def setattributes(self, args):
self.hk = HouseKeeping()
self.s = Stats_And_Summary()
if args.subparser_name == 'graft':
commands = ExternalProgramSuite([
'orfm', 'nhmmer', 'hmmsearch', 'mfqe', 'pplacer',
'ktImportText', 'diamond'
])
self.hk.set_attributes(self.args)
self.hk.set_euk_hmm(self.args)
if args.euk_check:
self.args.search_hmm_files.append(self.args.euk_hmm_file)
self.ss = SequenceSearcher(
self.args.search_hmm_files,
(None if self.args.search_only else self.args.aln_hmm_file))
self.sequence_pair_list = self.hk.parameter_checks(args)
if hasattr(args, 'reference_package'):
self.p = Pplacer(self.args.reference_package)
elif self.args.subparser_name == "create":
commands = ExternalProgramSuite(
['taxit', 'FastTreeMP', 'hmmalign', 'mafft'])
self.create = Create(commands)
def _get_hmm_from_alignment(self, alignment, hmm_filename,
output_alignment_filename):
'''Return a HMM file and alignment of sequences to that HMM
Parameters
----------
alignment: str
path to aligned proteins
hmm_filename: str
write the hmm to this file path
output_alignment_filename: str
write the output alignment to this file path
Returns
-------
Return the pipeline type of the HMM.
'''
logging.info("Building HMM from alignment")
with tempfile.NamedTemporaryFile(suffix='.fasta',
prefix='graftm',
mode='w') as tempaln:
cmd = "hmmbuild -O /dev/stdout -o /dev/stderr '%s' '%s'" % (
hmm_filename, alignment)
output = extern.run(cmd)
SeqIO.write(SeqIO.parse(StringIO(output), 'stockholm'), tempaln,
'fasta')
tempaln.flush()
ptype, _ = self._pipe_type(hmm_filename)
SequenceSearcher(hmm_filename).alignment_correcter(
[tempaln.name], output_alignment_filename)
return ptype
def test_merg_aln(self):
forward_reads = '''>no_overlap
-------CGTATGCAACCTACCTT---------------------------------------
>overlap_all_match
-------CGTATGCAACCTACCTT---------------------------------------
>overlap_mismatch_in_reverse
-------CGTATGCAACCTACCTT---------------------------------------
>overlap_mismatch_in_forward
-------CGTATGCAACCTTCCTT---------------------------------------
>complete_overlap_all_match
-------CGTATGCAACCTACCTT---------------------------------------
>complete_overlap_mismatch
-------CGTATGCATCCTACCTT---------------------------------------'''
reverse_reads = '''>no_overlap
---------------------------------------CGTATGCAACCTACCTT-------
>overlap_all_match
----------------CCTACCTTCAACCTACCTT----------------------------
>overlap_mismatch_in_reverse
----------------CCTTCCTTCAACCTACCTT----------------------------
>overlap_mismatch_in_forward
----------------CCTACCTTCAACCTACCTT----------------------------
>complete_overlap_all_match
-------CGTATGCAACCTACCTT---------------------------------------
>complete_overlap_mismatch
-------CGTTTGCAAGCTACCTT---------------------------------------'''
expected_aln = '''>no_overlap
-------CGTATGCAACCTACCTT---------------CGTATGCAACCTACCTT-------
>overlap_all_match
-------CGTATGCAACCTACCTTCAACCTACCTT----------------------------
>overlap_mismatch_in_reverse
-------CGTATGCAACCTACCTTCAACCTACCTT----------------------------
>overlap_mismatch_in_forward
-------CGTATGCAACCTTCCTTCAACCTACCTT----------------------------
>complete_overlap_all_match
-------CGTATGCAACCTACCTT---------------------------------------
>complete_overlap_mismatch
-------CGTATGCATCCTACCTT---------------------------------------'''.split()
with tempfile.NamedTemporaryFile(suffix='_forward.fa') as forward_file:
with tempfile.NamedTemporaryFile(
suffix='_reverse.fa') as reverse_file:
with tempfile.NamedTemporaryFile(suffix='.fa') as output_file:
forward_file.write(forward_reads.encode())
reverse_file.write(reverse_reads.encode())
forward_file.flush()
reverse_file.flush()
