def __init__(self, filename, verbose=False):
if filename.endswith(".gz"):
raise ValueError("Must be decompressed.")
self._fasta = FastxFile(filename)
self.filename = filename
logger.info("Reading input fasta file...please wait")
self._N = len([x for x in FastxFile(filename)])
def __init__(self,
input_files: Union[str, list],
outq: multiprocessing.Queue,
read_buffer: int = 100000,
read_counter: multiprocessing.Manager().Value = None,
n_subprocesses: int = 1,
statq: multiprocessing.Queue = None) -> None:
# Input variables
self.input_files = input_files
self._multifile = self._is_multifile(input_files)
if self._multifile:
self._input_files_pysam = [FastxFile(f) for f in self.input_files]
else:
self._input_files_pysam = [FastxFile(self.input_files), ]
# Multiprocessing variables
self.outq = outq
self.statq = statq
self.n_subprocesses = n_subprocesses
# Reader variables
self.read_buffer = read_buffer
self.read_counter = read_counter
super(FastqReaderProcess, self).__init__()
def readfx(fastx):
if not file_exists(fastx):
logger.critical("File Not Found: %s" % fastx)
raise IOError(2, "No such file:", fastx)
fx = ""
try:
fx = FastxFile(fastx)
for f in fx:
yield f.name, f.sequence, f.quality
finally:
if fx:
fx.close()
def next(self): # python 2
# reads 4 lines
try:
d = next(self._fasta)
return d
except KeyboardInterrupt: #pragma: no cover
# This should allow developers to break a loop that takes too long
# through the reads to run forever
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
except:
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
raise StopIteration
def next(self): # python 2
# reads 4 lines
try:
d = next(self._fasta)
return d
except KeyboardInterrupt:
# This should allow developers to break a loop that takes too long
# through the reads to run forever
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
except:
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
raise StopIteration
return d
def split_fastx(fname, output, chunksize=10000):
"""Split records in a fasta/q into fixed lengths.
:param fname: input filename.
:param output: output filename.
:param chunksize: (maximum) length of output records.
"""
with open(output, 'w') as fout:
with FastxFile(fname, persist=False) as fin:
for rec in fin:
name = rec.name
seq = rec.sequence
qual = rec.quality
if rec.comment is None:
comment = 'chunk_length={}'.format(chunksize)
else:
comment = '{} chunk_length={}'.format(rec.comment, chunksize)
if qual is None:
for i, s in enumerate(chunks(seq, chunksize)):
chunk_name = '{}_chunk{}'.format(name, i)
fout.write(">{} {}\n{}\n".format(
chunk_name, comment, ''.join(s)))
else:
for i, (s, q) in enumerate(zip(chunks(seq, chunksize), chunks(qual, chunksize))):
chunk_name = '{}_chunk{}'.format(name, i)
fout.write('@{} {}\n{}\n+{}\n'.format(
chunk_name, comment, ''.join(s), ''.join(q)))
def _base_content(filename, window_size, letters, circular=False):
# DOC: see gc_content
fasta = FastxFile(filename)
checker = set(letters)
chrom_gc_content = dict()
for chrom in fasta:
mid = int(window_size / 2)
# Create gc_content array
gc_content = np.empty(len(chrom.sequence))
gc_content[:] = np.nan
if circular:
chrom.sequence = (chrom.sequence[-mid:] + chrom.sequence +
chrom.sequence[:mid])
# Does not shift index of array
mid = 0
# Count first window content
counter = Counter(chrom.sequence[0:window_size])
gc_count = 0
for letter in letters:
gc_count += counter[letter]
gc_content[mid] = gc_count
for i in range(1, len(chrom.sequence) - window_size + 1):
if chrom.sequence[i - 1] in checker:
gc_count -= 1
if chrom.sequence[i + window_size - 1] in checker:
gc_count += 1
gc_content[i + mid] = gc_count
chrom_gc_content[chrom.name] = gc_content / window_size
return chrom_gc_content
def parseFasta(filepath: str, ref_dict: dict, target1: str,
