def main():
parser = make_arg_parser()
args = parser.parse_args()
db = RefSeqDatabase()
nt = NCBITree()
# parse command line
with open(args.input, 'r') if args.input != '-' else sys.stdin as inf:
fasta_gen = FASTA(inf)
assembly_version = os.path.basename(args.input).split('_genomic')[0]
with open(args.output, 'w') if args.output != '-' else sys.stdout as outf:
for header, sequence in fasta_gen.read():
if '.cluster' in header:
header = header.replace('.cluster','_cluster')
else:
pass
ncbi_tid = db.get_ncbi_tid_from_refseq_accession_version(header.split('_cluster')[0])
if ncbi_tid:
ncbi_tid = ncbi_tid[0]
organism = nt.gg_lineage(ncbi_tid)
genus_species = organism.split(';')[-1]
genus_species = genus_species.replace('s__','')
outf.write('>ncbi_tid|%d|ref|%s|organism|%s|\n' % (ncbi_tid, header, genus_species))
outf.write(sequence+'\n')
else:
outf.write('>ref|%s|\n' % (header))
outf.write(sequence+'\n')
def main():
parser = make_arg_parser()
args = parser.parse_args()
db = RefSeqDatabase()
nt = NCBITree()
# parse command line
with open(args.input, 'r') if args.input != '-' else sys.stdin as inf:
fasta_gen = FASTA(inf)
assembly_version = os.path.basename(args.input).split('_genomic')[0]
with open(args.output, 'w') if args.output != '-' else sys.stdout as outf:
for header, sequence in fasta_gen.read():
if '.cluster' in header:
header = header.replace('.cluster','_cluster')
else:
pass
ncbi_tid = db.get_ncbi_tid_from_refseq_accession_version(header.split('_cluster')[0])
if ncbi_tid:
ncbi_tid = ncbi_tid[0]
organism = nt.gg_lineage(ncbi_tid)
# genus_species = organism.split(';')[-1]
# genus_species = genus_species.replace('s__','')
outf.write('>ncbi_tid|%d|ref|%s|organism|%s|\n' % (ncbi_tid, header, organism))
outf.write(sequence+'\n')
else:
outf.write('>ref|%s|\n' % (header))
outf.write(sequence+'\n')
def list_organisms(ofus, hclus, nt_cat, typetable, outpath, cut_h):
bgc_dd = defaultdict(list)
for value, key in hclus.itertuples(index=True):
key = str('%05d' % key)
bgc_dd[key].extend(list([value]))
ofu_list = ofus.split(',')
i = 0
# Preload the Database and Tree
db = RefSeqDatabase()
nt = NCBITree()
for ofu in ofu_list:
ofu = str(ofu)
if ofu.startswith('ofu'):
ofu_n = str(ofu.replace('ofu', ''))
elif ofu.startswith('ofu_'):
ofu_n = str(ofu.replace('ofu', ''))
else:
ofu_n = ofu
bgcs = bgc_dd[ofu_n]
name_dict = defaultdict(list)
with suppress_stdout():
for bgc in bgcs:
if bgc.startswith('ncbi_tid'):
ncbi_tid = bgc.split('|')[1]
if ncbi_tid == 'na':
name = bgc.split('|')[3]
else:
ncbi_tid = int(ncbi_tid)
name = nt.green_genes_lineage(ncbi_tid,
depth=8,
depth_force=True)
elif '|genbank|' in bgc:
gbk_id = bgc.split('|')[3].split('_cluster')[0]
if nt_cat == '-':
sys.exit(
'Genbank ID BGC headers require an NT Catalog for annotation... see --help'
)
tid, organism = genbank_id_to_tid(gbk_id, nt_cat)
name = organism
else:
refseqid = '_'.join(bgc.split('_')[:2])
name = refseq_to_name(refseqid, db=db, nt=nt)
if typetable is not False:
ctype = typetable.filter(like=bgc, axis=0)
ctype = str(ctype.iloc[0, 0])
else:
ctype = 'NA'
if bgc == name:
name_dict[bgc] = [ctype, refseqid]
else:
name_dict[bgc] = [ctype, name]
ofu_file = ''.join(['ofu', ofu_n, '_id', cut_h, '.txt'])
with open(os.path.join(outpath, ofu_file), 'w') as outf:
outdf = pd.DataFrame.from_dict(name_dict, orient='index')
outdf.columns = ['predicted_type', 'organism']
outdf.to_csv(outf, sep='\t')
i += 1
print('\nOrganism information for %d OFUs written to file.\n' % i)
return bgc_dd
def genbank_id_to_tid(gbk_id, nt_cat): with open(nt_cat, 'r') as nt_catalog: reader = csv.reader(nt_catalog, delimiter='\t') next(reader) nt = NCBITree() gbk_set = set() gbk_set.add(gbk_id) for line in reader: if line[1] in gbk_set: tid = line[2] tid = int(tid) organism = nt.green_genes_lineage(tid, depth=8, depth_force=True) else: tid, organism = 'na', 'k__None;p__None;c__None;o__None;f__None;g__None;s__None;t__None' return tid, organism
def refseq_to_name(refseq_id, db=RefSeqDatabase(), nt=NCBITree()):
ncbi_tid = db.get_ncbi_tid_from_refseq_accession(refseq_id)
if ncbi_tid:
ncbi_tid = ncbi_tid[0]
organism = nt.green_genes_lineage(ncbi_tid, depth=8, depth_force=True)
else:
organism = refseq_id # if DOJO fails to find the tid, just return the refseq accession ID.
