def main(args):
### Get result files paths from SqueezeMeta_conf.pl
perlVars = parse_conf_file(args.project_path,
override={'$projectdir': args.project_path})
nokegg, nocog, nopfam, doublepass = map(int, [
perlVars['$nokegg'], perlVars['$nocog'], perlVars['$nopfam'],
perlVars['$doublepass']
])
### Create output dir.
try:
mkdir(args.output_dir)
except OSError as e:
if e.errno != 17:
raise
elif args.sqm2anvio or args.force_overwrite: # We know what we are doing.
pass
else:
print(
'\nThe directory {} already exists. Please remove it or use a different output name.\n'
.format(args.output_dir))
exit(1)
### Calculate tables and write results.
prefix = args.output_dir + '/' + perlVars['$projectname'] + '.'
### Functions
if not args.sqm2anvio:
# Were custom annotation databases used in this project?
methods = [
f.split('.')[-1] for f in listdir(perlVars['$resultpath'])
if len(f.split('.')) > 2 and f.split('.')[-2] == 'fun3'
]
customMethods = [
method for method in methods
if method not in ('kegg', 'cog', 'pfam', 'wranks')
]
# Parse ORF table.
sampleNames, orfs, kegg, cog, pfam, custom = parse_orf_table(
perlVars['$mergedfile'], nokegg, nocog, nopfam,
args.trusted_functions, args.ignore_unclassified, customMethods)
# Round aggregated functional abundances.
# We can have non-integer abundances bc of the way we split counts in ORFs with multiple KEGGs.
# We round the aggregates to the closest integer for convenience.
kegg['abundances'] = {
k: a.round().astype(int)
for k, a in kegg['abundances'].items()
}
cog['abundances'] = {
k: a.round().astype(int)
for k, a in cog['abundances'].items()
}
pfam['abundances'] = {
k: a.round().astype(int)
for k, a in pfam['abundances'].items()
}
#write_row_dict(sampleNames, orfs['tpm'], prefix + 'orf.tpm.tsv')
if not nokegg:
write_row_dict(['Name', 'Path'], kegg['info'],
prefix + 'KO.names.tsv')
write_row_dict(sampleNames, kegg['abundances'],
prefix + 'KO.abund.tsv')
write_row_dict(sampleNames, kegg['bases'], prefix + 'KO.bases.tsv')
write_row_dict(sampleNames, kegg['tpm'], prefix + 'KO.tpm.tsv')
if 'copyNumber' in kegg:
write_row_dict(sampleNames, kegg['copyNumber'],
prefix + 'KO.copyNumber.tsv')
if not nocog:
write_row_dict(['Name', 'Path'], cog['info'],
prefix + 'COG.names.tsv')
write_row_dict(sampleNames, cog['abundances'],
prefix + 'COG.abund.tsv')
write_row_dict(sampleNames, cog['bases'], prefix + 'COG.bases.tsv')
write_row_dict(sampleNames, cog['tpm'], prefix + 'COG.tpm.tsv')
if 'copyNumber' in cog:
write_row_dict(sampleNames, cog['copyNumber'],
prefix + 'COG.copyNumber.tsv')
write_row_dict(sampleNames,
{'COG0468': cog['coverages']['COG0468']},
prefix + 'RecA.tsv')
if not nopfam:
write_row_dict(sampleNames, pfam['abundances'],
prefix + 'PFAM.abund.tsv')
write_row_dict(sampleNames, pfam['bases'],
prefix + 'PFAM.bases.tsv')
write_row_dict(sampleNames, pfam['tpm'], prefix + 'PFAM.tpm.tsv')
if 'copyNumber' in pfam:
write_row_dict(sampleNames, pfam['copyNumber'],
prefix + 'PFAM.copyNumber.tsv')
for method, d in custom.items():
write_row_dict(['Name'], d['info'], prefix + method + '.names.tsv')
write_row_dict(sampleNames, d['abundances'],
prefix + method + '.abund.tsv')
write_row_dict(sampleNames, d['bases'],
prefix + method + '.bases.tsv')
write_row_dict(sampleNames, d['tpm'], prefix + method + '.tpm.tsv')
if 'copyNumber' in d:
write_row_dict(sampleNames, d['copyNumber'],
prefix + method + '.copyNumber.tsv')
else:
# Not super beautiful code. Just read the orf names and create a fake orf dict
# since we need to know the names of all the orfs to create the taxonomy output.
orfs = {'abundances': read_orf_names(perlVars['$mergedfile'])}
### Taxonomy.
fun_prefix = perlVars['$fun3tax_blastx'] if doublepass else perlVars[
'$fun3tax']
orf_tax, orf_tax_wranks = parse_tax_table(fun_prefix + '.wranks')
orf_tax_nofilter, orf_tax_nofilter_wranks = parse_tax_table(
fun_prefix + '.noidfilter.wranks')
# Add ORFs not present in the input tax file.
unclass_list, unclass_list_wranks = parse_tax_string('n_Unclassified')
for orf in orfs['abundances']:
if orf not in orf_tax:
assert orf not in orf_tax_wranks
assert orf not in orf_tax_nofilter
assert orf not in orf_tax_nofilter_wranks
orf_tax[orf] = unclass_list
orf_tax_wranks[orf] = unclass_list_wranks
orf_tax_nofilter[orf] = unclass_list
orf_tax_nofilter_wranks[orf] = unclass_list_wranks
orf_tax_prokfilter, orf_tax_prokfilter_wranks = {}, {}
for orf in orf_tax:
tax = orf_tax[orf]
tax_nofilter = orf_tax_nofilter[orf]
if 'Bacteria' in (tax[0], tax_nofilter[0]) or 'Archaea' in (
tax[0], tax_nofilter[0]): # We check both taxonomies.
orf_tax_prokfilter[orf] = tax
orf_tax_prokfilter_wranks[orf] = orf_tax_wranks[orf]
else:
orf_tax_prokfilter[orf] = tax_nofilter
orf_tax_prokfilter_wranks[orf] = orf_tax_nofilter_wranks[orf]
contig_abunds, contig_tax, contig_tax_wranks = parse_contig_table(
perlVars['$contigtable'])
write_row_dict(TAXRANKS, orf_tax, prefix + 'orf.tax.allfilter.tsv')
write_row_dict(TAXRANKS, contig_tax, prefix + 'contig.tax.tsv')
if not args.sqm2anvio:
fna_blastx = perlVars['$fna_blastx'] if doublepass else None
write_orf_seqs(orfs['abundances'].keys(), perlVars['$aafile'],
fna_blastx, perlVars['$rnafile'],
perlVars['$trnafile'] + '.fasta',
prefix + 'orf.sequences.tsv')
write_contig_seqs(perlVars['$contigsfna'],
prefix + 'contig.sequences.tsv')
write_row_dict(TAXRANKS, orf_tax_nofilter,
prefix + 'orf.tax.nofilter.tsv')
write_row_dict(TAXRANKS, orf_tax_prokfilter,
prefix + 'orf.tax.prokfilter.tsv')
### Bins
if not int(perlVars['$nobins']):
bin_tpm, bin_tax, bin_tax_wranks = parse_bin_table(
perlVars['$bintable'])
write_row_dict(TAXRANKS, bin_tax, prefix + 'bin.tax.tsv')
for idx, rank in enumerate(TAXRANKS):
tax_abunds_orfs = aggregate_tax_abunds(orfs['abundances'],
orf_tax_prokfilter_wranks,
idx)
write_row_dict(sampleNames, tax_abunds_orfs,
prefix + '{}.prokfilter.abund.tsv'.format(rank))
#write_row_dict(sampleNames, normalize_abunds(tax_abunds_orfs, 100), prefix + '{}.prokfilter.percent.tsv'.format(rank))
tax_abunds_contigs = aggregate_tax_abunds(contig_abunds,
contig_tax_wranks, idx)
write_row_dict(sampleNames, tax_abunds_contigs,
prefix + '{}.allfilter.abund.tsv'.format(rank))
def main(args):
### Get result files paths from SqueezeMeta_conf.pl
perlVars = parse_conf_file(args.project_path)
