def shogun_utree_lca(input, output, utree_indx, threads):
verify_make_dir(output)
basenames = [os.path.basename(filename)[:-4] for filename in os.listdir(input) if filename.endswith('.fna')]
for basename in basenames:
fna_file = os.path.join(input, basename + '.fna')
tsv_outf = os.path.join(output, basename + '.utree.tsv')
if not os.path.isfile(tsv_outf):
print(utree_search(utree_indx, fna_file, tsv_outf))
else:
print("Found the output file \"%s\". Skipping the alignment phase for this file." % tsv_outf)
counts = []
utree_outf = os.path.join(output, 'taxon_counts.txt')
# Indexing for emblalmer
if not os.path.isfile(utree_outf):
for basename in basenames:
lcas = []
utree_tsv = os.path.join(output, basename + '.utree.tsv')
with open(utree_tsv) as inf:
tsv_parser = csv.reader(inf, delimiter='\t')
for line in tsv_parser:
if line[1]:
lcas.append(';'.join(line[1].split('; ')))
counts.append(Counter(filter(None, lcas)))
df = pd.DataFrame(counts, index=basenames)
df.T.to_csv(os.path.join(output, 'taxon_counts.csv'))
def shogun_bt2_db(input, output, annotater, extract_id, prefixes, depth, depth_force):
verify_make_dir(output)
# Verify the FASTA is annotated
if input == '-':
output_fn = 'stdin'
else:
output_fn = '.'.join(str(os.path.basename(input)).split('.')[:-1])
outf_fasta = os.path.join(output, output_fn + '.annotated.fna')
outf_map = os.path.join(output, output_fn + '.annotated.map')
if not os.path.isfile(outf_fasta) or not os.path.isfile(outf_map):
tree = NCBITree()
db = RefSeqDatabase()
if annotater == 'refseq':
annotater_class = RefSeqAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
elif annotater == 'nt':
annotater_class = NTAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
else:
annotater_class = GIAnnotater(extract_id, db, tree, depth=depth, depth_force=depth_force)
with open(outf_fasta, 'w') as output_fna:
with open(outf_map, 'w') as output_map:
with open(input) as inf:
inf_fasta = FASTA(inf)
for lines_fna, lines_map in annotater_class.annotate(inf_fasta.read()):
output_fna.write(lines_fna)
output_map.write(lines_map)
else:
print("Found the output files \"%s\" and \"%s\". Skipping the annotation phase for this file." % (
outf_fasta, outf_map))
# Build the output BT2 database
verify_make_dir(os.path.join(output, 'bt2'))
print(bowtie2_build(outf_fasta, os.path.join(output, 'bt2', output_fn)))
def shogun_embalmer_lca(input_dir, output_dir, embalmer_db, threads, pct_id, mincount, taxa_ncbi):
if output_dir is None:
output_dir = input_dir
verify_make_dir(output_dir)
inputfiles = [filename for filename in os.listdir(input_dir) if filename.endswith('.fna') or filename.endswith('fasta')]
basenames = [os.path.splitext(filename)[0] for filename in inputfiles]
outputfps = []
for i,filename in enumerate(inputfiles):
input_fp = os.path.join(input_dir, filename)
tsv_outf = os.path.join(output_dir, basenames[i] + '.embalmer.tsv')
outputfps.append(tsv_outf)
if not os.path.isfile(tsv_outf):
print("Did not file the output file \"%s\". Running the alignment phase for this file." % tsv_outf)
print(embalmer_search(input_fp, tsv_outf, embalmer_db+".edb", embalmer_db+".tax", embalmer_db+".acc", threads, pct_id, taxa_ncbi))
else:
print("Found the output file \"%s\". Skipping the alignment phase for this file." % tsv_outf)
counts = []
# Tabulating
print("Tabulating and filtering hits...")