target2: str) -> dict:
fasta = FastxFile(filepath)
for ref in fasta:
if target1 == ref.name or target2 == ref.name:
ref_dict[ref.name] = ref.sequence
return ref_dict
def run_fastq_qc(fastq_path, output):
qualities = list()
mean_qualities = list()
lengths = list()
with FastxFile(fastq_path) as fq:
for rec in fq:
# ONT calculation for "mean Q score"
quals = np.fromiter((ord(x) - 33 for x in rec.quality),
dtype=int,
count=len(rec.quality))
mean_p = np.mean(np.power(10, quals / -10))
mean_qualities.append(-10 * np.log10(mean_p))
# all qualities
qualities.extend(quals)
lengths.append(len(quals))
with open(os.path.join(output, "base_qual.txt")) as f:
f.write("\n".join((str(q) for q in qualities)))
with open(os.path.join(output, "read_qual.txt")) as f:
f.write("\n".join((str(q) for q in mean_qualities)))
with open(os.path.join(output, "lengths.txt")) as f:
f.write("\n".join((str(l) for l in lengths)))
def _method_pysam(self, quality_file=None, *args, **kwargs):
from pysam import FastxFile
if quality_file is None:
_log.warning("No quality file provided. Please use --quality-file")
with open(self.outfile, 'w') as fastq_out:
for seq in FastxFile(self.infile):
fastq_out.write("@{0} {1}\n{2}\n+\n{3}\n".format(
seq.name, seq.comment, seq.sequence,
len(seq.sequence) * "I"))
else: # length must be equal and identifiers sorted similarly
with open(self.outfile, "w") as fastq_out:
for seq, qual in zip(FastxFile(self.infile),
FastxFile(quality_file)):
assert seq.name == qual.name
fastq_out.write("@{0} {1}\n{2}\n+\n{3}\n".format(
seq.name, seq.comment, seq.sequence, qual.sequence))
def select_random_reads(self, N=None, output_filename="random.fasta"):
"""Select random reads and save in a file
:param int N: number of random unique reads to select
should provide a number but a list can be used as well.
:param str output_filename:
"""
import numpy as np
thisN = len(self)
if isinstance(N, int):
if N > thisN:
N = thisN
# create random set of reads to pick up
cherries = list(range(thisN))
np.random.shuffle(cherries)
# cast to set for efficient iteration
cherries = set(cherries[0:N])
elif isinstance(N, set):
cherries = N
elif isinstance(N, list):
cherries = set(N)
fasta = FastxFile(self.filename)
pb = Progress(thisN) # since we scan the entire file
with open(output_filename, "w") as fh:
for i, read in enumerate(fasta):
if i in cherries:
fh.write(read.__str__() + "\n")
else:
pass
pb.animate(i + 1)
return cherries
def _method_pysam(self, *args, **kwargs):
from pysam import FastxFile
if self.infile[1] is None:
_log.error(
"No quality file provided. Please add a quality file path ")
sys.exit(1)
else: # length must be equal and identifiers sorted similarly
with open(self.outfile, "w") as fastq_out:
for seq, qual in zip(FastxFile(self.infile[0]),
FastxFile(self.infile[1])):
assert seq.name == qual.name
if seq.comment:
fastq_out.write("@{0} {1}\n{2}\n+\n{3}\n".format(
seq.name, seq.comment, seq.sequence,
qual.sequence))
else:
fastq_out.write("@{0}\n{1}\n+\n{2}\n".format(
seq.name, seq.sequence, qual.sequence))
def get_run_index(self, fout: bool = False, sort_by: str = 'start_time'):
self.fastx_index = pandas.DataFrame(
[extract_read_data(read) for read in FastxFile(self.fastx)])
if sort_by:
self.fastx_index = self.fastx_index.sort_values(sort_by)
if fout:
self.fastx_index.to_csv(fout, sep='\t', index=False)
return self.fastx_index
def fx_filter(fpath, ids, output, column, sep):
""" Filter reads by external file of read header names """
ids_df = pandas.read_csv(ids, sep=sep, header=None)
read_ids = set(
[str(read_id) for read_id in ids_df.iloc[:, column].tolist()])
with FastxFile(fpath) as fin, \
get_output_handle(output) as fout:
for read in fin:
if read.name in read_ids:
fout.write(str(read) + "\n")
def readfx(fastx):
"""FASTX file reader.
