def contigs(args):
step_list = []
(contigs_fasta, database_folder, taxonomy_folder, r, one_minus_r, f,
out_prefix, predicted_proteins_fasta, diamond_file, path_to_prodigal,
path_to_diamond, no_stars, force, quiet, no_log, nproc, sensitive,
block_size, index_chunks, tmpdir, top) = check.convert_arguments(args)
if no_log:
log_file = None
else:
# Check out_prefix already as the log file needs to be written to a
# valid location.
error = check.check_out_prefix(out_prefix, None, quiet)
if error:
sys.exit(1)
log_file = '{0}.log'.format(out_prefix)
with open(log_file, 'w') as outf1:
pass
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message, log_file, quiet, show_time=False)
# Check at which state to start.
if predicted_proteins_fasta is None and diamond_file is None:
message = ('\n'
'CAT is running. Protein prediction, alignment, and contig '
'classification are carried out.\n'
'Rarw!\n\n'
'Supplied command: {0}\n\n'
'Contigs fasta: {1}\n'
'Taxonomy folder: {2}/\n'
'Database folder: {3}/\n'
'Parameter r: {4}\n'
'Parameter f: {5}\n'
'Log file: {6}\n\n'
'-----------------\n'.format(' '.join(sys.argv),
contigs_fasta, taxonomy_folder,
database_folder, args.r,
args.f, log_file))
shared.give_user_feedback(message, log_file, quiet, show_time=False)
step_list.append('run_prodigal')
step_list.append('run_diamond')
elif (predicted_proteins_fasta is not None and diamond_file is None):
message = ('\n'
'CAT is running. Since a predicted protein fasta is '
'supplied, only alignment and contig classification are '
'carried out.\n'
'Rarw!\n\n'
'Supplied command: {0}\n\n'
'Contigs fasta: {1}\n'
'Taxonomy folder: {2}/\n'
'Database folder: {3}/\n'
'Parameter r: {4}\n'
'Parameter f: {5}\n'
'Log file: {6}\n\n'
'-----------------\n'.format(' '.join(sys.argv),
contigs_fasta, taxonomy_folder,
database_folder, args.r,
args.f, log_file))
shared.give_user_feedback(message, log_file, quiet, show_time=False)
step_list.append('run_diamond')
elif (predicted_proteins_fasta is not None and diamond_file is not None):
message = ('\n'
'CAT is running. Since a predicted protein fasta and '
'DIAMOND alignment file are supplied, only contig '
'classification is carried out.\n'
'Rarw!\n\n'
'Supplied command: {0}\n\n'
'Contigs fasta: {1}\n'
'Taxonomy folder: {2}/\n'
'Database folder: {3}/\n'
'Parameter r: {4}\n'
'Parameter f: {5}\n'
'Log file: {6}\n\n'
'-----------------\n'.format(' '.join(sys.argv),
contigs_fasta, taxonomy_folder,
database_folder, args.r,
args.f, log_file))
shared.give_user_feedback(message, log_file, quiet, show_time=False)
elif (predicted_proteins_fasta is None and diamond_file is not None):
message = ('ERROR: if you want CAT to directly do the classification, '
'you should not only supply a DIAMOND alignment table but '
'also a predicted protein fasta file with argument '
'[-p / --proteins].')
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
# Check binaries, output files, taxonomy folder and database folder, and
# set parameters.
message = 'Doing some pre-flight checks first.'
shared.give_user_feedback(message, log_file, quiet, show_time=False)
errors = []
errors.append(check.check_out_prefix(out_prefix, log_file, quiet))
if 'run_prodigal' in step_list:
errors.append(
check.check_prodigal_binaries(path_to_prodigal, log_file, quiet))
predicted_proteins_fasta = ('{0}.predicted_proteins.faa'
''.format(out_prefix))
predicted_proteins_gff = ('{0}.predicted_proteins.gff'
''.format(out_prefix))
if not force:
errors.append(
check.check_output_file(predicted_proteins_fasta, log_file,
quiet))
errors.append(
check.check_output_file(predicted_proteins_gff, log_file,
quiet))
if 'run_diamond' in step_list:
errors.append(
check.check_diamond_binaries(path_to_diamond, log_file, quiet))
diamond_file = '{0}.alignment.diamond'.format(out_prefix)
if not force:
errors.append(
check.check_output_file(diamond_file, log_file, quiet))
else:
diamond_file = diamond_file
errors.append(
check.check_folders_for_run(taxonomy_folder, database_folder,
step_list, log_file, quiet))
contig2classification_output_file = ('{0}.contig2classification.txt'
''.format(out_prefix))
ORF2LCA_output_file = '{0}.ORF2LCA.txt'.format(out_prefix)
if not force:
errors.append(
check.check_output_file(contig2classification_output_file,
log_file, quiet))
errors.append(
check.check_output_file(ORF2LCA_output_file, log_file, quiet))
if 'run_prodigal' not in step_list:
if not check.check_whether_file_is_fasta(predicted_proteins_fasta):
message = ('ERROR: {0} is not a fasta file.'