SequenceSearcher(None).merge_forev_aln([forward_file.name],
[reverse_file.name],
[output_file.name])
count = 0
for line in open(output_file.name):
self.assertEqual(expected_aln[count], line.strip())
count += 1
with open(output_file.name) as f:
self.assertEqual(count, len(f.readlines()))
def _align_sequences_to_hmm(self, hmm_file, sequences_file, output_alignment_file):
'''Align sequences to an HMM, and write an alignment of
these proteins after cleanup so that they can be used for tree-making
Parameters
----------
sequences_file: str
path to file of unaligned protein sequences
hmm_file: str
path to hmm file
output_alignment_file: str
write alignment to this file
Returns
-------
nothing
'''
ss = SequenceSearcher(hmm_file)
with tempfile.NamedTemporaryFile(prefix='graftm', suffix='.aln.fasta') as tempalign:
ss.hmmalign_sequences(hmm_file, sequences_file, tempalign.name)
ss.alignment_correcter([tempalign.name], output_alignment_file)
def _get_hmm_from_alignment(self, alignment, hmm_filename,
output_alignment_filename):
'''Return a HMM file and alignment of sequences to that HMM
Parameters
----------
alignment: str
path to aligned proteins
hmm_filename: str
write the hmm to this file path
output_alignment_filename: str
write the output alignment to this file path
Returns
-------
Return the pipeline type of the HMM.
'''
logging.info("Building HMM from alignment")
with tempfile.NamedTemporaryFile(suffix='.fasta',
prefix='graftm') as tempaln:
cmd = "hmmbuild -O /dev/stdout -o /dev/stderr '%s' '%s'" % (
hmm_filename, alignment)
process = subprocess.Popen(["bash", "-c", cmd],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
output, error = process.communicate()
logging.debug("Got STDERR from hmmbuild: %s" % error)
if process.returncode != 0:
logging.error(
"hmmbuild exitstatus was non-zero, likely indicating an error of "
"some description")
logging.error("Got STDERR from hmmbuild: %s" % error)
SeqIO.write(SeqIO.parse(StringIO(output), 'stockholm'), tempaln,
'fasta')
tempaln.flush()
ptype, _ = self._pipe_type(hmm_filename)
SequenceSearcher(hmm_filename).alignment_correcter(
[tempaln.name], output_alignment_filename)
return ptype
def _align_sequences_to_hmm(self, hmm_file, sequences_file,
output_alignment_file):
'''Align sequences to an HMM, and write an alignment of
these proteins after cleanup so that they can be used for tree-making
Parameters
----------
sequences_file: str
path to file of unaligned protein sequences
hmm_file: str
path to hmm file
output_alignment_file: str
write alignment to this file
Returns
-------
nothing
'''
ss = SequenceSearcher(hmm_file)
with tempfile.NamedTemporaryFile(prefix='graftm',
suffix='.aln.fasta') as tempalign:
ss.hmmalign_sequences(hmm_file, sequences_file, tempalign.name)
ss.alignment_correcter([tempalign.name], output_alignment_file)
def generate_expand_search_database_from_contigs(self, contig_files,
output_database_file,
search_method):
'''Given a collection of search_hmm_files, search the contigs in
contig_files, and generate an HMM from the resulting hits, outputting
it as output_database_file.
Parameters
----------
contig_files: list of str
list of files to search
output_database_file: str
path to output file
search_method: str
"diamond" or "hmmsearch", to specify search method to use and what
type of database to build.
Returns
-------
True if genes were recovered, else False'''
ss = SequenceSearcher(self.search_hmm_files)
seqio = SequenceIO()
if search_method == self.DIAMOND_SEARCH_METHOD:
if self.diamond_database == None or self.unaligned_sequence_database == None:
logging.warning(
"Cannot expand_search continue with no diamond database or unaligned sequences."
