def as_refpkg(sequences, name='temp.refpkg', threads=FASTTREE_THREADS):
"""Context manager yielding a temporary reference package for a
collection of aligned sequences.
Builds a tree with FastTree, creates a reference package, yields.
"""
sequences = list(sequences)
with ntf(prefix='fasttree-', suffix='.log') as log_fp, \
ntf(prefix='fasttree-', suffix='.tre') as tree_fp, \
tempdir(prefix='refpkg') as refpkg_dir:
log_fp.close()
fasttree(sequences, log_path=log_fp.name, output_fp=tree_fp, gtr=True,
threads=threads)
tree_fp.close()
rp = Refpkg(refpkg_dir(name), create=True)
rp.update_metadata('locus', '')
rp.update_phylo_model('FastTree', log_fp.name)
rp.update_file('tree', tree_fp.name)
# FASTA and Stockholm alignment
with ntf(suffix='.fasta') as f:
SeqIO.write(sequences, f, 'fasta')
f.close()
rp.update_file('aln_fasta', f.name)
with ntf(suffix='.sto') as f:
SeqIO.write(sequences, f, 'stockholm')
f.close()
rp.update_file('aln_sto', f.name)
logging.debug("Reference package written to %s", rp.path)
yield rp
def build_index_refpkg(hrefpkg_paths, sequence_file, seqinfo, taxonomy,
dest='index.refpkg', **meta):
"""
Build an index.refpkg from a set of hrefpkgs
"""
# Clear taxonomy
taxonomy = copy.deepcopy(taxonomy)
for node in taxonomy:
node.sequence_ids = set()
def sequence_names(f):
with open(f) as fp:
r = csv.DictReader(fp)
for i in r:
yield i['seqname']
hrefpkgs = (Refpkg(i, create=False) for i in hrefpkg_paths)
seqinfo_files = (i.open_resource('seq_info') for i in hrefpkgs)
# Add seqinfo
for f in seqinfo_files:
with f:
taxonomy.populate_from_seqinfo(f)
# Remove lineages without sequences
taxonomy.prune_unrepresented()
sequence_ids = frozenset(taxonomy.subtree_sequence_ids())
with util.ntf(prefix='aln_fasta', suffix='.fasta') as tf, \
util.ntf(prefix='seq_info', suffix='.csv') as seq_info_fp, \
util.ntf(prefix='taxonomy', suffix='.csv') as tax_fp:
wrap.esl_sfetch(sequence_file, sequence_ids, tf)
tf.close()
# Seqinfo file
r = (i for i in seqinfo if i['seqname'] in sequence_ids)
w = csv.DictWriter(seq_info_fp, seqinfo[0].keys(), lineterminator='\n',
quoting=csv.QUOTE_NONNUMERIC)
w.writeheader()
w.writerows(r)
seq_info_fp.close()
taxonomy.write_taxtable(tax_fp)
tax_fp.close()
rp = Refpkg(dest, create=True)
rp.start_transaction()
rp.update_file('aln_fasta', tf.name)
rp.update_file('seq_info', seq_info_fp.name)
rp.update_file('taxonomy', tax_fp.name)
rp.update_file('profile', wrap.CM)
for k, v in meta.items():
rp.update_metadata(k, v)
rp.commit_transaction()
return rp, sequence_ids
def as_refpkg(sequences, name='temp.refpkg', threads=FASTTREE_THREADS):
"""Context manager yielding a temporary reference package for a
collection of aligned sequences.
Builds a tree with FastTree, creates a reference package, yields.
"""
sequences = list(sequences)
with ntf(prefix='fasttree-', suffix='.log') as log_fp, \
ntf(prefix='fasttree-', suffix='.tre') as tree_fp, \
tempdir(prefix='refpkg') as refpkg_dir:
log_fp.close()
fasttree(sequences,
log_path=log_fp.name,
output_fp=tree_fp,
gtr=True,
threads=threads)
tree_fp.close()
rp = Refpkg(refpkg_dir(name), create=True)
rp.update_metadata('locus', '')
rp.update_phylo_model('FastTree', log_fp.name)
rp.update_file('tree', tree_fp.name)
# FASTA and Stockholm alignment
with ntf(suffix='.fasta') as f:
SeqIO.write(sequences, f, 'fasta')
f.close()
rp.update_file('aln_fasta', f.name)
with ntf(suffix='.sto') as f:
SeqIO.write(sequences, f, 'stockholm')
f.close()
rp.update_file('aln_sto', f.name)
logging.debug("Reference package written to %s", rp.path)
yield rp
def build_index_refpkg(hrefpkg_paths,
sequence_file,
seqinfo,
taxonomy,
dest='index.refpkg',
**meta):
"""
Build an index.refpkg from a set of hrefpkgs
"""
# Clear taxonomy
taxonomy = copy.deepcopy(taxonomy)
for node in taxonomy:
node.sequence_ids = set()
def sequence_names(f):
with open(f) as fp:
r = csv.DictReader(fp)
for i in r:
yield i['seqname']
hrefpkgs = (Refpkg(i, create=False) for i in hrefpkg_paths)
seqinfo_files = (i.open_resource('seq_info') for i in hrefpkgs)
# Add seqinfo
for f in seqinfo_files:
with f:
taxonomy.populate_from_seqinfo(f)
# Remove lineages without sequences
taxonomy.prune_unrepresented()
sequence_ids = frozenset(taxonomy.subtree_sequence_ids())
with util.ntf(prefix='aln_fasta', suffix='.fasta') as tf, \
util.ntf(prefix='seq_info', suffix='.csv') as seq_info_fp, \
util.ntf(prefix='taxonomy', suffix='.csv') as tax_fp:
wrap.esl_sfetch(sequence_file, sequence_ids, tf)
tf.close()
# Seqinfo file
r = (i for i in seqinfo if i['seqname'] in sequence_ids)
w = csv.DictWriter(seq_info_fp,
seqinfo[0].keys(),
lineterminator='\n',
quoting=csv.QUOTE_NONNUMERIC)
w.writeheader()
w.writerows(r)
seq_info_fp.close()
taxonomy.write_taxtable(tax_fp)
tax_fp.close()
rp = Refpkg(dest, create=True)
rp.start_transaction()
rp.update_file('aln_fasta', tf.name)
rp.update_file('seq_info', seq_info_fp.name)
rp.update_file('taxonomy', tax_fp.name)
rp.update_file('profile', wrap.CM)
for k, v in meta.items():
rp.update_metadata(k, v)
rp.commit_transaction()
return rp, sequence_ids
