def write(f):
i = 0
for seqrecord in sequences:
if seqrecord.id == "<unknown id>":
seqrecord.id = str(i)
i+=1
writer = FastaWriter(f)
writer.write_file(sequences)
f.flush() #IMPORTANT
def write_fasta(sequence, file_handle, wrap=60):
"""
:param sequence: sequence to write in the file
:type sequence: :class:`Bio.SeqRecord.SeqRecord` object
:param file_handle: output file handler
:type file_handle:
"""
_LOGGER.info("Writing output to " + file_handle.name + "...")
writer = FastaWriter(file_handle, wrap=wrap)
writer.write_file(sequence)
def handle_noargs(self, **options):
outfilename = options['outfile']
outfileh = open(outfilename, 'w')
print "Fetching records."
records = Protein.objects.all()
seqs = self._records_to_seqs(records)
print "Writing records to %s" % outfilename
writer = FastaWriter(outfileh, record2title=lambda x: x.id)
writer.write_file(seqs)
outfileh.close()
print "Done."
def _write(self, file, value):
"""
Write output to fasta file
:param folder: file and location of outputfile
:param value:
:return:
"""
handle = open(file, "w")
writer = FastaWriter(handle, wrap=None)
writer.write_file(value)
handle.close()
def split_files(fasta_file):
"""This next section removes line wraps, so I can
split the file without interrupting a gene"""
from Bio.SeqIO.FastaIO import FastaWriter
output_handle = open("nowrap.fasta", "w")
seqrecords=[ ]
writer = FastaWriter(output_handle, wrap=0)
for record in SeqIO.parse(open(fasta_file), "fasta"):
seqrecords.append(record)
writer.write_file(seqrecords)
output_handle.close()
"""I can always make the number of lines an alterable field"""
subprocess.check_call("split -l 200000 nowrap.fasta", shell=True)
def split_files(fasta_file):
"""This next section removes line wraps, so I can
split the file without interrupting a gene"""
from Bio.SeqIO.FastaIO import FastaWriter
output_handle = open("nowrap.fasta", "w")
seqrecords=[ ]
writer = FastaWriter(output_handle, wrap=0)
for record in SeqIO.parse(open(fasta_file), "fasta"):
seqrecords.append(record)
writer.write_file(seqrecords)
output_handle.close()
"""I can always make the number of lines an alterable field"""
subprocess.check_call("split -l 200000 nowrap.fasta", shell=True)
def write_by_og(self, output_folder):
'''
Write for each og all the mapped sequences into separate fasta files to a specified folder
:param output_folder: folder where files should be stored
'''
if not os.path.exists(output_folder):
os.makedirs(output_folder)
for key, value in tqdm(self.og_records.items(),
desc="Writing DNA seq sorted by OG",
unit=" OG"):
handle = open(os.path.join(output_folder, 'mapped_' + key + '.fa'),
"w")
writer = FastaWriter(handle, wrap=None)
writer.write_file(value)
handle.close()
def write_select_og_dna(self):
'''
Write for each species all the DNA sequences into separate fasta files
:param output_folder: folder where files should be stored
'''
output_folder = os.path.join(self.args.output_path, "reference_ogs_dna")
if not os.path.exists(output_folder):
os.makedirs(output_folder)
for key, value in tqdm(self.ogs.items(), desc="Writing OGs sorted by species",
unit=" species"):
handle = open(os.path.join(output_folder, key + '.fa'), "w")
writer = FastaWriter(handle, wrap=None)
writer.write_file(value.dna)
handle.close()
elif len(self.ogs_dna_by_species) == len(glob.glob(os.path.join(output_folder, '*.fa'))):
print('Folder with files already exists and will not be overwritten.')
"""
Remove unpaired reads from a fasta file.
This script can be used for the case that unpaired reads (e.g. as
reads were removed during quality trimming) in a pair of fasta files
from paired-end sequencing need to be removed.
"""
import argparse
from Bio import SeqIO
from Bio.SeqIO.FastaIO import FastaWriter
parser = argparse.ArgumentParser()
parser.add_argument("fasta_file_to_filter")
parser.add_argument("reference_fasta_file")
parser.add_argument("--output_fasta", default="output.fa")
args = parser.parse_args()
# Read reference file header
reference_headers = {}
for seq_record in SeqIO.parse(args.reference_fasta_file, "fasta"):
reference_headers[seq_record.id.split()[0]] = 1
# Read fasta file to filter and write output
with open(args.output_fasta, 'w') as output_fh:
writer = FastaWriter(output_fh, wrap=0)
writer.write_file(
filter(lambda seq_record: seq_record.id.split()[0] in reference_headers,
SeqIO.parse(args.fasta_file_to_filter, "fasta")))
def write_fasta_output(fasta_output_file, filtered_seqs):
handle = open(fasta_output_file, "w")
writer = FastaWriter(handle)
writer.write_file(filtered_seqs)
handle.close()
def write_dna(self, species, output_folder):
handle = open(os.path.join(output_folder, species + '_OGs.fa'), "w")
writer = FastaWriter(handle, wrap=None)
writer.write_file(self.dna)
handle.close()
z=[x.description for x in fa if i in x.description]
if len(z)>0:
new_name=df2[i]
full_name=z[0]
master_dict.update({full_name : new_name})
for i in fa:
if i.description in master_dict.keys():
i.id=master_dict[i.description]
i.description=""
## Write temporary file
handle = open('temp.fa', "w")
writer = FastaWriter(handle, wrap=0)
writer.write_file(fa)
handle.close()
## Read in temporary file and print properly formatted fasta
x = open("temp.fa", "r")
y=x.readlines()
z=''.join(y)
if z[-1]=='\n':
z=z[:-1]
print (z)
os.remove("temp.fa")
########## BIN
def select_from_small_file(args):
inp_file, db_inp_file, db_out_file, out_file, num = args
inp = list(SeqIO.parse(open(inp_file), 'fasta'))
shuffle(inp)
writer = FastaWriter(open(out_file, 'w'), wrap=0)
writer.write_file(inp[:num])