''.format(predicted_proteins_fasta))
shared.give_user_feedback(message, log_file, quiet, error=True)
errors.append(True)
errors.append(check.check_top(top, r, log_file, quiet))
if True in errors:
sys.exit(1)
(nodes_dmp, names_dmp, prot_accession2taxid_file
) = check.inspect_taxonomy_folder(taxonomy_folder)
(nr_file, diamond_database, fastaid2LCAtaxid_file,
taxids_with_multiple_offspring_file
) = check.inspect_database_folder(database_folder)
message = 'Ready to fly!\n\n-----------------\n'
shared.give_user_feedback(message, log_file, quiet, show_time=False)
# Start CAT.
contig_names = shared.import_contig_names(contigs_fasta, log_file, quiet)
if 'run_prodigal' in step_list:
shared.run_prodigal(path_to_prodigal, contigs_fasta,
predicted_proteins_fasta, predicted_proteins_gff,
log_file, quiet)
contig2ORFs = shared.import_ORFs(predicted_proteins_fasta, log_file, quiet)
check.check_whether_ORFs_are_based_on_contigs(contig_names, contig2ORFs,
log_file, quiet)
if 'run_diamond' in step_list:
shared.run_diamond(path_to_diamond, diamond_database,
predicted_proteins_fasta, diamond_file, nproc,
sensitive, block_size, index_chunks, tmpdir, top,
log_file, quiet)
(ORF2hits, all_hits) = shared.parse_diamond_file(diamond_file, one_minus_r,
log_file, quiet)
(taxid2parent, taxid2rank) = tax.import_nodes(nodes_dmp, log_file, quiet)
fastaid2LCAtaxid = tax.import_fastaid2LCAtaxid(fastaid2LCAtaxid_file,
all_hits, log_file, quiet)
taxids_with_multiple_offspring = tax.import_taxids_with_multiple_offspring(
taxids_with_multiple_offspring_file, log_file, quiet)
message = ('CAT is spinning! Files {0} and {1} are created.'
''.format(contig2classification_output_file,
ORF2LCA_output_file))
shared.give_user_feedback(message, log_file, quiet)
number_of_classified_contigs = 0
with open(contig2classification_output_file,
'w') as outf1, open(ORF2LCA_output_file, 'w') as outf2:
outf1.write('# contig\tclassification\treason\tlineage\t'
'lineage scores\n')
outf2.write('# ORF\tlineage\tbit-score\n')
for contig in sorted(contig_names):
if contig not in contig2ORFs:
outf1.write('{0}\tunclassified\tno ORFs found\n'
''.format(contig))
continue
LCAs_ORFs = []
for ORF in contig2ORFs[contig]:
if ORF not in ORF2hits:
outf2.write('{0}\tORF has no hit to database\n'
''.format(ORF))
continue
(taxid,
top_bitscore) = tax.find_LCA_for_ORF(ORF2hits[ORF],
fastaid2LCAtaxid,
taxid2parent)
if taxid.startswith('no taxid found'):
outf2.write('{0}\t{1}\t{2}\n'.format(
ORF, taxid, top_bitscore))
else:
lineage = tax.find_lineage(taxid, taxid2parent)
if not no_stars:
lineage = tax.star_lineage(
lineage, taxids_with_multiple_offspring)
outf2.write('{0}\t{1}\t{2}\n'
''.format(ORF, ';'.join(lineage[::-1]),
top_bitscore))
LCAs_ORFs.append((taxid, top_bitscore), )
if len(LCAs_ORFs) == 0:
outf1.write('{0}\tunclassified\tno hits to database\n'
''.format(contig))
continue
(lineages, lineages_scores,
based_on_number_of_ORFs) = tax.find_weighted_LCA(
LCAs_ORFs, taxid2parent, f)
if lineages == 'no ORFs with taxids found.':
outf1.write('{0}\tunclassified\t'
'hits not found in taxonomy files\n'
''.format(contig))
continue
if lineages == 'no lineage whitelisted.':
outf1.write('{0}\tunclassified\t'
'no lineage reached minimum bit-score support\n'
''.format(contig))
continue
# The contig has a valid classification.
number_of_classified_contigs += 1
for (i, lineage) in enumerate(lineages):
if not no_stars:
lineage = tax.star_lineage(lineage,
taxids_with_multiple_offspring)
scores = [
'{0:.2f}'.format(score) for score in lineages_scores[i]
]
if len(lineages) == 1:
# There is only one classification.
outf1.write('{0}\tclassified\t'
'based on {1}/{2} ORFs\t{3}\t{4}\n'
''.format(contig, based_on_number_of_ORFs,
len(contig2ORFs[contig]),
';'.join(lineage[::-1]),
';'.join(scores[::-1])))
else:
# There are multiple classifications.
outf1.write('{0}\tclassified ({1}/{2})\t'
'based on {3}/{4} ORFs\t{5}\t{6}\n'
''.format(contig, i + 1, len(lineages),
based_on_number_of_ORFs,
len(contig2ORFs[contig]),
';'.join(lineage[::-1]),
';'.join(scores[::-1])))
message = ('\n-----------------\n\n'
'[{0}] CAT is done! {1}/{2} contigs classified.'
