif (fastx_type == "fastq") or fastq:
# It's a FASTQ file
entries = fastq_utils.read_fastq(fastx_filename)
return entries
def download_misc_seqs(genome, output_dir):
"""
Download assorted sequences related to genome.
"""
# Mapping from sequence label (e.g. rRNA)
# to accession numbers
organism = None
if genome.startswith("hg"):
organism = "human"
elif genome.startswith("mm"):
organism = "mouse"
else:
print "Error: Unsupported genome."
sys.exit(1)
# Fetch the accession numbers for the organism's
# misc sequences and download them
misc_seqs = NCBI_MISC_SEQS[organism]
ncbi_outdir = os.path.join(output_dir, "ncbi")
misc_outdir = os.path.join(output_dir, "misc")
utils.make_dir(ncbi_outdir)
utils.make_dir(misc_outdir)
for seq_label, access_id in misc_seqs.iteritems():
if access_id is None:
continue
output_filename = os.path.join(misc_outdir, "%s.fa" %(seq_label))
if os.path.isfile(output_filename):
print "%s exists. Skipping download.." %(seq_label)
continue
print "Downloading: %s (NCBI: %s)" %(seq_label,
access_id)
url_filename = download_ncbi_fasta(access_id, ncbi_outdir)
fasta_in = fasta_utils.read_fasta(url_filename)
fasta_out = open(output_filename, "w")
print " - Writing to: %s" %(output_filename)
# Fetch first FASTA record
rec = fasta_in.next()
curr_label, fasta_seq = rec
# Output it with the required label
new_rec = (">%s" %(seq_label), fasta_seq)
fasta_utils.write_fasta(fasta_out, [new_rec])
def __init__(self, fasta_fname):
self.fasta_fname = fasta_fname
self.seqs = fasta_utils.read_fasta(self.fasta_fname)
def __init__(self, fasta_fname):
self.fasta_fname = fasta_fname
self.seqs = fasta_utils.read_fasta(self.fasta_fname)