return organism
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 main():
parser = make_arg_parser()
args = parser.parse_args()
db = RefSeqDatabase()
nt = NCBITree()
# parse command line
with open(args.output, 'w') if args.output != '-' else sys.stdout as outf:
if args.assembly != '-':
ncbi_tid = db.get_ncbi_tid_from_assembly_accession_version(args.assembly)[0]
elif args.refseq != '-':
ncbi_tid = db.get_ncbi_tid_from_refseq_accession(args.refseq)[0]
elif args.tid != '-':
ncbi_tid = int(args.tid)
organism = nt.green_genes_lineage(ncbi_tid)
# genus_species = organism.split(';')[-1]
# genus_species = genus_species.replace('s__','')
outf.write('>ncbi_tid|%d|organism|%s\n' % (ncbi_tid, organism))
outf.write('\n')
def list_organism_ofus(orgs, nt_cat, hclus, height, outpath):
bgc_dd = defaultdict(list)
for value, key in hclus.itertuples(index=True):
key = str('%05d' % key)
key = ''.join(['ofu', key])
bgc_dd[key].extend(list([value]))
orgs_list = orgs.split(',')
i = len(orgs_list)
ofu_dict = defaultdict(list)
# Preload the Database and Tree
db = RefSeqDatabase()
nt = NCBITree()
for org in orgs_list:
# print(org)
org_ofu_dup = []
for ofu_num, ofu_orgs in bgc_dd.items():
for ofu_org in ofu_orgs:
if org in ofu_org:
if org.startswith('BGC'):
name = org
else:
name = identify_organism(org, nt_cat, db=db, nt=nt)
if ofu_num not in org_ofu_dup:
org_ofu_dup.append(ofu_num)
ofu_dict[name].extend([ofu_num])
else:
continue
height = str(height)
ofu_file = ''.join(['OFUs_from_similarity_level', height, '.txt'])
outdf = pd.DataFrame.from_dict(ofu_dict, orient='index')
if not outdf.empty:
with open(os.path.join(outpath, ofu_file), 'w') as outf:
outdf.to_csv(outf, sep='\t', header=False)
print(
'\nOFU assigments written to file for the %d organism ID entries given.\n'
% i)
else:
print(
'\nNo OFU assignments found; check RefSeq / Genbank / MIBiG identifier and format'
)
return ofu_dict
def tid_to_name(ncbi_tid, nt=NCBITree()):
organism = nt.green_genes_lineage(ncbi_tid, depth=8, depth_force=True)
return organism
def main():
parser = make_arg_parser()
args = parser.parse_args()
if os.getcwd().split('/')[-1] == 'antismash_results':
for rdir in os.listdir('.'):
if rdir.startswith('GCF'):
parse_products(rdir)
else:
pass
else:
print(
'\nNOTE:\nProgram may fail if you are not in a proper antismash_results directory\n'
)
for rdir in os.listdir('.'):
if rdir.startswith('GCF'):
parse_products(rdir)
else:
pass
if args.compile:
if "compiled_cluster_types" not in os.listdir('.'):
os.mkdir("compiled_cluster_types")
outfilename = 'compiled_cluster_types.csv'
with open(os.path.join("compiled_cluster_types", outfilename),
'w') as outf:
for cdir in os.listdir('.'):
if cdir.startswith('GCF'):
if "cluster_types" not in os.listdir(cdir):
pass
else:
outf = compile_types(cdir, outf)
outf.close()
if args.annotate:
if not args.compile:
print(
'\nSORRY:\nAnnotation only available with compiled option (-c)\n'
)
quit()
else:
# Preload the Database and Tree
db = RefSeqDatabase()
nt = NCBITree()
strain_label = []
with open(
os.path.join('compiled_cluster_types',
'compiled_cluster_types.csv')) as intab:
odf = pd.read_csv(intab, index_col=0, header=None)
refseq_list = list(odf.index)
for refseq_id in refseq_list:
organism = refseq_to_name(refseq_id, db=db, nt=nt)
ncbi_tid = refseq_to_tid(refseq_id, db=db)
ncbi_tid = str(ncbi_tid)
# genus_species = organism.split(';')[-1]
# genus_species = genus_species.replace('s__', '')
if ncbi_tid == organism: # sometimes DOJO can't look up the refseq accession; in this case, just return refseq.