''.format(datetime.datetime.now(), number_of_classified_contigs,
len(contig_names)))
shared.give_user_feedback(message, log_file, quiet, show_time=False)
if f < 0.5:
message = ('\nWARNING: since f is set to smaller than 0.5, one '
'contig may have multiple classifications.')
shared.give_user_feedback(message, log_file, quiet, show_time=False)
def summarise_contigs(args):
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message,
args.log_file,
args.quiet,
show_time=False)
errors = []
errors.append(
check.check_input_file(args.input_file, args.log_file, args.quiet))
if not args.force:
errors.append(
check.check_output_file(args.output_file, args.log_file,
args.quiet))
if True in errors:
sys.exit(1)
contig2length = import_contig_lengths(args.contigs_fasta, args.log_file,
args.quiet)
message = 'Summarising...'
shared.give_user_feedback(message, args.log_file, args.quiet)
with open(args.input_file, 'r') as f1:
for line in f1:
if line.startswith('#'):
line = line.split('\t')
if line[0] != '# contig':
message = '{0} is not a CAT classification file.'.format(
args.input_file)
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
if line[0] == '# bin':
message = (
'{0} appears to be a BAT classification file. '
'If you want to summarise bin '
'classifications, simply don\'t supply a '
'contigs fasta and everything should be fine.'
''.format(args.input_file))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
try:
superkingdom_index = line.index('superkingdom')
except:
message = (
'official ranks not found in header of {0}. Make '
'sure that the CAT classification file is named '
'with official ranks with \'CAT add_names '
'--only_official\'.'.format(args.input_file))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
break
else:
message = 'input file does not have a recognisable header.'
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
length = {}
length['no taxid assigned'] = []
ORFs = {}
official_ranks = [
'superkingdom', 'phylum', 'class', 'order', 'family', 'genus',
'species'
]
for rank in official_ranks:
length[rank] = {}
ORFs[rank] = {}
n = 0
contig_trace = set()
doubles = set()
with open(args.input_file, 'r') as f1:
for line in f1:
line = line.rstrip()
if line.startswith('#'):
continue
n += 1
line = line.split('\t')
contig = line[0]
if contig in contig_trace:
doubles.add(contig)
contig_trace.add(contig)
if contig not in contig2length:
message = (
'contig {0} in CAT classification file is not found '
'in supplied contigs fasta file. Are you sure the CAT '
'classification file is based on the contigs fasta?'
''.format(contig))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
if line[1] == 'no taxid assigned':
length['no taxid assigned'].append(contig2length[contig])
continue
for (i, classification) in enumerate(line[superkingdom_index:]):
classification = classification.rsplit(': ', 1)[0].rstrip('*')
rank = official_ranks[i]
if classification not in length[rank]:
length[rank][classification] = []
ORFs[rank][classification] = []
length[rank][classification].append(contig2length[contig])
# NOTE that the total number of ORFs on a contig is reproted,
# not only the number of ORFs a classification is based on.
ORFs_on_contig = int(line[2].split('/')[1].split(' ')[0])
ORFs[rank][classification].append(ORFs_on_contig)
if len(doubles) != 0:
message = ('some contigs have multiple classifications. CAT summarise '
'currently does not allow for this. Contigs with multiple '
'classifications: {0}.'.format(', '.join(list(doubles))))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
if n != len(contig2length):
message = ('the number of classified contigs is not the same as the '
'number of contigs in contigs fasta. Are you sure the CAT '
'classification file is based on the contigs fasta?')
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
with open(args.output_file, 'w') as outf1:
n_contigs = len(contig2length)
total_length = sum(contig2length.values())
n_classified_contigs = n_contigs - len(length['no taxid assigned'])
total_classified_length = total_length - sum(
length['no taxid assigned'])
outf1.write('# total number of contigs in {0} is {1:,d} representing '
'{2:,d} positions.\n'.format(args.contigs_fasta, n_contigs,
total_length))
outf1.write(
'# {0:,d} contigs have taxonomy assigned ({1:.2f}%) '
'representing {2:,d} positions ({3:.2f}%) in {4}.\n'.format(
n_classified_contigs, n_classified_contigs / n_contigs * 100,
total_classified_length,
total_classified_length / total_length * 100, args.input_file))
outf1.write('#\n')
outf1.write('# rank\t'
'clade\t'
'number of contigs\t'
'number of ORFs\t'
'number of positions\n')
for rank in official_ranks:
for clade in sorted(length[rank],
key=lambda x: sum(length[rank][x]),
reverse=True):
outf1.write('{0}\t{1}\t{2}\t{3}\t{4}\n'.format(
rank, clade, len(length[rank][clade]),
sum(ORFs[rank][clade]), sum(length[rank][clade])))
message = '{0} is created!'.format(args.output_file)
shared.give_user_feedback(message, args.log_file, args.quiet)
return
def summarise_bins(args):
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message,
args.log_file,
args.quiet,
show_time=False)
errors = []
errors.append(
check.check_input_file(args.input_file, args.log_file, args.quiet))
if not args.force:
errors.append(
check.check_output_file(args.output_file, args.log_file,
args.quiet))
if True in errors:
sys.exit(1)
message = 'Summarising...'
shared.give_user_feedback(message, args.log_file, args.quiet)
with open(args.input_file, 'r') as f1:
for line in f1:
if line.startswith('#'):
line = line.split('\t')
if line[0] != '# bin':
message = '{0} is not a BAT classification file.'.format(
args.input_file)
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
if line[0] == '# contig':
message = (
'{0} appears to be a CAT classification file. '
'If you want to summarise contig '
'classifications, supply a contigs fasta with '
'argument [-c / --contigs_fasta].'.format(
args.input_file))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
try:
superkingdom_index = line.index('superkingdom')
except:
message = (
'official ranks not found in header of {0}. Make '
'sure that the BAT classification file is named '
'with official ranks with \'CAT add_names '
'--only_official\'.'.format(args.input_file))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
break
else:
message = 'input file does not have a recognisable header.'