Args:
fastx (str): file path to fasta or fastq file; supports gzip compressed files
Yields:
tuple: The tuple consists of the read name, the sequence, and quality scores if the file
is a fastq.
Raises:
IOError: If `fastx` file does not exist.
"""
if not os.path.exists(fastx):
raise IOError(2, "No such file:", fastx)
fx = ""
try:
fx = FastxFile(fastx)
for f in fx:
yield f.name, f.sequence, f.quality
finally:
if fx:
fx.close()
def explain_report(filtered_analysis, sequencefile, min_repeats, jobs=1):
"""Calculate fraction of reads explainable by each motif"""
explained_analysis = filtered_analysis.copy()
explained_analysis["bases_explained"], total_bases = 0.0, 0
with FastxFile(sequencefile) as fastx:
def get_number_of_masked_positions(sequence, motifs):
n_masked_positions_per_motif = {}
for motif in motifs:
positions_to_mask = set()
motifs_pattern = get_circular_pattern(
motif,
repeats=min_repeats,
)
matcher = motifs_pattern.finditer(sequence, overlapped=True)
for match in matcher:
positions_to_mask |= set(range(match.start(), match.end()))
n_masked_positions_per_motif[motif] = len(positions_to_mask)
return n_masked_positions_per_motif, len(sequence)
with ThreadPoolExecutor(max_workers=jobs) as pool:
workers = [
pool.submit(
get_number_of_masked_positions,
entry.sequence,
set(filtered_analysis["motif"]),
) for entry in fastx
]
iterator = progressbar(
as_completed(workers),
total=len(workers),
desc="Calculating fractions",
unit="read",
)
for worker in iterator:
n_masked_positions_per_motif, total_seq_bases = worker.result()
for motif, n_pos in n_masked_positions_per_motif.items():
indexer = (
explained_analysis["motif"] == motif,
"bases_explained",
)
explained_analysis.loc[indexer] += n_pos
total_bases += total_seq_bases
return explained_analysis, total_bases
def main(references: List[str], accession2taxid: str, output: str):
"""Write out a tsv file mapping reference names to taxids."""
output_tsv = open(output, 'w')
accession2taxid_df = pd.read_csv(accession2taxid,
sep='\t',
header=0,
index_col=1)
for ref in references:
with FastxFile(ref) as fh:
for entry in fh:
try:
taxid = accession2taxid_df.at[entry.name, 'taxid']
except KeyError:
print("Error: couldn't find taxid for {}".format(
entry.name))
sys.exit(1)
output_tsv.write('{name}\t{taxid}\n'.format(name=entry.name,
taxid=taxid))
def get_output_handle(fpath: str, fastx: bool = False, out: bool = True):
if fpath == "-":
if out:
handle = sys.stdout
else:
handle = sys.stdin
else:
p = Path(fpath)
if not p.parent.is_dir():
raise NotADirectoryError(
"Directory specified for output file does not exist: {}".
format(p.parent))
if fastx:
handle = FastxFile(p)
else:
handle = p.open("w")
return handle
def _open_dataset(self):
return FastxFile(self._urlpath)
class FastA(object):
"""Class to handle FastA files. Cannot be compressed
"""
def __init__(self, filename, verbose=False):
if filename.endswith(".gz"):
raise ValueError("Must be decompressed.")
self._fasta = FastxFile(filename)
self.filename = filename
logger.info("Reading input fasta file...please wait")
self._N = len([x for x in FastxFile(filename)])
def __iter__(self):
return self
def __next__(self): # python 3
return self.next()
def next(self): # python 2
# reads 4 lines
try:
d = next(self._fasta)
return d
except KeyboardInterrupt:
# This should allow developers to break a loop that takes too long
# through the reads to run forever
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
except:
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
raise StopIteration
return d
def __len__(self):
return self._N
def _get_names(self):
return [this.name for this in self]
names = property(_get_names)
def _get_sequences(self):
return [this.sequence for this in self]
sequences = property(_get_sequences)
def _get_comment(self):
return [this.comment for this in self]
comments = property(_get_comment)
def _get_lengths(self):
return [len(this.sequence) for this in self]
lengths = property(_get_lengths)
def get_lengths_as_dict(self):
return dict(zip(self.names, self.lengths))
def format_contigs_denovo(self, output_file, len_min=500):
"""Replace NODE with the project name and remove contigs with a length
lower than len_min.