# print a row of "-" for every 10 samples
if len(inputfiles) >= 100:
for i in range(floor(len(basenames)/10)):
sys.stdout.write('-')
sys.stdout.write('\n')
sys.stdout.flush()
taxon_outf = os.path.join(output_dir, 'taxon_counts.tsv')
if os.path.isfile(taxon_outf):
print("Skipping tabulation step, output file %s already exists." %(taxon_outf))
else:
for outputfp in outputfps:
with open(outputfp) as output_file:
tsv_parser = csv.reader(output_file, delimiter='\t')
taxon_counts = Counter()
for line in tsv_parser:
taxon = line[12]
# drop trailing t__ in redistribute
taxon = re.sub('; t__$','',taxon)
taxon = re.sub('; t__None$','',taxon)
taxon_counts[taxon] += 1
counts.append(taxon_counts)
df = pd.DataFrame(counts, index=basenames)
# filter by mincount
df[df < mincount] = 0
# drop spaces in column
df.columns = [colname.replace('; ',';') for colname in df.columns]
# drop columns that sum to zero
df = df.loc[:,(df.sum(axis=0) != 0)]
df.T.to_csv(taxon_outf,
index_label='Taxon',na_rep='0',sep='\t')
get_rank_specific_taxonomy_tables(df,output_dir)
def shogun_bt2_db(input, output, annotater, extract_id, prefixes, depth,
depth_force):
verify_make_dir(output)
# Verify the FASTA is annotated
if input == '-':
output_fn = 'stdin'
else:
output_fn = '.'.join(str(os.path.basename(input)).split('.')[:-1])
outf_fasta = os.path.join(output, output_fn + '.annotated.fna')
outf_map = os.path.join(output, output_fn + '.annotated.map')
if not os.path.isfile(outf_fasta) or not os.path.isfile(outf_map):
tree = NCBITree()
db = RefSeqDatabase()
if annotater == 'refseq':
annotater_class = RefSeqAnnotater(extract_id,
prefixes,
db,
tree,
depth=depth,
depth_force=depth_force)
elif annotater == 'nt':
annotater_class = NTAnnotater(extract_id,
prefixes,
db,
tree,
depth=depth,
depth_force=depth_force)
else:
annotater_class = GIAnnotater(extract_id,
db,
tree,
depth=depth,
depth_force=depth_force)
with open(outf_fasta, 'w') as output_fna:
with open(outf_map, 'w') as output_map:
with open(input) as inf:
inf_fasta = FASTA(inf)
for lines_fna, lines_map in annotater_class.annotate(
inf_fasta.read()):
output_fna.write(lines_fna)
output_map.write(lines_map)
else:
print(
"Found the output files \"%s\" and \"%s\". Skipping the annotation phase for this file."
% (outf_fasta, outf_map))
# Build the output BT2 database
verify_make_dir(os.path.join(output, 'bt2'))
print(bowtie2_build(outf_fasta, os.path.join(output, 'bt2', output_fn)))
def shogun_utree_db(input, output, annotater, extract_id, threads, prefixes, depth, depth_force):
verify_make_dir(output)
# Verify the FASTA is annotated
if input == '-':
output_fn = 'stdin'
else:
output_fn = '.'.join(str(os.path.basename(input)).split('.')[:-1])
outf_fasta = os.path.join(output, output_fn + '.annotated.fna')
outf_map = os.path.join(output, output_fn + '.annotated.map')
if not os.path.isfile(outf_fasta) or not os.path.isfile(outf_map):
tree = NCBITree()
db = RefSeqDatabase()
if annotater == 'refseq':
annotater_class = RefSeqAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
elif annotater == 'nt':
annotater_class = NTAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
elif annotater == 'ncbi':
annotater_class = NCBIAnnotater(extract_id, tree, depth=depth, depth_force=depth_force)
else:
annotater_class = GIAnnotater(extract_id, db, tree, depth=depth, depth_force=depth_force)
with open(outf_fasta, 'w') as output_fna:
with open(outf_map, 'w') as output_map:
with open(input) as inf:
inf_fasta = FASTA(inf)
for lines_fna, lines_map in annotater_class.annotate(inf_fasta.read()):
output_fna.write(lines_fna)
output_map.write(lines_map)
else:
print("Found the output files \"%s\" and \"%s\". Skipping the annotation phase for this file." % (
outf_fasta, outf_map))
# Build the output CTR
verify_make_dir(os.path.join(output, 'utree'))
path_uncompressed_tree = os.path.join(output, 'utree', output_fn + '.utr')
path_compressed_tree = os.path.join(output, 'utree', output_fn + '.ctr')
if os.path.exists(path_compressed_tree):
print('Compressed tree database file %s exists, skipping this step.' % path_compressed_tree)
else:
if not os.path.exists(path_uncompressed_tree):
print(utree_build(outf_fasta, outf_map, path_uncompressed_tree, threads=threads))
print(utree_compress(path_uncompressed_tree, path_compressed_tree))
os.remove(path_uncompressed_tree)
def shogun_bt2_lca(input, output, bt2_indx, extract_ncbi_tid, depth, threads, annotate_lineage, run_lca):
verify_make_dir(output)
basenames = [os.path.basename(filename)[:-4] for filename in os.listdir(input) if filename.endswith('.fna')]