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
n_bins = {}
n_bins['no taxid assigned'] = 0
official_ranks = [
'superkingdom', 'phylum', 'class', 'order', 'family', 'genus',
'species'
]
for rank in official_ranks:
n_bins[rank] = {}
n = 0
bin_trace = set()
doubles = set()
with open(args.input_file, 'r') as f1:
for line in f1:
line = line.rstrip()
if line.startswith('#'):
continue
n += 1
line = line.split('\t')
bin_ = line[0]
if bin_ in bin_trace:
doubles.add(bin_)
bin_trace.add(bin_)
if line[1] == 'no taxid assigned':
n_bins['no taxid assigned'] += 1
continue
for (i, classification) in enumerate(line[superkingdom_index:]):
classification = classification.rsplit(': ', 1)[0].rstrip('*')
rank = official_ranks[i]
if classification not in n_bins[rank]:
n_bins[rank][classification] = 0
n_bins[rank][classification] += 1
if len(doubles) != 0:
message = ('some bins have multiple classifications. CAT summarise '
'currently does not allow for this. Bins with multiple '
'classifications: {0}.'.format(', '.join(list(doubles))))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
n_classified_bins = n - n_bins['no taxid assigned']
with open(args.output_file, 'w') as outf1:
outf1.write('# total number of bins is {0:,d}, of which {1:,d} '
'({2:.2f}%) have taxonomy assigned.\n'.format(
n, n_classified_bins, n_classified_bins / n * 100))
outf1.write('#\n')
outf1.write('# rank\tclade\tnumber of bins\n')
for rank in official_ranks:
for clade in sorted(n_bins[rank],
key=lambda x: n_bins[rank][x],
reverse=True):
outf1.write('{0}\t{1}\t{2}\n'.format(rank, clade,
n_bins[rank][clade]))
message = '{0} is created!'.format(args.output_file)
shared.give_user_feedback(message, args.log_file, args.quiet)
return
def run():
args = parse_arguments()
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message,
args.log_file,
args.quiet,
show_time=False)
errors = []
errors.append(
check.check_input_file(args.input_file, args.log_file, args.quiet))
if not args.force:
errors.append(
check.check_output_file(args.output_file, args.log_file,
args.quiet))
if True in errors:
sys.exit(1)
(taxid2parent, taxid2rank) = tax.import_nodes(args.nodes_dmp,
args.log_file, args.quiet)
taxid2name = tax.import_names(args.names_dmp, args.log_file, args.quiet)
message = 'Appending names...'
shared.give_user_feedback(message, args.log_file, args.quiet)
with open(args.input_file, 'r') as f1:
for line in f1:
if line.startswith('#'):
line = line.rstrip().split('\t')
if 'lineage' in line:
lineage_index = line.index('lineage')
else:
message = ('{0} is not a supported classification file.'
''.format(input_file))
shared.give_user_feedback(message,
args.log_file,
args.quiet,
error=True)
sys.exit(1)
try:
scores_index = line.index('lineage scores')
except:
scores_index = None
full_length = len(line)
break
else:
message = ('{0} is not a supported classification file.'.format(
args.input_file))
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
with open(args.input_file, 'r') as f1, open(args.output_file,
'w') as outf1:
for line in f1:
line = line.rstrip()
if line.startswith('#'):
if args.only_official:
outf1.write('{0}\tsuperkingdom\tphylum\tclass\torder\t'
'family\tgenus\tspecies\n'.format(line))
else:
outf1.write('{0}\tfull lineage names\n'.format(line))
continue
line = line.split('\t')
if len(line) != full_length:
# Entry does not have a full annotation.
outf1.write('{0}\n'.format('\t'.join(line)))
continue
if (line[1].startswith('no taxid found')
or line[2].startswith('no taxid found')):
# ORF has database hits but the accession number is not found
# in the taxonomy files.
outf1.write('{0}\n'.format('\t'.join(line)))
continue
lineage = line[lineage_index].split(';')
if scores_index is not None and not args.exclude_scores:
scores = line[scores_index].split(';')
else:
scores = None
if args.only_official:
names = tax.convert_to_official_names(lineage, taxid2rank,
taxid2name, scores)
else:
names = tax.convert_to_names(lineage, taxid2rank, taxid2name,
scores)
outf1.write('{0}\t{1}\n'.format('\t'.join(line), '\t'.join(names)))
message = 'Names written to {0}!'.format(args.output_file)
shared.give_user_feedback(message, args.log_file, args.quiet)
return
def summarise_bins(input_file, output_file, force, quiet):
# Currently summarise does not a allow for a log file.
log_file = None
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message, log_file, quiet, show_time=False)
errors = []
errors.append(check.check_input_file(input_file, log_file, quiet))
if not force:
errors.append(check.check_output_file(output_file, log_file, quiet))
if True in errors:
sys.exit(1)
message = 'Summarising...'
shared.give_user_feedback(message, log_file, quiet)
with shared.open_maybe_gzip(input_file, 'rt') as f1:
for line in f1:
if line.startswith('#'):
line = line.split('\t')
if line[0] != '# bin':
message = ('ERROR: {0} is not a BAT classification file.'
