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 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'
'CAT is running. Protein prediction, alignment, and contig '
'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'
'CAT is running. Since a predicted protein fasta is supplied, '
'only alignment and contig 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'
'CAT is running. Since a predicted protein fasta and '
'alignment file are supplied, only contig 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 CAT to directly do the classification, you '
'should not only supply an alignment table but also a '
'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'
'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),
args.contigs_fasta,
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_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,
'proteins_fasta',
'{0}.predicted_proteins.faa'.format(args.out_prefix))
setattr(args,
'proteins_gff',
'{0}.predicted_proteins.gff'.format(args.out_prefix))
if not args.force:
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}.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,
'contig2classification_output_file',
'{0}.contig2classification.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.contig2classification_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 CAT.
contig_names = shared.import_contig_names(
args.contigs_fasta, args.log_file, args.quiet)
if 'predict_proteins' in step_list:
shared.run_prodigal(
args.path_to_prodigal,
args.contigs_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 = 'CAT is spinning! Files {0} and {1} are created.'.format(
args.contig2classification_output_file, args.ORF2LCA_output_file)
shared.give_user_feedback(message, args.log_file, args.quiet)
n_classified_contigs = 0
with open(args.contig2classification_output_file, 'w') as outf1, open(args.ORF2LCA_output_file, 'w') as outf2:
outf1.write(
'# contig\tclassification\treason\tlineage\tlineage scores\n')
outf2.write('# ORF\tnumber of hits\tlineage\ttop bit-score\n')
for contig in sorted(contig_names):
if contig not in contig2ORFs:
outf1.write('{0}\tno taxid assigned\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
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}\n'.format(
ORF, 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}\n'.format(
ORF, n_hits, ';'.join(lineage[::-1]), top_bitscore))
LCAs_ORFs.append((taxid, top_bitscore),)
if len(LCAs_ORFs) == 0:
outf1.write('{0}\tno taxid assigned\t'
'no hits to database\n'.format(contig))
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(contig))
continue
if lineages == 'no lineage whitelisted.':
outf1.write(
'{0}\tno taxid assigned\t'
'no lineage reached minimum bit-score support\n'
''.format(contig))
continue
# The contig has a valid classification.
n_classified_contigs += 1
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(
contig,
based_on_n_ORFs,
len(contig2ORFs[contig]),
';'.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(
contig,
i + 1,
len(lineages),
based_on_n_ORFs,
len(contig2ORFs[contig]),
';'.join(lineage[::-1]),
';'.join(scores[::-1])))
message = ('\n-----------------\n\n'
'{0} CAT is done! {1:,d}/{2:,d} contigs have taxonomy assigned.'
''.format(
shared.timestamp(),
n_classified_contigs,
len(contig_names)))
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 contig '
'may have multiple classifications.')
shared.give_user_feedback(message, args.log_file, args.quiet,
show_time=False)
return