for basename in basenames:
fna_inf = os.path.join(input, basename + '.fna')
sam_outf = os.path.join(output, basename + '.sam')
if os.path.isfile(sam_outf):
print("Found the samfile \"%s\". Skipping the alignment phase for this file." % sam_outf)
else:
print(bowtie2_align(fna_inf, sam_outf, bt2_indx, num_threads=threads))
if run_lca:
tree = NCBITree()
rank_name = list(tree.lineage_ranks.keys())[depth-1]
if not rank_name:
raise ValueError('Depth must be between 0 and 7, it was %d' % depth)
begin, end = extract_ncbi_tid.split(',')
counts = []
for basename in basenames:
sam_file = os.path.join(output, basename + '.sam')
lca_map = {}
for qname, rname in yield_alignments_from_sam_inf(sam_file):
ncbi_tid = int(find_between(rname, begin, end))
if qname in lca_map:
current_ncbi_tid = lca_map[qname]
if current_ncbi_tid:
if current_ncbi_tid != ncbi_tid:
lca_map[qname] = tree.lowest_common_ancestor(ncbi_tid, current_ncbi_tid)
else:
lca_map[qname] = ncbi_tid
if annotate_lineage:
lca_map = valmap(lambda x: tree.green_genes_lineage(x, depth=depth), lca_map)
taxon_counts = Counter(filter(None, lca_map.values()))
else:
lca_map = valfilter(lambda x: tree.get_rank_from_taxon_id(x) == rank_name, lca_map)
taxon_counts = Counter(filter(None, lca_map.values()))
counts.append(taxon_counts)
df = pd.DataFrame(counts, index=basenames)
df.T.to_csv(os.path.join(output, 'taxon_counts.csv'))
def shogun_bugbase(input, output, img_database_folder):
verify_make_dir(output)
utree_outf = os.path.join(output, 'taxa_counts.txt')
# Indexing for emblalmer
if not os.path.isfile(utree_outf):
utree_indx = os.path.join(img_database_folder, 'img.genes.ctr')
with open(os.path.join(img_database_folder, 'img_map.pkl'),
'rb') as inf:
gg2img_oid = pickle.load(inf)
basenames = [
os.path.basename(filename)[:-4] for filename in os.listdir(input)
if filename.endswith('.fna')
]
for basename in basenames:
fna_file = os.path.join(input, basename + '.fna')
tsv_outf = os.path.join(output, basename + '.utree.tsv')
if not os.path.isfile(tsv_outf):
print(utree_search(utree_indx, fna_file, tsv_outf))
else:
print(
"Found the output file \"%s\". Skipping the alignment phase for this file."
% tsv_outf)
counts = []
for basename in basenames:
lcas = []
utree_tsv = os.path.join(output, basename + '.utree.tsv')
with open(utree_tsv) as inf:
tsv_parser = csv.reader(inf, delimiter='\t')
for line in tsv_parser:
if line[1]:
taxon = line[1].replace('; ', ';')
if taxon in gg2img_oid:
lcas.append(gg2img_oid[taxon])
counts.append(Counter(filter(None, lcas)))
df = pd.DataFrame(counts, index=basenames).fillna(0).astype(int).T
df.to_csv(utree_outf, sep='\t', index_label='#OTU ID')
else:
print("Found the output file \"%s\". Skipping all steps." % utree_outf)
def shogun_utree_db(input, output, annotater, extract_id, threads, prefixes, depth, depth_force):
verify_make_dir(output)
# Verify the FASTA is annotated
if input == '-':
output_fn = 'stdin'
else:
output_fn = '.'.join(str(os.path.basename(input)).split('.')[:-1])
outf_fasta = os.path.join(output, output_fn + '.annotated.fna')
outf_map = os.path.join(output, output_fn + '.annotated.map')
if not os.path.isfile(outf_fasta) or not os.path.isfile(outf_map):
tree = NCBITree()
db = RefSeqDatabase()
if annotater == 'refseq':
annotater_class = RefSeqAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
elif annotater == 'nt':
annotater_class = NTAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
else:
annotater_class = GIAnnotater(extract_id, db, tree, depth=depth, depth_force=depth_force)
with open(outf_fasta, 'w') as output_fna:
with open(outf_map, 'w') as output_map:
with open(input) as inf:
inf_fasta = FASTA(inf)
for lines_fna, lines_map in annotater_class.annotate(inf_fasta.read()):
output_fna.write(lines_fna)
output_map.write(lines_map)
else:
print("Found the output files \"%s\" and \"%s\". Skipping the annotation phase for this file." % (
outf_fasta, outf_map))
# Build the output CTR
verify_make_dir(os.path.join(output, 'utree'))
path_uncompressed_tree = os.path.join(output, 'utree', output_fn + '.utr')
path_compressed_tree = os.path.join(output, 'utree', output_fn + '.ctr')
if os.path.exists(path_compressed_tree):
print('Compressed tree database file %s exists, skipping this step.' % path_compressed_tree)
else:
if not os.path.exists(path_uncompressed_tree):
print(utree_build(outf_fasta, outf_map, path_uncompressed_tree, threads=threads))
print(utree_compress(path_uncompressed_tree, path_compressed_tree))