''.format(input_file))
shared.give_user_feedback(message,
log_file,
quiet,
error=True)
if line[0] == '# contig':
message = ('ERROR: {0} appears to be a CAT '
'classification file. If you want to '
'summarise contig classifications, please '
'supply a contigs fasta.'
''.format(input_file))
shared.give_user_feedback(message,
log_file,
quiet,
error=True)
sys.exit(1)
try:
superkingdom_index = line.index('superkingdom')
except:
message = ('ERROR: official ranks not found in header of '
'{0}. Make sure that the BAT classification '
'file is named with official ranks with \'CAT '
'add_names --only_official\'.'
''.format(input_file))
shared.give_user_feedback(message,
log_file,
quiet,
error=True)
sys.exit(1)
break
else:
message = 'ERROR: input file does not have a recognisable header.'
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
number_of_bins = {}
number_of_bins['unclassified'] = 0
official_ranks = [
'superkingdom', 'phylum', 'class', 'order', 'family', 'genus',
'species'
]
for rank in official_ranks:
number_of_bins[rank] = {}
n = 0
bin_trace = set()
doubles = set()
with open(input_file, 'r') as f1:
for line in f1:
line = line.rstrip()
if line.startswith('#'):
continue
n += 1
line = line.split('\t')
bin_ = line[0]
if bin_ in bin_trace:
doubles.add(bin_)
bin_trace.add(bin_)
if line[1] == 'unclassified':
number_of_bins['unclassified'] += 1
continue
for (i, classification) in enumerate(line[superkingdom_index:]):
classification = classification.rsplit(': ', 1)[0].rstrip('*')
rank = official_ranks[i]
if classification not in number_of_bins[rank]:
number_of_bins[rank][classification] = 0
number_of_bins[rank][classification] += 1
if len(doubles) != 0:
message = ('ERROR: some bins have multiple classifications. CAT '
'summarise currently does not allow for this. Bins with '
'multiple classifications: {0}.'
''.format(', '.join(list(doubles))))
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
number_of_classified_bins = n - number_of_bins['unclassified']
with shared.open_maybe_gzip(output_file, 'wt') as outf1:
outf1.write('# total number of bins is {0}, of which {1} ({2:.2f}%) '
'are classified.\n'
''.format(n, number_of_classified_bins,
number_of_classified_bins / n * 100))
outf1.write('#\n')
outf1.write('# rank\tclade\tnumber of bins\n')
for rank in official_ranks:
for clade in sorted(number_of_bins[rank],
key=lambda x: number_of_bins[rank][x],
reverse=True):
outf1.write('{0}\t{1}\t{2}\n'
''.format(rank, clade,
number_of_bins[rank][clade]))
message = '{0} is created!'.format(output_file)
shared.give_user_feedback(message, log_file, quiet)
def add_names(args):
(input_file, output_file, taxonomy_folder, only_official, exclude_scores,
force, quiet) = check.convert_arguments(args)
# Currently add_names does not allow for a log file.
log_file = None
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message, log_file, quiet, show_time=False)
errors = []
errors.append(check.check_input_file(input_file, log_file, quiet))
if not force:
errors.append(check.check_output_file(output_file, log_file, quiet))
if True in errors:
sys.exit(1)
(nodes_dmp, names_dmp, prot_accession2taxid_file
) = check.inspect_taxonomy_folder(taxonomy_folder)
(taxid2parent, taxid2rank) = tax.import_nodes(nodes_dmp, log_file, quiet)
taxid2name = tax.import_names(names_dmp, log_file, quiet)
message = 'Appending names...'
shared.give_user_feedback(message, log_file, quiet)
with shared.open_maybe_gzip(input_file, 'rt') as f1:
for line in f1:
if line.startswith('#'):
line = line.rstrip().split('\t')
try:
lineage_index = line.index('lineage')
except:
message = ('ERROR: {0} is not a supported classification '
'file.'.format(input_file))
shared.give_user_feedback(message,
log_file,
quiet,
error=True)
sys.exit(1)
try:
scores_index = line.index('lineage scores')
except:
scores_index = None
full_length = len(line)
break
else:
message = ('ERROR: {0} is not a supported classification file.'