:param str output_file: output file name.
:param int len_min: minimal length of contigs.
Example:
from sequana import FastA
contigs = FastA("denovo_assembly.fasta")
contigs.format_contigs_denovo("path/to/file.fasta", len_min=500)
Results are stored in "path/to/file.fasta".
"""
# catch basename of file without extension
project = os.path.basename(output_file).split(".")[0]
# check if directory exist
output_dir = os.path.dirname(output_file)
try:
if not os.path.exists(output_dir):
os.makedirs(output_dir)
except FileNotFoundError:
pass
n = 1
with open(output_file, "w") as fp:
for contigs in self:
if len(contigs.sequence) < len_min:
break
name = ">{}_{} {}\n".format(project, n, contigs.name)
sequence = "\n".join([contigs.sequence[i:min(i+80,
len(contigs.sequence))] for i in range(0,
len(contigs.sequence), 80)]) + "\n"
fp.write(name + sequence)
n += 1
def select_random_reads(self, N=None, output_filename="random.fasta"):
"""Select random reads and save in a file
:param int N: number of random unique reads to select
should provide a number but a list can be used as well.
:param str output_filename:
"""
import numpy as np
thisN = len(self)
if isinstance(N, int):
if N > thisN:
N = thisN
# create random set of reads to pick up
cherries = list(range(thisN))
np.random.shuffle(cherries)
# cast to set for efficient iteration
cherries = set(cherries[0:N])
elif isinstance(N, set):
cherries = N
elif isinstance(N, list):
cherries = set(N)
fasta = FastxFile(self.filename)
pb = Progress(thisN) # since we scan the entire file
with open(output_filename, "w") as fh:
for i, read in enumerate(fasta):
if i in cherries:
fh.write(read.__str__() + "\n")
else:
pass
pb.animate(i+1)
return cherries
def get_stats(self):
stats = {}
stats["N"] = 2
stats["mean_length"] = mean(self.lengths)
return stats
logger.warning(f"Sample {sample} is not in the VCF [skipping]")
else:
s.add(sample)
if len(s) == 0:
logger.warning(
"No valid samples found in {} - using all samples in VCF", samples_fname
)
else:
samples = s
else:
logger.info("Using all samples in VCF")
logger.info(f"Loaded {len(samples)} samples")
logger.info("Determining which strand each gene is on...")
strand: Dict[str, str] = dict()
for entry in FastxFile(fasta_ref):
for field in entry.comment.rstrip().split():
if field.startswith("strand"):
strand[entry.name] = field[7]
if entry.name not in strand:
raise ValueError(f"Couldn't find strand for {entry.name}")
logger.info("Extracting consensus sequences with bcftools consensus...")
with TemporaryDirectory() as tmpdirname:
for sample in samples:
outname = Path(tmpdirname) / f"{sample}.fa"
args = (
"bcftools",
"consensus",
"-s",
sample,
def get_seq_lens(fastx):
"""Get sequence lengths from fastx file"""
return [len(r.sequence) for r in FastxFile(fastx)]
def sequence_cleaner(fasta_q_file, min_length=0, percentage_n=100.0, concatenate_duplicates=True, remove_ambiguous=False):
"""Read FASTA/FASTQ file and clean the file.
Args:
fasta_q_file (str): Path to FASTA/Q file.
min_length (str): Minimum length allowed (default=0 - allows all the lengths).
percentage_n (float): % of N is allowed (default=100).
concatenate_duplicates (bool): Remove duplicate and keep one sequence (default=True).
remove_ambiguous (bool): Remove any sequence with an ambiguous base (default=False).