os.remove(path_uncompressed_tree)
def shogun_bugbase(input, output, img_database_folder):
verify_make_dir(output)
utree_outf = os.path.join(output, 'taxa_counts.txt')
# Indexing for emblalmer
if not os.path.isfile(utree_outf):
utree_indx = os.path.join(img_database_folder, 'img.genes.ctr')
with open(os.path.join(img_database_folder, 'img_map.pkl'), 'rb') as inf:
gg2img_oid = pickle.load(inf)
basenames = [os.path.basename(filename)[:-4] for filename in os.listdir(input) if filename.endswith('.fna')]
for basename in basenames:
fna_file = os.path.join(input, basename + '.fna')
tsv_outf = os.path.join(output, basename + '.utree.tsv')
if not os.path.isfile(tsv_outf):
print(utree_search(utree_indx, fna_file, tsv_outf))
else:
print("Found the output file \"%s\". Skipping the alignment phase for this file." % tsv_outf)
counts = []
for basename in basenames:
lcas = []
utree_tsv = os.path.join(output, basename + '.utree.tsv')
with open(utree_tsv) as inf:
tsv_parser = csv.reader(inf, delimiter='\t')
for line in tsv_parser:
if line[1]:
taxon = line[1].replace('; ', ';')
if taxon in gg2img_oid:
lcas.append(gg2img_oid[taxon])
counts.append(Counter(filter(None, lcas)))
df = pd.DataFrame(counts, index=basenames).fillna(0).astype(int).T
df.to_csv(utree_outf, sep='\t', index_label='#OTU ID')
else:
print("Found the output file \"%s\". Skipping all steps." % utree_outf)
def annotate_fasta(input, output, extract_refseq_id, prefixes, depth,
depth_force):
verify_make_dir(output)
if input == '-':
output_fn = 'stdin'
else:
output_fn = '.'.join(str(os.path.basename(input)).split('.')[:-1])
with open(input, 'r') if input != '-' else sys.stdin as inf:
with open(os.path.join(output, output_fn + '.annotated.fna'),
'w') as output_fna:
with open(os.path.join(output, output_fn + '.annotated.map'),
'w') as output_map:
inf_fasta = FASTA(inf)
annotater = refseq_annotater(inf_fasta.read(),
prefixes,
extract_refseq_id,
depth=depth,
depth_force=depth_force)
for lines_fna, lines_map in annotater:
output_fna.write(lines_fna)
output_map.write(lines_map)
def shogun_bt2_lca(input, output, bt2_indx, extract_ncbi_tid, depth, threads, annotate_lineage, run_lca):
verify_make_dir(output)
basenames = [os.path.basename(filename)[:-4] for filename in os.listdir(input) if filename.endswith('.fna')]
for basename in basenames:
fna_inf = os.path.join(input, basename + '.fna')
sam_outf = os.path.join(output, basename + '.sam')
if os.path.isfile(sam_outf):
print("Found the samfile \"%s\". Skipping the alignment phase for this file." % sam_outf)
else:
print(bowtie2_align(fna_inf, sam_outf, bt2_indx, num_threads=threads))
if run_lca:
tree = NCBITree()
rank_name = list(tree.lineage_ranks.keys())[depth-1]
if not rank_name:
raise ValueError('Depth must be between 0 and 7, it was %d' % depth)
begin, end = extract_ncbi_tid.split(',')
counts = []
for basename in basenames:
sam_file = os.path.join(output, basename + '.sam')
lca_map = build_lca_map(sam_file, lambda x: int(find_between(x, begin, end)), tree)
if annotate_lineage:
lca_map = valmap(lambda x: tree.green_genes_lineage(x, depth=depth), lca_map)
taxon_counts = Counter(filter(None, lca_map.values()))
else:
lca_map = valfilter(lambda x: tree.get_rank_from_taxon_id(x) == rank_name, lca_map)
taxon_counts = Counter(filter(None, lca_map.values()))
counts.append(taxon_counts)
df = pd.DataFrame(counts, index=basenames)
df.T.to_csv(os.path.join(output, 'taxon_counts.csv'))
def shogun_utree_lca(input, output, utree_indx, threads, confidence, support,
mincount):
verify_make_dir(output)
basenames = [
os.path.basename(filename)[:-4] for filename in os.listdir(input)
if filename.endswith('.fna')
]
for basename in basenames:
fna_file = os.path.join(input, basename + '.fna')
tsv_outf = os.path.join(output, basename + '.utree.tsv')
if not os.path.isfile(tsv_outf):
print(utree_search(utree_indx, fna_file, tsv_outf))
else:
print(
"Found the output file \"%s\". Skipping the alignment phase for this file."
% tsv_outf)
counts = []
utree_outf = os.path.join(output, 'taxon_counts.txt')
# Tabulating
print("Tabulating and filtering hits...")
# print a row of "-" for every 10 samples
if len(basenames) >= 100:
for i in range(floor(len(basenames) / 10)):
sys.stdout.write('-')
sys.stdout.write('\n')
sys.stdout.flush()
if not os.path.isfile(utree_outf):
n_fail_confidence_only = 0
n_fail_support_only = 0
n_fail_both = 0
n = 0
n_pass = 0
for i, basename in enumerate(basenames):
if len(basenames) >= 100:
if (i + 1) % 10 == 0:
sys.stdout.write('.')