''.format(input_file))
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
with shared.open_maybe_gzip(input_file,
'rt') as f1, shared.open_maybe_gzip(
output_file, 'wt') as outf1:
for line in f1:
line = line.rstrip()
if line.startswith('#'):
if only_official:
outf1.write('{0}\tsuperkingdom\tphylum\tclass\torder\t'
'family\tgenus\tspecies\n'.format(line))
else:
outf1.write('{0}\tfull lineage names\n'.format(line))
continue
line = line.split('\t')
if len(line) != full_length:
# Entry does not have a full annotation.
outf1.write('{0}\n'.format('\t'.join(line)))
continue
if (line[1].startswith('no taxid found')
or line[2].startswith('no taxid found')):
# ORF has database hits but the accession number is not found
# in the taxonomy files.
outf1.write('{0}\n'.format('\t'.join(line)))
continue
lineage = line[lineage_index].split(';')
if scores_index and not exclude_scores:
scores = line[scores_index].split(';')
else:
scores = None
if only_official:
names = tax.convert_to_official_names(lineage, taxid2rank,
taxid2name, scores)
else:
names = tax.convert_to_names(lineage, taxid2rank, taxid2name,
scores)
outf1.write('{0}\t{1}\n'.format('\t'.join(line), '\t'.join(names)))
message = 'Names written to {0}!'.format(output_file)
shared.give_user_feedback(message, log_file, quiet)
def run():
args = parse_arguments()
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
# Check at which state to start.
step_list = []
if not args.proteins_fasta and not args.alignment_file:
message = (
'\n'
'BAT is running. Protein prediction, alignment, and bin '
'classification are carried out.')
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
step_list.append('predict_proteins')
step_list.append('align')
elif args.proteins_fasta and not args.alignment_file:
message = (
'\n'
'BAT is running. Since a predicted protein fasta is supplied, '
'only alignment and bin classification are carried out.')
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
step_list.append('align')
elif args.proteins_fasta and args.alignment_file:
message = (
'\n'
'BAT is running. Since a predicted protein fasta and '
'alignment file are supplied, only bin classification is '
'carried out.')
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
elif not args.proteins_fasta and args.alignment_file:
message = (
'if you want BAT to directly classify a set of bins, you '
'should not only supply a DIAMOND alignment table but also a '
'concatenated predicted protein fasta file with argument '
'[-p / --proteins].')
shared.give_user_feedback(message, args.log_file, args.quiet,
error=True)
sys.exit(1)
step_list.append('classify')
# Print variables.
message = (
'Rarw!\n\n'
'Supplied command: {0}\n\n'
'Bin folder: {1}\n'
'Taxonomy folder: {2}\n'
'Database folder: {3}\n'
'Parameter r: {4}\n'
'Parameter f: {5}\n'
'Log file: {6}\n\n'
'-----------------\n'.format(
' '.join(sys.argv),
args.bin_folder,
args.taxonomy_folder,
args.database_folder,
int(args.r),
float(args.f),
args.log_file))
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
# Check binaries, output files, taxonomy folder and database folder, and
# set variables.
message = 'Doing some pre-flight checks first.'
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
errors = []
errors.append(
check.check_bin_folder(
args.bin_folder, args.bin_suffix, args.log_file, args.quiet))
errors.append(
check.check_out_prefix(args.out_prefix, args.log_file, args.quiet))
if 'predict_proteins' in step_list:
errors.append(
check.check_prodigal_binaries(
args.path_to_prodigal, args.log_file, args.quiet))
setattr(args,
'concatenated_fasta',
'{0}.concatenated.fasta'.format(args.out_prefix))
setattr(args,
'proteins_fasta',
'{0}.concatenated.predicted_proteins.faa'.format(
args.out_prefix))
setattr(args,
'proteins_gff',
'{0}.concatenated.predicted_proteins.gff'.format(
args.out_prefix))
if not args.force:
errors.append(
check.check_output_file(
args.concatenated_fasta, args.log_file, args.quiet))
errors.append(
check.check_output_file(
args.proteins_fasta, args.log_file, args.quiet))
errors.append(
check.check_output_file(
args.proteins_gff, args.log_file, args.quiet))
if 'align' in step_list:
errors.append(
check.check_diamond_binaries(
args.path_to_diamond, args.log_file, args.quiet))
setattr(args,
'alignment_file',
'{0}.concatenated.alignment.diamond'.format(args.out_prefix))
if not args.force:
errors.append(
check.check_output_file(
args.alignment_file, args.log_file, args.quiet))
errors.append(
check.check_folders_for_run(
args.taxonomy_folder,
args.nodes_dmp,
args.names_dmp,
args.database_folder,
args.diamond_database,
args.fastaid2LCAtaxid_file,
args.taxids_with_multiple_offspring_file,
step_list,
args.log_file,
args.quiet))
setattr(args,
'bin2classification_output_file',
'{0}.bin2classification.txt'.format(args.out_prefix))
setattr(args,
'ORF2LCA_output_file',
'{0}.ORF2LCA.txt'.format(args.out_prefix))
if not args.force:
errors.append(
check.check_output_file(
args.bin2classification_output_file,
args.log_file,
args.quiet))
errors.append(
check.check_output_file(
args.ORF2LCA_output_file, args.log_file, args.quiet))
if 'predict_proteins' not in step_list:
errors.append(
check.check_fasta(
args.proteins_fasta, args.log_file, args.quiet))
if 'align' in step_list:
errors.append(
check.check_top(args.top, args.r, args.log_file, args.quiet))
# Print all variables.
shared.print_variables(args, step_list)
if True in errors:
sys.exit(1)
message = 'Ready to fly!\n\n-----------------\n'
