def dereplicate_seqs(seqs_fp,
output_fp,
min_size=2,
uc_output=True):
"""Dereplicate FASTA sequences and remove singletons using VSEARCH
Parameters
----------
seqs_fp : string
filepath to FASTA sequence file
output_fp : string
file path to dereplicated sequences (FASTA format)
min_size : integer, optional
discard sequences with an abundance value smaller
than integer
uc_output: boolean, optional
output the dereplication map in .uc format
"""
log_name = "%s.log" % splitext(output_fp)[0]
vsearch_dereplicate_exact_seqs(
fasta_filepath=seqs_fp,
output_filepath=output_fp,
output_uc=uc_output,
minuniquesize=min_size,
log_name=log_name)
def dereplicate_seqs(seqs_fp, output_fp, min_size=2):
"""Dereplicate FASTA sequences and remove singletons using VSEARCH
Parameters
----------
seqs_fp : string
filepath to FASTA sequence file
output_fp : string
filepath to dereplicated FASTA file
min_size : integer
discard sequences with an abundance value smaller
than integer
"""
log_name = "%s.log" % splitext(output_fp)[0]
vsearch_dereplicate_exact_seqs(fasta_filepath=seqs_fp,
output_filepath=output_fp,
minuniquesize=min_size,
log_name=log_name)
def dereplicate_seqs(seqs_fp, output_fp, min_size=2, uc_output=True):
"""Dereplicate FASTA sequences and remove singletons using VSEARCH
Parameters
----------
seqs_fp : string
filepath to FASTA sequence file
output_fp : string
file path to dereplicated sequences (FASTA format)
min_size : integer, optional
discard sequences with an abundance value smaller
than integer
uc_output: boolean, optional
output the dereplication map in .uc format
"""
log_name = "%s.log" % splitext(output_fp)[0]
vsearch_dereplicate_exact_seqs(fasta_filepath=seqs_fp,
output_filepath=output_fp,
output_uc=uc_output,
minuniquesize=min_size,
log_name=log_name)
def dereplicate_seqs(seqs_fp,
output_fp,
min_size=2):
"""Dereplicate FASTA sequences and remove singletons using VSEARCH
Parameters
----------
seqs_fp : string
filepath to FASTA sequence file
output_fp : string
filepath to dereplicated FASTA file
min_size : integer
discard sequences with an abundance value smaller
than integer
"""
log_name = "%s.log" % splitext(output_fp)[0]
vsearch_dereplicate_exact_seqs(
fasta_filepath=seqs_fp,
output_filepath=output_fp,
minuniquesize=min_size,
log_name=log_name)