### Create output dir.
try:
mkdir(args.output_dir)
except OSError as e:
if e.errno != 17:
raise
else:
print(
'\nThe directory {} already exists. Please remove it or use a different output name.\n'
.format(args.output_dir))
exit(1)
### Create samples file.
with open(perlVars['$mappingfile']) as infile, open(
'{}/samples.tsv'.format(args.output_dir), 'w') as outfile:
outfile.write('Sample\ttest\n')
addedSamples = set()
for line in infile:
sample = line.split('\t')[0].strip(
) # There shouldn't be trailing spaces though...
if sample not in addedSamples:
addedSamples.add(sample)
outfile.write('{}\t{}\n'.format(sample, len(addedSamples)))
### Create orftable.
def new2old(str_, orftable=False, bintable=False):
"""Replace 1.0 headers with old headers, so we don't have to modify and re-deploy SQMdb"""
if orftable:
str_ = str_.replace('Coverage', 'COVERAGE').replace(
'Raw read count',
'RAW READ COUNT').replace('Raw base count', 'RAW BASE COUNT')
else:
str_ = str_.replace('Strain het',
'Strain Het').replace('Raw read count', 'Raw')
if bintable:
str_ = str_.replace('Length', 'Size')
return str_
allORFs = []
newFields = [
'ORF ID', 'Contig ID', 'Length AA', 'GC perc', 'Gene name', 'Tax',
'KEGG ID', 'KEGGFUN', 'KEGGPATH', 'COG ID', 'COGFUN', 'COGPATH', 'PFAM'
]
goodFields = [
'ORF', 'CONTIG ID', 'LENGTH AA', 'GC perc', 'GENNAME', 'TAX ORF',
'KEGG ID', 'KEGGFUN', 'KEGGPATH', 'COG ID', 'COGFUN', 'COGPATH', 'PFAM'
]
with open(perlVars['$mergedfile']) as infile, open(
'{}/genes.tsv'.format(args.output_dir), 'w') as outfile:
outfile.write(infile.readline())
header = infile.readline().strip().split('\t')
newFields.extend([
f for f in header
if f.startswith('TPM ') or f.startswith('Coverage ')
or f.startswith('Raw read ') or f.startswith('Raw base ')
])
goodFields.extend([
new2old(f, True) for f in header
if f.startswith('TPM ') or f.startswith('Coverage ')
or f.startswith('Raw read ') or f.startswith('Raw base ')
])
outfile.write('\t'.join(goodFields) + '\n')
idx = {f: i for i, f in enumerate(header) if f in newFields}
for line in infile:
line = line.strip().split('\t')
if line[2] == 'CDS':
allORFs.append(line[0])
outfile.write('{}\n'.format('\t'.join(
[line[idx[f]] for f in newFields])))
### Create contigtable.
with open(perlVars['$contigtable']) as infile, open(
'{}/contigs.tsv'.format(args.output_dir), 'w') as outfile:
outfile.write(infile.readline())
outfile.write(new2old(infile.readline())) # adapt header
[outfile.write(line) for line in infile]
### Create bintable.
if not int(perlVars['$nobins']):
with open(perlVars['$bintable']) as infile, open(
'{}/bins.tsv'.format(args.output_dir), 'w') as outfile:
outfile.write(infile.readline())
outfile.write(new2old(infile.readline(),
bintable=True)) # adapt header
[outfile.write(line) for line in infile]
### Create sequences file.
aafile = perlVars['$aafile']
fna_blastx = perlVars['$fna_blastx'] if int(
perlVars['$doublepass']) else None
outname = '{}/sequences.tsv'.format(args.output_dir)
write_orf_seqs(allORFs, aafile, fna_blastx, None, outname)