sys.stdout.flush()
lcas = [] # list of tuples [redistribute, confidence, support]
utree_tsv = os.path.join(output, basename + '.utree.tsv')
with open(utree_tsv) as inf:
tsv_parser = csv.reader(inf, delimiter='\t')
for line in tsv_parser:
if line[1]:
taxonomy = line[1]
is_confident = float(line[2]) >= confidence
is_supported = int(line[3]) >= support
n += 1
if not is_confident and not is_supported:
n_fail_both += 1
elif not is_confident:
n_fail_confidence_only += 1
elif not is_supported:
n_fail_support_only += 1
else:
n_pass += 1
lcas.append(taxonomy)
counts.append(Counter(lcas))
print(
'%d total assignments\n%d failed confidence only\n%d failed support_only\n%d failed both\n%d remaining'
% (n, n_fail_confidence_only, n_fail_support_only, n_fail_both,
n_pass))
sys.stdout.write('\n')
sys.stdout.flush()
df = pd.DataFrame(counts, index=basenames)
# filter by mincount
df[df < mincount] = 0
# drop spaces in column
df.columns = [colname.replace('; ', ';') for colname in df.columns]
# drop trailing t__ in redistribute
df.columns = [re.sub(';t__$', '', colname) for colname in df.columns]
df.T.to_csv(os.path.join(output, 'taxon_counts.csv'),
index_label='Taxon',
na_rep='0',
sep='\t')
def shogun_bt2_capitalist(input, output, bt2_indx, reference_fasta, reference_map, extract_ncbi_tid, depth, threads):
verify_make_dir(output)
fna_files = [os.path.join(input, filename) for filename in os.listdir(input) if filename.endswith('.fna')]
for fna_file in fna_files:
sam_outf = os.path.join(output, '.'.join(str(os.path.basename(fna_file)).split('.')[:-1]) + '.sam')
print(bowtie2_align(fna_file, sam_outf, bt2_indx, num_threads=threads))
tree = NCBITree()
begin, end = extract_ncbi_tid.split(',')
sam_files = [os.path.join(output, filename) for filename in os.listdir(output) if filename.endswith('.sam')]
lca_maps = {}
for sam_file in sam_files:
lca_map = {}
for qname, rname in yield_alignments_from_sam_inf(sam_file):
ncbi_tid = int(find_between(rname, begin, end))
if qname in lca_map:
current_ncbi_tid = lca_map[qname]
if current_ncbi_tid:
if current_ncbi_tid != ncbi_tid:
lca_map[qname] = tree.lowest_common_ancestor(ncbi_tid, current_ncbi_tid)
else:
lca_map[qname] = ncbi_tid
lca_map = valmap(lambda x: tree.green_genes_lineage(x, depth=depth), lca_map)
# filter out null values
lca_maps['.'.join(os.path.basename(sam_file).split('.')[:-1])] = reverse_collision_dict(lca_map)
for basename in lca_maps.keys():
lca_maps[basename] = valmap(lambda val: (basename, val), lca_maps[basename])
lca_map_2 = defaultdict(list)
for basename in lca_maps.keys():
for key, val in lca_maps[basename].items():
if key:
lca_map_2[key].append(val)
fna_faidx = {}
for fna_file in fna_files:
fna_faidx[os.path.basename(fna_file)[:-4]] = pyfaidx.Fasta(fna_file)
dict_reference_map = defaultdict(list)
with open(reference_map) as inf:
tsv_in = csv.reader(inf, delimiter='\t')
for line in tsv_in:
dict_reference_map[';'.join(line[1].split('; '))].append(line[0])
# reverse the dict to feed into embalmer
references_faidx = pyfaidx.Fasta(reference_fasta)
tmpdir = tempfile.mkdtemp()
with open(os.path.join(output, 'embalmer_out.txt'), 'w') as embalmer_cat:
for key in lca_map_2.keys():
queries_fna_filename = os.path.join(tmpdir, 'queries.fna')
references_fna_filename = os.path.join(tmpdir, 'reference.fna')
output_filename = os.path.join(tmpdir, 'output.txt')
with open(queries_fna_filename, 'w') as queries_fna:
for basename, headers in lca_map_2[key]:
for header in headers:
record = fna_faidx[basename][header][:]
queries_fna.write('>filename|%s|%s\n%s\n' % (basename, record.name, record.seq))
with open(references_fna_filename, 'w') as references_fna:
for i in dict_reference_map[key]:
record = references_faidx[i][:]
references_fna.write('>%s\n%s\n' % (record.name, record.seq))
embalmer_align(queries_fna_filename, references_fna_filename, output_filename)
with open(output_filename) as embalmer_out:
for line in embalmer_out:
embalmer_cat.write(line)
os.remove(queries_fna_filename)
os.remove(references_fna_filename)
os.remove(output_filename)
os.rmdir(tmpdir)
sparse_ncbi_dict = defaultdict(dict)
# build query by NCBI_TID DataFrame
with open(os.path.join(output, 'embalmer_out.txt')) as embalmer_cat:
embalmer_csv = csv.reader(embalmer_cat, delimiter='\t')
for line in embalmer_csv:
# line[0] = qname, line[1] = rname, line[2] = %match
ncbi_tid = np.int(find_between(line[1], begin, end))
sparse_ncbi_dict[line[0]][ncbi_tid] = np.float(line[2])
df = pd.DataFrame.from_dict(sparse_ncbi_dict)
df.to_csv(os.path.join(output, 'strain_alignments.csv'))
def shogun_functional(input, output, bt2_indx, extract_ncbi_tid, threads):
verify_make_dir(output)
basenames = [os.path.basename(filename)[:-4] for filename in os.listdir(input) if filename.endswith('.fna')]
# Create a SAM file for each input FASTA file
for basename in basenames:
fna_inf = os.path.join(input, basename + '.fna')
sam_outf = os.path.join(output, basename + '.sam')
if os.path.isfile(sam_outf):
print("Found the samfile \"%s\". Skipping the alignment phase for this file." % sam_outf)
else:
print(bowtie2_align(fna_inf, sam_outf, bt2_indx, num_threads=threads))
img_map = IMGMap()
for basename in basenames:
sam_inf = os.path.join(output, basename + '.sam')
step_outf = 'test'
if os.path.isfile(step_outf):
print("Found the \"%s.kegg.csv\". Skipping the LCA phase for this file." % step_outf)
else:
lca_map = build_img_ncbi_map(yield_alignments_from_sam_inf(sam_inf), )
sam_files = [os.path.join(args.input, filename) for filename in os.listdir(args.input) if filename.endswith('.sam')]
img_map = IMGMap()
ncbi_tree = NCBITree()
lca = LCA(ncbi_tree, args.depth)
with open(args.output, 'w') if args.output else sys.stdout as outf:
csv_outf = csv.writer(outf, quoting=csv.QUOTE_ALL, lineterminator='\n')
csv_outf.writerow(['sample_id', 'sequence_id', 'ncbi_tid', 'img_id'])
for file in sam_files:
with open(file) as inf:
lca_map = build_lca_map(yield_alignments_from_sam_inf(inf), lca, img_map)
for key in lca_map:
img_ids, ncbi_tid = lca_map[key]
csv_outf.writerow([os.path.basename(file).split('.')[0], key, ncbi_tid, ','.join(img_ids)])
if run_lca:
tree = NCBITree()
rank_name = list(tree.lineage_ranks.keys())[depth - 1]
if not rank_name:
raise ValueError('Depth must be between 0 and 7, it was %d' % depth)
begin, end = extract_ncbi_tid.split(',')
counts = []
for basename in basenames:
sam_file = os.path.join(output, basename + '.sam')
lca_map = {}
for qname, rname in yield_alignments_from_sam_inf(sam_file):
ncbi_tid = int(find_between(rname, begin, end))
if qname in lca_map:
current_ncbi_tid = lca_map[qname]
if current_ncbi_tid:
if current_ncbi_tid != ncbi_tid:
lca_map[qname] = tree.lowest_common_ancestor(ncbi_tid, current_ncbi_tid)
else:
lca_map[qname] = ncbi_tid
if annotate_lineage:
lca_map = valmap(lambda x: tree.green_genes_lineage(x, depth=depth), lca_map)
taxon_counts = Counter(filter(None, lca_map.values()))
else:
lca_map = valfilter(lambda x: tree.get_rank_from_taxon_id(x) == rank_name, lca_map)
taxon_counts = Counter(filter(None, lca_map.values()))
counts.append(taxon_counts)
df = pd.DataFrame(counts, index=basenames)
df.T.to_csv(os.path.join(output, 'taxon_counts.csv'))
def shogun_bt2_capitalist(input, output, bt2_indx, reference_fasta,
reference_map, extract_ncbi_tid, depth, threads):
verify_make_dir(output)
fna_files = [
os.path.join(input, filename) for filename in os.listdir(input)
if filename.endswith('.fna')
]
for fna_file in fna_files:
sam_outf = os.path.join(
output,
'.'.join(str(os.path.basename(fna_file)).split('.')[:-1]) + '.sam')
print(bowtie2_align(fna_file, sam_outf, bt2_indx, num_threads=threads))
tree = NCBITree()
begin, end = extract_ncbi_tid.split(',')
sam_files = [
os.path.join(output, filename) for filename in os.listdir(output)
if filename.endswith('.sam')
]
lca_maps = {}
for sam_file in sam_files:
lca_map = {}
for qname, rname in yield_alignments_from_sam_inf(sam_file):
ncbi_tid = int(find_between(rname, begin, end))
if qname in lca_map:
current_ncbi_tid = lca_map[qname]
if current_ncbi_tid:
if current_ncbi_tid != ncbi_tid:
lca_map[qname] = tree.lowest_common_ancestor(
ncbi_tid, current_ncbi_tid)
else:
lca_map[qname] = ncbi_tid
lca_map = valmap(lambda x: tree.green_genes_lineage(x, depth=depth),
lca_map)
# filter out null values
lca_maps['.'.join(os.path.basename(sam_file).split('.')