)
return False
with tempfile.NamedTemporaryFile(
prefix='graftm_expand_search_orfs') as orfs:
logging.info("Finding expand_search hits in provided contigs..")
for contig_file in contig_files:
logging.debug("Finding expand_search hits in %s.." %
contig_file)
unpack = UnpackRawReads(contig_file)
with tempfile.NamedTemporaryFile(prefix='graftm_expand_search') as \
hit_reads_orfs_fasta:
# search and extract matching ORFs
with tempfile.NamedTemporaryFile(prefix='graftm_expand_search2') as \
hmmsearch_output_table:
with tempfile.NamedTemporaryFile(prefix='graftm_expand_search3') as \
hit_reads_fasta:
ss.search_and_extract_orfs_matching_protein_database(\
unpack,
search_method,
self.maximum_range,
self.threads,
self.evalue,
self.min_orf_length,
None,
(self.diamond_database if self.diamond_database else None),
hmmsearch_output_table.name,
hit_reads_fasta.name,
hit_reads_orfs_fasta.name)
# Append to the file
shutil.copyfileobj(open(hit_reads_orfs_fasta.name), orfs)
# Now have a fasta file of ORFs.
# Check to make sure the file is not zero-length
orfs.flush()
with tempfile.NamedTemporaryFile(
prefix="graftm_expand_search_aln") as aln:
if search_method == self.HMM_SEARCH_METHOD:
# Check that there is more than one sequence to align.
if len(
seqio.read_fasta_file(orfs.name)
) <= 1: # Just to build on this, you need to check if there is > 1 hit
# otherwise mafft will fail to align, causing a crash when hmmbuild is
# run on an empty file.
logging.warn(
"Failed to find two or more matching ORFs in the expand_search contigs"
)
return False
# Run mafft to align them
cmd = "mafft --auto %s >%s" % (orfs.name, aln.name)
logging.info("Aligning expand_search hits..")
extern.run(cmd)
# Run hmmbuild to create an HMM
cmd = "hmmbuild --amino %s %s >/dev/null" % (
output_database_file, aln.name)
logging.info("Building HMM from expand_search hits..")
extern.run(cmd)
elif search_method == self.DIAMOND_SEARCH_METHOD:
# Concatenate database with existing database
with tempfile.NamedTemporaryFile(
prefix="concatenated_database") as databasefile:
for f in [orfs.name, self.unaligned_sequence_database]:
for line in open(f):
databasefile.write(line)
databasefile.flush()
# Run diamond make to create a diamond database
cmd = "diamond makedb --in '%s' -d '%s'" % (
databasefile.name, output_database_file)
logging.info(
"Building a diamond database from expand_search hits.."
)
extern.run(cmd)
else:
raise Exception("Search method not recognised: %s" %
search_method)
return False
return True
class Run:
PIPELINE_AA = "P"
PIPELINE_NT = "D"
_MIN_VERBOSITY_FOR_ART = 3 # with 2 then, only errors are printed
PPLACER_TAXONOMIC_ASSIGNMENT = 'pplacer'
DIAMOND_TAXONOMIC_ASSIGNMENT = 'diamond'
MIN_ALIGNED_FILTER_FOR_NUCLEOTIDE_PACKAGES = 95
MIN_ALIGNED_FILTER_FOR_AMINO_ACID_PACKAGES = 30
DEFAULT_MAX_SAMPLES_FOR_KRONA = 100
NO_ORFS_EXITSTATUS = 128
def __init__(self, args):
self.args = args
self.setattributes(self.args)
def setattributes(self, args):
self.hk = HouseKeeping()
self.s = Stats_And_Summary()
if args.subparser_name == 'graft':
commands = ExternalProgramSuite([
'orfm', 'nhmmer', 'hmmsearch', 'mfqe', 'pplacer',
'ktImportText', 'diamond'
])
self.hk.set_attributes(self.args)
self.hk.set_euk_hmm(self.args)
if args.euk_check:
self.args.search_hmm_files.append(self.args.euk_hmm_file)
self.ss = SequenceSearcher(
self.args.search_hmm_files,
(None if self.args.search_only else self.args.aln_hmm_file))
self.sequence_pair_list = self.hk.parameter_checks(args)
if hasattr(args, 'reference_package'):
self.p = Pplacer(self.args.reference_package)
elif self.args.subparser_name == "create":
commands = ExternalProgramSuite(
['taxit', 'FastTreeMP', 'hmmalign', 'mafft'])
self.create = Create(commands)
def summarise(self, base_list, trusted_placements, reverse_pipe, times,
hit_read_count_list, max_samples_for_krona):
'''
summarise - write summary information to file, including otu table, biom
file, krona plot, and timing information
Parameters
----------
base_list : array
list of each of the files processed by graftm, with the path and
and suffixed removed
trusted_placements : dict
dictionary of placements with entry as the key, a taxonomy string
as the value
reverse_pipe : bool
True = run reverse pipe, False = run normal pipeline
times : array
list of the recorded times for each step in the pipeline in the
format: [search_step_time, alignment_step_time, placement_step_time]
hit_read_count_list : array
list containing sublists, one for each file run through the GraftM
pipeline, each two entries, the first being the number of putative
eukaryotic reads (when searching 16S), the second being the number
of hits aligned and placed in the tree.