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
# Start BAT.
(bin2contigs, contig_names) = import_bins(
args.bin_folder, args.bin_suffix, args.log_file, args.quiet)
if 'predict_proteins' in step_list:
make_concatenated_fasta(
args.concatenated_fasta,
bin2contigs,
args.bin_folder,
args.log_file,
args.quiet)
shared.run_prodigal(
args.path_to_prodigal,
args.concatenated_fasta,
args.proteins_fasta,
args.proteins_gff,
args.log_file,
args.quiet)
contig2ORFs = shared.import_ORFs(
args.proteins_fasta, args.log_file, args.quiet)
check.check_whether_ORFs_are_based_on_contigs(
contig_names, contig2ORFs, args.log_file, args.quiet)
if 'align' in step_list:
shared.run_diamond(args)
(ORF2hits,
all_hits) = shared.parse_tabular_alignment(
args.alignment_file,
args.one_minus_r,
args.log_file,
args.quiet)
(taxid2parent,
taxid2rank) = tax.import_nodes(
args.nodes_dmp, args.log_file, args.quiet)
fastaid2LCAtaxid = tax.import_fastaid2LCAtaxid(
args.fastaid2LCAtaxid_file, all_hits, args.log_file, args.quiet)
taxids_with_multiple_offspring = tax.import_taxids_with_multiple_offspring(
args.taxids_with_multiple_offspring_file,
args.log_file,
args.quiet)
message = 'BAT is flying! Files {0} and {1} are created.'.format(
args.bin2classification_output_file, args.ORF2LCA_output_file)
shared.give_user_feedback(message, args.log_file, args.quiet)
n_classified_bins = 0
with open(args.bin2classification_output_file, 'w') as outf1, open(args.ORF2LCA_output_file, 'w') as outf2:
outf1.write('# bin\tclassification\treason\tlineage\tlineage scores\n')
outf2.write('# ORF\tbin\tnumber of hits\tlineage\ttop bit-score\n')
for bin_ in sorted(bin2contigs):
LCAs_ORFs = []
for contig in sorted(bin2contigs[bin_]):
if contig not in contig2ORFs:
continue
for ORF in contig2ORFs[contig]:
if ORF not in ORF2hits:
outf2.write('{0}\t{1}\tORF has no hit to database\n'
''.format(ORF, bin_))
continue
n_hits = len(ORF2hits[ORF])
(taxid,
top_bitscore) = tax.find_LCA_for_ORF(
ORF2hits[ORF],
fastaid2LCAtaxid,
taxid2parent)
if taxid.startswith('no taxid found'):
outf2.write('{0}\t{1}\t{2}\t{3}\t{4}\n'.format(
ORF, bin_, n_hits, taxid, top_bitscore))
else:
lineage = tax.find_lineage(taxid, taxid2parent)
if not args.no_stars:
lineage = tax.star_lineage(
lineage, taxids_with_multiple_offspring)
outf2.write('{0}\t{1}\t{2}\t{3}\t{4}\n'.format(
ORF,
bin_,
n_hits,
';'.join(lineage[::-1]),
top_bitscore))
LCAs_ORFs.append((taxid, top_bitscore),)
if len(LCAs_ORFs) == 0:
outf1.write('{0}\tno taxid assigned\tno hits to database\n'
''.format(bin_))
continue
(lineages,
lineages_scores,
based_on_n_ORFs) = tax.find_weighted_LCA(
LCAs_ORFs, taxid2parent, args.f)
if lineages == 'no ORFs with taxids found.':
outf1.write('{0}\tno taxid assigned\t'
'hits not found in taxonomy files\n'.format(bin_))
continue
if lineages == 'no lineage whitelisted.':
outf1.write(
'{0}\tno taxid assigned\t'
'no lineage reached minimum bit-score support\n'
''.format(bin_))
continue
# The bin has a valid classification.
n_classified_bins += 1
total_n_ORFs = sum([len(contig2ORFs[contig]) for
contig in bin2contigs[bin_] if contig in contig2ORFs])
for (i, lineage) in enumerate(lineages):
if not args.no_stars:
lineage = tax.star_lineage(
lineage, taxids_with_multiple_offspring)
scores = ['{0:.2f}'.format(score) for
score in lineages_scores[i]]
if len(lineages) == 1:
# There is only one classification.
outf1.write(
'{0}\t'
'taxid assigned\t'
'based on {1}/{2} ORFs\t'
'{3}\t'
'{4}\n'.format(
bin_,
based_on_n_ORFs,
total_n_ORFs,
';'.join(lineage[::-1]),
';'.join(scores[::-1])))
else:
# There are multiple classifications.
outf1.write(
'{0}\t'
'taxid assigned ({1}/{2})\t'
'based on {3}/{4} ORFs\t'
'{5}\t'
'{6}\n'.format(
bin_,
i + 1,
len(lineages),
based_on_n_ORFs,
total_n_ORFs,
';'.join(lineage[::-1]),
';'.join(scores[::-1])))
message = ('\n-----------------\n\n'
'{0} BAT is done! {1:,d}/{2:,d} bins have taxonomy assigned.'