[:-1])] = reverse_collision_dict(lca_map)
for basename in lca_maps.keys():
lca_maps[basename] = valmap(lambda val: (basename, val),
lca_maps[basename])
lca_map_2 = defaultdict(list)
for basename in lca_maps.keys():
for key, val in lca_maps[basename].items():
if key:
lca_map_2[key].append(val)
fna_faidx = {}
for fna_file in fna_files:
fna_faidx[os.path.basename(fna_file)[:-4]] = pyfaidx.Fasta(fna_file)
dict_reference_map = defaultdict(list)
with open(reference_map) as inf:
tsv_in = csv.reader(inf, delimiter='\t')
for line in tsv_in:
dict_reference_map[';'.join(line[1].split('; '))].append(line[0])
# reverse the dict to feed into embalmer
references_faidx = pyfaidx.Fasta(reference_fasta)
tmpdir = tempfile.mkdtemp()
with open(os.path.join(output, 'embalmer_out.txt'), 'w') as embalmer_cat:
for key in lca_map_2.keys():
queries_fna_filename = os.path.join(tmpdir, 'queries.fna')
references_fna_filename = os.path.join(tmpdir, 'reference.fna')
output_filename = os.path.join(tmpdir, 'output.txt')
with open(queries_fna_filename, 'w') as queries_fna:
for basename, headers in lca_map_2[key]:
for header in headers:
record = fna_faidx[basename][header][:]
queries_fna.write('>filename|%s|%s\n%s\n' %
(basename, record.name, record.seq))
with open(references_fna_filename, 'w') as references_fna:
for i in dict_reference_map[key]:
record = references_faidx[i][:]
references_fna.write('>%s\n%s\n' %
(record.name, record.seq))
embalmer_align(queries_fna_filename, references_fna_filename,
output_filename)
with open(output_filename) as embalmer_out:
for line in embalmer_out:
embalmer_cat.write(line)
os.remove(queries_fna_filename)
os.remove(references_fna_filename)
os.remove(output_filename)
os.rmdir(tmpdir)
sparse_ncbi_dict = defaultdict(dict)
# build query by NCBI_TID DataFrame
with open(os.path.join(output, 'embalmer_out.txt')) as embalmer_cat:
embalmer_csv = csv.reader(embalmer_cat, delimiter='\t')
for line in embalmer_csv:
# line[0] = qname, line[1] = rname, line[2] = %match
ncbi_tid = np.int(find_between(line[1], begin, end))
sparse_ncbi_dict[line[0]][ncbi_tid] = np.float(line[2])
df = pd.DataFrame.from_dict(sparse_ncbi_dict)
df.to_csv(os.path.join(output, 'strain_alignments.csv'))
def shogun_utree_capitalist(input, output, utree_indx, reference_fasta,
reference_map, extract_ncbi_tid, threads):
verify_make_dir(output)
basenames = [
os.path.basename(filename)[:-4] for filename in os.listdir(input)
if filename.endswith('.fna')
]
for basename in basenames:
fna_file = os.path.join(input, basename + '.fna')
tsv_outf = os.path.join(output, basename + '.utree.tsv')
if not os.path.isfile(tsv_outf):
print(utree_search(utree_indx, fna_file, tsv_outf))
else:
print(
"Found the output file \"%s\". Skipping the alignment phase for this file."
% tsv_outf)
embalmer_outf = os.path.join(output, 'embalmer_out.txt')
# Indexing for emblalmer
if not os.path.isfile(embalmer_outf):
lca_maps = defaultdict(lambda: defaultdict(list))
for basename in basenames:
utree_tsv = os.path.join(output, basename + '.utree.tsv')
with open(utree_tsv) as inf:
tsv_parser = csv.reader(inf, delimiter='\t')
for line in tsv_parser:
if line[1]:
lca_maps[';'.join(
line[1].split('; '))][basename].append(line[0])
fna_faidx = {}
for basename in basenames:
fna_faidx[basename] = pyfaidx.Fasta(
os.path.join(input, basename + '.fna'))
dict_reference_map = defaultdict(list)
with open(reference_map) as inf:
tsv_in = csv.reader(inf, delimiter='\t')
for line in tsv_in:
dict_reference_map[';'.join(line[1].split('; '))].append(
line[0])
# reverse the dict to feed into embalmer
references_faidx = pyfaidx.Fasta(reference_fasta)
tmpdir = tempfile.mkdtemp()
print(tmpdir)
with open(embalmer_outf, 'w') as embalmer_cat:
for species in lca_maps.keys():
queries_fna_filename = os.path.join(tmpdir, 'queries.fna')
references_fna_filename = os.path.join(tmpdir, 'reference.fna')
output_filename = os.path.join(tmpdir, 'output.txt')
with open(queries_fna_filename, 'w') as queries_fna:
for basename in lca_maps[species].keys():
for header in lca_maps[species][basename]:
record = fna_faidx[basename][header][:]
queries_fna.write(
'>filename|%s|%s\n%s\n' %
(basename, record.name, record.seq))
with open(references_fna_filename, 'w') as references_fna:
for i in dict_reference_map[species]:
record = references_faidx[i][:]
references_fna.write('>%s\n%s\n' %
(record.name, record.seq))
print(
embalmer_align(queries_fna_filename,
references_fna_filename, output_filename))
with open(output_filename) as embalmer_out:
for line in embalmer_out:
embalmer_cat.write(line)
os.remove(queries_fna_filename)
os.remove(references_fna_filename)
os.remove(output_filename)
os.rmdir(tmpdir)
else:
print(
"Found the output file \"%s\". Skipping the strain alignment phase for this file."