max_samples_for_krona: int
If the number of files processed is greater than this number, then
do not generate a krona diagram.
Returns
-------
'''
# Summary steps.
placements_list = []
for base in base_list:
# First assign the hash that contains all of the trusted placements
# to a variable to it can be passed to otu_builder, to be written
# to a file. :)
placements = trusted_placements[base]
self.s.readTax(
placements,
GraftMFiles(base, self.args.output_directory,
False).read_tax_output_path(base))
placements_list.append(placements)
#Generate coverage table
#logging.info('Building coverage table for %s' % base)
#self.s.coverage_of_hmm(self.args.aln_hmm_file,
# self.gmf.summary_table_output_path(base),
# self.gmf.coverage_table_path(base),
# summary_dict[base]['read_length'])
logging.info('Writing summary table')
with open(self.gmf.combined_summary_table_output_path(), 'w') as f:
self.s.write_tabular_otu_table(base_list, placements_list, f)
logging.info('Writing biom file')
with biom_open(self.gmf.combined_biom_output_path(), 'w') as f:
biom_successful = self.s.write_biom(base_list, placements_list, f)
if not biom_successful:
os.remove(self.gmf.combined_biom_output_path())
logging.info('Building summary krona plot')
if len(base_list) > max_samples_for_krona:
logging.warn(
"Skipping creation of Krona diagram since there are too many input files. The maximum can be overridden using --max_samples_for_krona"
)
else:
self.s.write_krona_plot(base_list, placements_list,
self.gmf.krona_output_path())
# Basic statistics
placed_reads = [len(trusted_placements[base]) for base in base_list]
self.s.build_basic_statistics(times, hit_read_count_list, placed_reads, \
base_list, self.gmf.basic_stats_path())
# Delete unnecessary files
logging.info('Cleaning up')
for base in base_list:
directions = ['forward', 'reverse']
if reverse_pipe:
for i in range(0, 2):
self.gmf = GraftMFiles(base, self.args.output_directory,
directions[i])
self.hk.delete([
self.gmf.for_aln_path(base),
self.gmf.rev_aln_path(base),
self.gmf.conv_output_rev_path(base),
self.gmf.conv_output_for_path(base),
self.gmf.euk_free_path(base),
self.gmf.euk_contam_path(base),
self.gmf.readnames_output_path(base),
self.gmf.sto_output_path(base),
self.gmf.orf_titles_output_path(base),
self.gmf.orf_output_path(base),
self.gmf.output_for_path(base),
self.gmf.output_rev_path(base)
])
else:
self.gmf = GraftMFiles(base, self.args.output_directory, False)
self.hk.delete([
self.gmf.for_aln_path(base),
self.gmf.rev_aln_path(base),
self.gmf.conv_output_rev_path(base),
self.gmf.conv_output_for_path(base),
self.gmf.euk_free_path(base),
self.gmf.euk_contam_path(base),
self.gmf.readnames_output_path(base),
self.gmf.sto_output_path(base),
self.gmf.orf_titles_output_path(base),
self.gmf.orf_output_path(base),
self.gmf.output_for_path(base),
self.gmf.output_rev_path(base)
])
logging.info('Done, thanks for using graftM!\n')
def graft(self):