Returns:
collections.defaultdict: Hash with clean sequences.
int: # Sequences Processed.
int: # Repeated Sequences.
int: # Repeated Sequences (Reverse Complement).
int: # Short Sequences.
int: # High N Sequences.
"""
hash_sequences = defaultdict(list)
total_sequences_processed = 0
total_repeated_sequences = 0
total_repeated_sequences_rc = 0
total_short_sequences = 0
total_high_n_sequences = 0
with FastxFile(fasta_q_file) as fh:
for entry in fh:
total_sequences_processed += 1
sequence_id = entry.name
sequence = entry.sequence.upper()
found_ambiguous = False
if remove_ambiguous:
for base in sequence:
# found ambiguous base. Sequence is skipped
if base in AMBIGUOUS_BASES:
found_ambiguous = True
break
if not found_ambiguous:
# remove sequences that are shorter or equal to `min_length`
if len(sequence) <= min_length:
total_short_sequences += 1
continue
# remove sequences that do noot meet the % N
elif (float(sequence.count("N")) / float(len(sequence))) * 100 > percentage_n:
total_high_n_sequences += 1
continue
elif concatenate_duplicates:
# repeated sequence - add sequence ID to hash
if sequence in hash_sequences:
hash_sequences[sequence].append(sequence_id)
total_repeated_sequences += 1
else:
rc = reverse_complement(sequence)
# check if reverse complement is already in hash
# if so, add modified ID and flags that the sequence reverse complement was repeated
if rc in hash_sequences:
hash_sequences[rc].append("{}_RC".format(sequence_id))
total_repeated_sequences += 1
total_repeated_sequences_rc += 1
# if not, it means it was the first time the sequence was seen - add it to hash
else:
hash_sequences[sequence].append(sequence_id)
else:
hash_sequences[sequence_id].append(sequence)
return (hash_sequences, total_sequences_processed, total_repeated_sequences, total_repeated_sequences_rc,
total_short_sequences, total_high_n_sequences)
class FastA(object):
"""Class to handle FastA files. Cannot be compressed
"""
def __init__(self, filename, verbose=False):
if filename.endswith(".gz"): #pragma: no cover
raise ValueError("Must be decompressed.")
self._fasta = FastxFile(filename)
self.filename = filename
self._N = None
def __iter__(self):
return self
def __next__(self): # python 3
return self.next()
def next(self): # python 2
# reads 4 lines
try:
d = next(self._fasta)
return d
except KeyboardInterrupt: #pragma: no cover
# This should allow developers to break a loop that takes too long
# through the reads to run forever
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
except:
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
raise StopIteration
def __len__(self):
if self._N is None:
logger.info("Reading input fasta file...please wait")
self._N = len([x for x in FastxFile(self.filename)])
return self._N
def _get_names(self):
return [this.name for this in self]
names = property(_get_names)
def _get_sequences(self):
return [this.sequence for this in self]
sequences = property(_get_sequences)
def _get_comment(self):
return [this.comment for this in self]
comments = property(_get_comment)
def _get_lengths(self):
return [len(this.sequence) for this in self]
lengths = property(_get_lengths)
def get_lengths_as_dict(self):
return dict(zip(self.names, self.lengths))
def format_contigs_denovo(self, output_file, len_min=500):
"""Replace NODE with the project name and remove contigs with a length
lower than len_min.
:param str output_file: output file name.
:param int len_min: minimal length of contigs.
Example:
from sequana import FastA
contigs = FastA("denovo_assembly.fasta")
contigs.format_contigs_denovo("path/to/file.fasta", len_min=500)
Results are stored in "path/to/file.fasta".