% embalmer_outf)
# Convert the results from embalmer into CSV
sparse_ncbi_dict = defaultdict(dict)
begin, end = extract_ncbi_tid.split(',')
# build query by NCBI_TID DataFrame
with open(embalmer_outf) as embalmer_cat:
embalmer_csv = csv.reader(embalmer_cat, delimiter='\t')
for line in embalmer_csv:
# line[0] = qname, line[1] = rname, line[2] = %match
ncbi_tid = np.int(find_between(line[1], begin, end))
sparse_ncbi_dict[line[0]][ncbi_tid] = np.float(line[2])
df = pd.DataFrame.from_dict(sparse_ncbi_dict)
df.to_csv(os.path.join(output, 'strain_alignments.csv'))
def shogun_utree_capitalist(input, output, utree_indx, reference_fasta, reference_map, extract_ncbi_tid, threads):
verify_make_dir(output)
basenames = [os.path.basename(filename)[:-4] for filename in os.listdir(input) if filename.endswith('.fna')]
for basename in basenames:
fna_file = os.path.join(input, basename + '.fna')
tsv_outf = os.path.join(output, basename + '.utree.tsv')
if not os.path.isfile(tsv_outf):
print(utree_search(utree_indx, fna_file, tsv_outf))
else:
print("Found the output file \"%s\". Skipping the alignment phase for this file." % tsv_outf)
embalmer_outf = os.path.join(output, 'embalmer_out.txt')
# Indexing for emblalmer
if not os.path.isfile(embalmer_outf):
lca_maps = defaultdict(lambda: defaultdict(list))
for basename in basenames:
utree_tsv = os.path.join(output, basename + '.utree.tsv')
with open(utree_tsv) as inf:
tsv_parser = csv.reader(inf, delimiter='\t')
for line in tsv_parser:
if line[1]:
lca_maps[';'.join(line[1].split('; '))][basename].append(line[0])
fna_faidx = {}
for basename in basenames:
fna_faidx[basename] = pyfaidx.Fasta(os.path.join(input, basename + '.fna'))
dict_reference_map = defaultdict(list)
with open(reference_map) as inf:
tsv_in = csv.reader(inf, delimiter='\t')
for line in tsv_in:
dict_reference_map[';'.join(line[1].split('; '))].append(line[0])
# reverse the dict to feed into embalmer
references_faidx = pyfaidx.Fasta(reference_fasta)
tmpdir = tempfile.mkdtemp()
print(tmpdir)
with open(embalmer_outf, 'w') as embalmer_cat:
for species in lca_maps.keys():
queries_fna_filename = os.path.join(tmpdir, 'queries.fna')
references_fna_filename = os.path.join(tmpdir, 'reference.fna')
output_filename = os.path.join(tmpdir, 'output.txt')
with open(queries_fna_filename, 'w') as queries_fna:
for basename in lca_maps[species].keys():
for header in lca_maps[species][basename]:
record = fna_faidx[basename][header][:]
queries_fna.write('>filename|%s|%s\n%s\n' % (basename, record.name, record.seq))
with open(references_fna_filename, 'w') as references_fna:
for i in dict_reference_map[species]:
record = references_faidx[i][:]
references_fna.write('>%s\n%s\n' % (record.name, record.seq))
print(embalmer_align(queries_fna_filename, references_fna_filename, output_filename))
with open(output_filename) as embalmer_out:
for line in embalmer_out:
embalmer_cat.write(line)
os.remove(queries_fna_filename)
os.remove(references_fna_filename)
os.remove(output_filename)
os.rmdir(tmpdir)
else:
print("Found the output file \"%s\". Skipping the strain alignment phase for this file." % embalmer_outf)
# Convert the results from embalmer into CSV
sparse_ncbi_dict = defaultdict(dict)
begin, end = extract_ncbi_tid.split(',')
# build query by NCBI_TID DataFrame
with open(embalmer_outf) as embalmer_cat:
embalmer_csv = csv.reader(embalmer_cat, delimiter='\t')
for line in embalmer_csv:
# line[0] = qname, line[1] = rname, line[2] = %match
ncbi_tid = np.int(find_between(line[1], begin, end))
sparse_ncbi_dict[line[0]][ncbi_tid] = np.float(line[2])
df = pd.DataFrame.from_dict(sparse_ncbi_dict)
df.to_csv(os.path.join(output, 'strain_alignments.csv'))