# The Graft pipeline:
# Searches for reads using hmmer, and places them in phylogenetic
# trees to derive a community structure.
if self.args.graftm_package:
gpkg = GraftMPackage.acquire(self.args.graftm_package)
else:
gpkg = None
REVERSE_PIPE = (True if self.args.reverse else False)
INTERLEAVED = (True if self.args.interleaved else False)
base_list = []
seqs_list = []
search_results = []
hit_read_count_list = []
db_search_results = []
if gpkg:
maximum_range = gpkg.maximum_range()
if self.args.search_diamond_file:
self.args.search_method = self.hk.DIAMOND_SEARCH_METHOD
diamond_db = self.args.search_diamond_file[0]
else:
diamond_db = gpkg.diamond_database_path()
if self.args.search_method == self.hk.DIAMOND_SEARCH_METHOD:
if not diamond_db:
logging.error(
"%s search method selected, but no diamond database specified. \
Please either provide a gpkg to the --graftm_package flag, or a diamond \
database to the --search_diamond_file flag." %
self.args.search_method)
raise Exception()
else:
# Get the maximum range, if none exists, make one from the HMM profile
if self.args.maximum_range:
maximum_range = self.args.maximum_range
else:
if self.args.search_method == self.hk.HMMSEARCH_SEARCH_METHOD:
if not self.args.search_only:
maximum_range = self.hk.get_maximum_range(
self.args.aln_hmm_file)
else:
logging.debug(
"Running search only pipeline. maximum_range not configured."
)
maximum_range = None
else:
logging.warning(
'Cannot determine maximum range when using %s pipeline and with no GraftM package specified'
% self.args.search_method)
logging.warning(
'Setting maximum_range to None (linked hits will not be detected)'
)
maximum_range = None
if self.args.search_diamond_file:
diamond_db = self.args.search_diamond_file
else:
if self.args.search_method == self.hk.HMMSEARCH_SEARCH_METHOD:
diamond_db = None
else:
logging.error(
"%s search method selected, but no gpkg or diamond database selected"
% self.args.search_method)
if self.args.assignment_method == Run.DIAMOND_TAXONOMIC_ASSIGNMENT:
if self.args.reverse:
logging.warn(
"--reverse reads specified with --assignment_method diamond. Reverse reads will be ignored."
)
self.args.reverse = None
# If merge reads is specified, check that there are reverse reads to merge with
if self.args.merge_reads and not hasattr(self.args, 'reverse'):
raise Exception("Programming error")
# Set the output directory if not specified and create that directory
logging.debug('Creating working directory: %s' %
self.args.output_directory)
self.hk.make_working_directory(self.args.output_directory,
self.args.force)
# Set pipeline and evalue by checking HMM format
if self.args.search_only:
if self.args.search_method == self.hk.HMMSEARCH_SEARCH_METHOD:
hmm_type, hmm_tc = self.hk.setpipe(
self.args.search_hmm_files[0])
logging.debug("HMM type: %s Trusted Cutoff: %s" %
(hmm_type, hmm_tc))
else:
hmm_type, hmm_tc = self.hk.setpipe(self.args.aln_hmm_file)
logging.debug("HMM type: %s Trusted Cutoff: %s" %
(hmm_type, hmm_tc))
if self.args.search_method == self.hk.HMMSEARCH_SEARCH_METHOD:
setattr(self.args, 'type', hmm_type)
if hmm_tc:
setattr(self.args, 'evalue', '--cut_tc')
else:
setattr(self.args, 'type', self.PIPELINE_AA)
if self.args.filter_minimum is not None:
filter_minimum = self.args.filter_minimum
else:
if self.args.type == self.PIPELINE_NT:
filter_minimum = Run.MIN_ALIGNED_FILTER_FOR_NUCLEOTIDE_PACKAGES
else:
filter_minimum = Run.MIN_ALIGNED_FILTER_FOR_AMINO_ACID_PACKAGES
# Generate expand_search database if required
if self.args.expand_search_contigs:
if self.args.graftm_package:
pkg = GraftMPackage.acquire(self.args.graftm_package)
else:
pkg = None
boots = ExpandSearcher(search_hmm_files=self.args.search_hmm_files,
maximum_range=self.args.maximum_range,
threads=self.args.threads,
evalue=self.args.evalue,
min_orf_length=self.args.min_orf_length,
graftm_package=pkg)
# this is a hack, it should really use GraftMFiles but that class isn't currently flexible enough
new_database = (os.path.join(self.args.output_directory, "expand_search.hmm") \