"""
# catch basename of file without extension
project = os.path.basename(output_file).split(".")[0]
# check if directory exist
output_dir = os.path.dirname(output_file)
try:
if not os.path.exists(output_dir): #pragma: no cover
os.makedirs(output_dir)
except FileNotFoundError: #pragma: no cover
pass
n = 1
with open(output_file, "w") as fp:
for contigs in self:
if len(contigs.sequence) < len_min:
break
name = ">{}_{} {}\n".format(project, n, contigs.name)
sequence = "\n".join([
contigs.sequence[i:min(i + 80, len(contigs.sequence))]
for i in range(0, len(contigs.sequence), 80)
]) + "\n"
fp.write(name + sequence)
n += 1
def filter(self,
output_filename,
names_to_keep=None,
names_to_exclude=None):
if names_to_exclude is None and names_to_keep is None: #pragma: no cover
logger.warning("No ids provided")
return
if names_to_exclude:
with open(self.filename) as fin:
with open(output_filename, "w") as fout:
skip = False
# do no use readlines. may be slower but may cause memory
# issue
for line in fin:
if line.startswith(">"):
if line[1:].split()[0] in names_to_exclude:
skip = True
else:
skip = False
if skip is False:
fout.write(line)
elif names_to_keep:
with open(self.filename) as fin:
with open(output_filename, "w") as fout:
# do no use readlines. may be slower but may cause memory
# issue
skip = True
for line in fin:
if line.startswith(">"):
if line[1:].split()[0] in names_to_keep:
skip = False
else:
skip = True
if skip is False:
fout.write(line)
def select_random_reads(self, N=None, output_filename="random.fasta"):
"""Select random reads and save in a file
:param int N: number of random unique reads to select
should provide a number but a list can be used as well.
:param str output_filename:
"""
import numpy as np
thisN = len(self)
if isinstance(N, int):
if N > thisN:
N = thisN
# create random set of reads to pick up
cherries = list(range(thisN))
np.random.shuffle(cherries)
# cast to set for efficient iteration
cherries = set(cherries[0:N])
elif isinstance(N, set):
cherries = N
elif isinstance(N, list):
cherries = set(N)
fasta = FastxFile(self.filename)
pb = Progress(thisN) # since we scan the entire file
with open(output_filename, "w") as fh:
for i, read in enumerate(fasta):
if i in cherries:
fh.write(read.__str__() + "\n")
else:
pass
pb.animate(i + 1)
return cherries
def get_stats(self):
from pylab import mean
stats = {}
stats["N"] = len(self.sequences)
stats["mean_length"] = mean(self.lengths)
stats["total_length"] = sum(self.lengths)
from sequana.stats import N50, L50
stats["N50"] = N50(self.lengths)
stats["L50"] = L50(self.lengths)
stats["min_length"] = min(self.lengths)
stats["max_length"] = max(self.lengths)
return stats
def summary(self, max_contigs=-1):
from pylab import mean, argmax
# used by sequana summary fasta
summary = {"number_of_contigs": len(self.sequences)}
summary["total_contigs_length"] = sum(self.lengths)
summary["mean_contig_length"] = mean(self.lengths)
summary["max_contig_length"] = max(self.lengths)
summary["min_contig_length"] = min(self.lengths)
N = 0
lengths = self.lengths[:]
positions = list(range(len(lengths)))
stats = self.get_stats()
print("#sample_name: {}".format(self.filename))
print("#total length: {}".format(stats['total_length']))
print("#N50: {}".format(stats['N50']))
print("#Ncontig: {}".format(stats['N']))
print("#L50: {}".format(stats['L50']))
print("#max_contig_length: {}".format(stats['max_length']))
print("#min_contig_length: {}".format(stats['min_length']))
print("#mean_contig_length: {}".format(stats['mean_length']))
print("contig name,length,count A,C,G,T,N")
if max_contigs == -1:
max_contigs = len(lengths) + 1
while lengths and N < max_contigs:
N += 1
index = argmax(lengths)
length = lengths.pop(index)
position = positions.pop(index)
sequence = self.sequences[position]
name = self.names[position]
print("{},{},{},{},{},{},{}".format(name, length,
sequence.count('A'),
sequence.count('C'),
sequence.count('G'),
sequence.count('T'),
sequence.count('N')))
def GC_content_sequence(self, sequence):
GC = sequence.count('G') + sequence.count('g')
GC += sequence.count('C') + sequence.count('c')
return GC / len(sequence) * 100
def GC_content(self):
lengths = sum(self.lengths)
GC = 0
for seq in self.sequences:
GC += seq.count('G') + seq.count('g')
GC += seq.count('C') + seq.count('c')
return GC / lengths * 100
def reverse_and_save(self, filename):
with open(filename, "w") as fout:
for read in self:
fout.write(">{}\t{}\n{}\n".format(read.name, read.comment,
read.sequence[::-1]))
def save_ctg_to_fasta(self, ctgname, outname, max_length=-1):
index = self.names.index(ctgname)
with open("{}.fa".format(outname), "w") as fout:
if max_length == -1:
fout.write(">{}\n{}".format(outname, self.sequences[index]))
else:
fout.write(">{}\n{}".format(
outname, self.sequences[index][0:max_length]))
def to_fasta(self, outfile, width=80):
"""Save the input FastA file into a new file
The interest of this method is to wrap the sequence into 80 characters.