strain_label.append(refseq_id)
else:
strain_label.append('ncbi_tid|%s|ref|%s|organism|%s' %
(ncbi_tid, refseq_id, organism))
odf.index = strain_label
odf.columns = ['cluster_type']
an_outn = 'annotated_cluster_types.csv'
with open(os.path.join('compiled_cluster_types', an_outn),
'w') as an_outf:
odf.to_csv(an_outf)
else:
pass
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 main():
parser = make_arg_parser()
args = parser.parse_args()
# Parse command line
method = args.method
height = 1 - (args.height / 100)
with open(args.input, 'r') as inf:
if args.clusterme:
print('...performing hierarchical clustering, tree cut at height of %s...\n' % args.height)
hclus = process_hierarchy(inf, height, method)
else:
hclus = pd.read_csv(inf, sep=',', header=0, index_col=0)
size = hclus.max(0)[0] # get the total number of clustered OFUs (depends on height cut)
print('\n...Preparing OFU profile for %s OFUs...\n' % size)
size += 1
fill = outer(size)
dd = defaultdict(fill) # Initialize the dict with all zeros
# Collapse into an OFU reference table, strains vs OFUs
if args.clusterme:
hclus.to_csv('hcsv_temp.csv')
with open('hcsv_temp.csv', 'r') as inf2:
df = cluster_ofus(inf2, dd)
else:
with open(args.input, 'r') as inf2:
df = cluster_ofus(inf2, dd)
j = 0
k = 0
if args.annotate:
# Preload the Database and Tree
db = RefSeqDatabase()
nt = NCBITree()
strain_label = []
refseq_list = list(df.index)
for refseq_id in refseq_list:
if refseq_id.startswith('ncbi_tid'):
ncbi_tid = refseq_id.split('|')[1]
if ncbi_tid == 'na':
genbank = '|'.join(refseq_id.split('_')[1].split('|')[2:4])
j += 1
else:
ncbi_tid = int(ncbi_tid)
organism = nt.green_genes_lineage(ncbi_tid, depth=8, depth_force=True)
if organism == 'k__;p__;c__;o__;f__;g__;s__;t__' and ncbi_tid != 'na':
strain_label.append('|'.join(['ncbi_tid', str(ncbi_tid)]))
k += 1
elif ncbi_tid == 'na':
strain_label.append(genbank)
else:
strain_label.append(organism)
else:
# TODO: Finish the regex for refseq id
# p = re.compile(r"N\w\_[\w+\d+]*\.\d")
# m = p.search(refseq_id) # searches using the regex defined above
# refseq_id_extract = ''.join(m)
organism = refseq_to_name(refseq_id, db=db, nt=nt)
ncbi_tid = refseq_to_tid(refseq_id, db=db)
ncbi_tid = str(ncbi_tid)
if args.taxonomy:
if ncbi_tid == organism: # sometimes DOJO can't look up the refseq accession; in this case, just return refseq.
strain_label.append(refseq_id)
else:
strain_label.append(organism)
elif args.ncbitid:
if ncbi_tid == organism: # sometimes DOJO can't look up the refseq accession; in this case, just return refseq.
strain_label.append(refseq_id)
else:
strain_label.append(ncbi_tid)
else:
if ncbi_tid == organism: # sometimes DOJO can't look up the refseq accession; in this case, just return refseq.
strain_label.append(refseq_id)
elif organism.endswith('None') or organism.endswith('t__'):
genus_species = organism.split(';')[-2]
# genus_species = genus_species.strip('s__')
strain_label.append('ncbi_tid|%s|ref|%s|organism|%s' % (ncbi_tid, refseq_id, genus_species))
else:
strain = organism.split(';')[-1]
# strain = strain.strip('t__')
strain_label.append('ncbi_tid|%s|ref|%s|organism|%s' % (ncbi_tid, refseq_id, strain))
df.index = strain_label
df.sort_index(axis=0, inplace=True)
if j > 0 or k > 0:
print('Note: Organism information was not obtained for all clusters:\n')
if j > 0:
print('%s clusters had no NCBI tid...\n' % j)
if k > 0:
print('%s clusters did not match a full named taxonomy annotation\n' % k)
else:
pass
with open(args.output, 'w') if args.output != '-' else sys.stdout as outf:
df.to_csv(outf)
print('...all done, cleaning up...\n')
os.remove('hcsv_temp.csv')