''.format(shared.timestamp(), n_classified_bins, len(bin2contigs)))
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
if args.f < 0.5:
message = ('\nWARNING: since f is set to smaller than 0.5, one bin '
'may have multiple classifications.')
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
return
def summarise_contigs(input_file, output_file, contigs_fasta, force, quiet):
# Currently summarise does not a allow for a log file.
log_file = None
message = '# CAT v{0}.'.format(about.__version__)
shared.give_user_feedback(message, log_file, quiet, show_time=False)
errors = []
errors.append(check.check_input_file(input_file, log_file, quiet))
if not force:
errors.append(check.check_output_file(output_file, log_file, quiet))
if True in errors:
sys.exit(1)
contig2length = import_contig_lengths(contigs_fasta, log_file, quiet)
message = 'Summarising...'
shared.give_user_feedback(message, log_file, quiet)
with open(input_file, 'r') as f1:
for line in f1:
if line.startswith('#'):
line = line.split('\t')
if line[0] != '# contig':
message = ('ERROR: {0} is not a CAT classification file.'
''.format(input_file))
shared.give_user_feedback(message,
log_file,
quiet,
error=True)
if line[0] == '# bin':
message = ('ERROR: {0} appears to be a BAT '
'classification file. If you want to '
'summarise bin classifications, just '
'don\'t supply a contigs fasta and '
'everything should be fine!'
''.format(input_file))
shared.give_user_feedback(message,
log_file,
quiet,
error=True)
sys.exit(1)
try:
superkingdom_index = line.index('superkingdom')
except:
message = ('ERROR: official ranks not found in header of '
'{0}. Make sure that the CAT classification '
'file is named with official ranks with \'CAT '
'add_names --only_official\'.'
''.format(input_file))
shared.give_user_feedback(message,
log_file,
quiet,
error=True)
sys.exit(1)
break
else:
message = 'ERROR: input file does not have a recognisable header.'
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
length = {}
length['unclassified'] = []
ORFs = {}
official_ranks = ['superkingdom', 'phylum', 'class', 'order', 'family',
'genus', 'species']
for rank in official_ranks:
length[rank] = {}
ORFs[rank] = {}
n = 0
contig_trace = set()
doubles = set()
with open(input_file, 'r') as f1:
for line in f1:
line = line.rstrip()
if line.startswith('#'):
continue
n += 1
line = line.split('\t')
contig = line[0]
if contig in contig_trace:
doubles.add(contig)
contig_trace.add(contig)
if contig not in contig2length:
message = ('ERROR: contig {0} in CAT classification file is '
'not found in supplied contigs fasta file. Are you '
'sure the CAT classification file is based on the '
'contigs fasta?'.format(contig))
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
if line[1].startswith('unclassified'):
length['unclassified'].append(contig2length[contig])
continue
for (i, classification) in enumerate(line[superkingdom_index:]):
classification = classification.rsplit(': ', 1)[0].rstrip('*')
rank = official_ranks[i]
if classification not in length[rank]:
length[rank][classification] = []
ORFs[rank][classification] = []
length[rank][classification].append(contig2length[contig])
ORFs[rank][classification].append(int(line[2]))
if len(doubles) != 0:
message = ('ERROR: some contigs have multiple classifications. CAT '
'summarise currently does not allow for this. Contigs with '
'multiple classifications: {0}.'
''.format(', '.join(list(doubles))))
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
if n != len(contig2length):
message = ('ERROR: the number of classified contigs is not the same '
'as the number of contigs in contigs fasta. Are you sure '
'the CAT classification file is based on the contigs '
'fasta?')
shared.give_user_feedback(message, log_file, quiet, error=True)
sys.exit(1)
with open(output_file, 'w') as outf1:
number_of_contigs = len(contig2length)
total_length = sum(contig2length.values())
number_of_classified_contigs = number_of_contigs - len(length['unclassified'])
total_classified_length = total_length - sum(length['unclassified'])
outf1.write('# total number of contigs in {0} is {1} representing {2} '
'positions.\n'
''.format(contigs_fasta,
number_of_contigs,
total_length))
outf1.write('# {0} contigs are classified ({1:.2f}%) representing {2} '
'positions ({3:.2f}%) in {4}.\n'
''.format(number_of_classified_contigs,
number_of_classified_contigs / number_of_contigs * 100,
total_classified_length,
total_classified_length / total_length * 100,
input_file))
outf1.write('#\n')
outf1.write('# rank\t'
'clade\t'
'number of contigs\t'
'number of ORFs\t'
'number of positions\n')
for rank in official_ranks:
for clade in sorted(length[rank],
key=lambda x: sum(length[rank][x]),
reverse=True):
outf1.write('{0}\t{1}\t{2}\t{3}\t{4}\n'
''.format(rank,
clade,
len(length[rank][clade]),
sum(ORFs[rank][clade]),
sum(length[rank][clade])))
message = '{0} is created!'.format(output_file)
shared.give_user_feedback(message, log_file, quiet)