This is useful if the input file is not formatted correctly.
"""
with open(outfile, "w") as fout:
for name, comment, seq in zip(self.names, self.comments,
self.sequences):
import textwrap
seq = "\n".join(textwrap.wrap(seq, width))
if comment is None:
fout.write(">{}\n{}\n".format(name, seq))
else:
fout.write(">{}\t{}\n{}\n".format(name, comment, seq))
def to_igv_chrom_size(self, output):
data = self.get_lengths_as_dict()
with open(output, "w") as fout:
for k, v in data.items():
fout.write("{}\t{}\n".format(k, v))
def __init__(self, filename, verbose=False):
if filename.endswith(".gz"): #pragma: no cover
raise ValueError("Must be decompressed.")
self._fasta = FastxFile(filename)
self.filename = filename
self._N = None
class FastA(object):
"""Class to handle FastA files. Cannot be compressed
"""
def __init__(self, filename, verbose=False):
if filename.endswith(".gz"):
raise ValueError("Must be decompressed.")
self._fasta = FastxFile(filename)
self._N = len([x for x in FastxFile(filename)])
def __iter__(self):
return self
def __next__(self): # python 3
return self.next()
def next(self): # python 2
# reads 4 lines
try:
d = next(self._fasta)
return d
except KeyboardInterrupt:
# This should allow developers to break a loop that takes too long
# through the reads to run forever
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
except:
self._fasta.close()
self._fasta = FastxFile(self._fasta.filename)
raise StopIteration
return d
def __len__(self):
return self._N
def _get_names(self):
return [this.name for this in self]
names = property(_get_names)
def _get_sequences(self):
return [this.sequence for this in self]
sequences = property(_get_sequences)
def _get_comment(self):
return [this.comment for this in self]
comments = property(_get_comment)
def _get_lengths(self):
return [len(this.sequence) for this in self]
lengths = property(_get_lengths)
def format_contigs_denovo(self, output_file, len_min=500):
"""Replace NODE with the project name and remove contigs with a length
lower than len_min.
:param str output_file: output file name.
:param int len_min: minimal length of contigs.
Example:
from sequana import FastA
contigs = FastA("denovo_assembly.fasta")
contigs.format_contigs_denovo("path/to/file.fasta", len_min=500)
Results are stored in "path/to/file.fasta".
"""
# catch basename of file without extension
project = os.path.basename(output_file).split(".")[0]
# check if directory exist
output_dir = os.path.dirname(output_file)
try:
if not os.path.exists(output_dir):
os.makedirs(output_dir)
except FileNotFoundError:
pass
n = 1
with open(output_file, "w") as fp:
for contigs in self:
if len(contigs.sequence) < len_min:
break
name = ">{}_{} {}\n".format(project, n, contigs.name)
sequence = "\n".join([
contigs.sequence[i:min(i + 80, len(contigs.sequence))]
for i in range(0, len(contigs.sequence), 80)
]) + "\n"
fp.write(name + sequence)
n += 1
def __len__(self):
if self._N is None:
logger.info("Reading input fasta file...please wait")
self._N = len([x for x in FastxFile(self.filename)])
return self._N
def __init__(self, filename, verbose=False):
if filename.endswith(".gz"):
raise ValueError("Must be decompressed.")
self._fasta = FastxFile(filename)
self._N = len([x for x in FastxFile(filename)])