if self.args.search_method == self.hk.HMMSEARCH_SEARCH_METHOD \
else os.path.join(self.args.output_directory, "expand_search")
)
if boots.generate_expand_search_database_from_contigs(
self.args.expand_search_contigs, new_database,
self.args.search_method):
if self.args.search_method == self.hk.HMMSEARCH_SEARCH_METHOD:
self.ss.search_hmm.append(new_database)
else:
diamond_db = new_database
first_search_method = self.args.search_method
if self.args.decoy_database:
decoy_filter = DecoyFilter(
Diamond(diamond_db, threads=self.args.threads),
Diamond(self.args.decoy_database, threads=self.args.threads))
doing_decoy_search = True
elif self.args.search_method == self.hk.HMMSEARCH_AND_DIAMOND_SEARCH_METHOD:
decoy_filter = DecoyFilter(
Diamond(diamond_db, threads=self.args.threads))
doing_decoy_search = True
first_search_method = self.hk.HMMSEARCH_SEARCH_METHOD
else:
doing_decoy_search = False
# For each pair (or single file passed to GraftM)
logging.debug('Working with %i file(s)' % len(self.sequence_pair_list))
for pair in self.sequence_pair_list:
# Guess the sequence file type, if not already specified to GraftM
unpack = UnpackRawReads(pair[0], self.args.input_sequence_type,
INTERLEAVED)
# Set the basename, and make an entry to the summary table.
base = unpack.basename()
pair_direction = ['forward', 'reverse']
logging.info("Working on %s" % base)
# Make the working base subdirectory
self.hk.make_working_directory(
os.path.join(self.args.output_directory, base),
self.args.force)
# for each of the paired end read files
for read_file in pair:
unpack = UnpackRawReads(read_file,
self.args.input_sequence_type,
INTERLEAVED)
if read_file is None:
# placeholder for interleaved (second file is None)
continue
if not os.path.isfile(read_file): # Check file exists
logging.info('%s does not exist! Skipping this file..' %
read_file)
continue
# Set the output file_name
if len(pair) == 2:
direction = 'interleaved' if pair[1] is None \
else pair_direction.pop(0)
logging.info("Working on %s reads" % direction)
self.gmf = GraftMFiles(base, self.args.output_directory,
direction)
self.hk.make_working_directory(
os.path.join(self.args.output_directory, base,
direction), self.args.force)
else:
direction = False
self.gmf = GraftMFiles(base, self.args.output_directory,
direction)
if self.args.type == self.PIPELINE_AA:
logging.debug("Running protein pipeline")
try:
search_time, (
result,
complement_information) = self.ss.aa_db_search(
self.gmf,
base,
unpack,
first_search_method,
maximum_range,
self.args.threads,
self.args.evalue,
self.args.min_orf_length,
self.args.restrict_read_length,
diamond_db,
self.args.diamond_performance_parameters,
)
except NoInputSequencesException as e:
logging.error(
"No sufficiently long open reading frames were found, indicating"
" either the input sequences are too short or the min orf length"
" cutoff is too high. Cannot continue sorry. Alternatively, there"
" is something amiss with the installation of OrfM. The specific"
" command that failed was: %s" % e.command)
exit(Run.NO_ORFS_EXITSTATUS)
# Or the DNA pipeline
elif self.args.type == self.PIPELINE_NT:
logging.debug("Running nucleotide pipeline")
search_time, (
result, complement_information) = self.ss.nt_db_search(
self.gmf, base, unpack, self.args.euk_check,
self.args.search_method, maximum_range,
self.args.threads, self.args.evalue)
reads_detected = True
if not result.hit_fasta() or os.path.getsize(
result.hit_fasta()) == 0:
logging.info('No reads found in %s' % base)
reads_detected = False
if self.args.search_only:
db_search_results.append(result)
base_list.append(base)
continue
# Filter out decoys if specified
if reads_detected and doing_decoy_search:
with tempfile.NamedTemporaryFile(prefix="graftm_decoy",
suffix='.fa') as f:
tmpname = f.name
any_remaining = decoy_filter.filter(
result.hit_fasta(), tmpname)
if any_remaining:
shutil.move(tmpname, result.hit_fasta())
else:
# No hits remain after decoy filtering.
os.remove(result.hit_fasta())
continue
if self.args.assignment_method == Run.PPLACER_TAXONOMIC_ASSIGNMENT:
logging.info(
'aligning reads to reference package database')
hit_aligned_reads = self.gmf.aligned_fasta_output_path(
base)
if reads_detected:
aln_time, aln_result = self.ss.align(
result.hit_fasta(), hit_aligned_reads,
complement_information, self.args.type,
filter_minimum)
else:
aln_time = 'n/a'
if not os.path.exists(
hit_aligned_reads
): # If all were filtered out, or there just was none..
with open(hit_aligned_reads, 'w') as f:
pass # just touch the file, nothing else
seqs_list.append(hit_aligned_reads)
db_search_results.append(result)
base_list.append(base)
search_results.append(result.search_result)
hit_read_count_list.append(result.hit_count)
# Write summary table
srchtw = SearchTableWriter()
srchtw.build_search_otu_table(
[x.search_objects for x in db_search_results], base_list,
self.gmf.search_otu_table())
if self.args.search_only:
logging.info(
'Stopping before alignment and taxonomic assignment phase\n')
exit(0)
if self.args.merge_reads: # not run when diamond is the assignment mode- enforced by argparse grokking
logging.debug("Running merge reads output")
if self.args.interleaved:
fwd_seqs = seqs_list
rev_seqs = []
else:
base_list = base_list[0::2]
fwd_seqs = seqs_list[0::2]
rev_seqs = seqs_list[1::2]
merged_output=[GraftMFiles(base, self.args.output_directory, False).aligned_fasta_output_path(base) \
for base in base_list]
logging.debug("merged reads to %s", merged_output)
self.ss.merge_forev_aln(fwd_seqs, rev_seqs, merged_output)
seqs_list = merged_output
REVERSE_PIPE = False
elif REVERSE_PIPE:
base_list = base_list[0::2]
# Leave the pipeline if search only was specified
if self.args.search_and_align_only:
logging.info('Stopping before taxonomic assignment phase\n')
exit(0)
elif not any(base_list):
logging.error(
'No hits in any of the provided files. Cannot continue with no reads to assign taxonomy to.\n'
)
exit(0)
self.gmf = GraftMFiles('', self.args.output_directory, False)
if self.args.assignment_method == Run.PPLACER_TAXONOMIC_ASSIGNMENT:
clusterer = Clusterer()
# Classification steps
seqs_list = clusterer.cluster(seqs_list, REVERSE_PIPE)
logging.info("Placing reads into phylogenetic tree")
taxonomic_assignment_time, assignments = self.p.place(
REVERSE_PIPE, seqs_list, self.args.resolve_placements,
self.gmf, self.args, result.slash_endings,
gpkg.taxtastic_taxonomy_path(), clusterer)
assignments = clusterer.uncluster_annotations(
assignments, REVERSE_PIPE)
elif self.args.assignment_method == Run.DIAMOND_TAXONOMIC_ASSIGNMENT:
logging.info("Assigning taxonomy with diamond")
taxonomic_assignment_time, assignments = self._assign_taxonomy_with_diamond(\
base_list,
db_search_results,
gpkg,
self.gmf,
self.args.diamond_performance_parameters)
aln_time = 'n/a'
else:
raise Exception("Unexpected assignment method encountered: %s" %
self.args.placement_method)
self.summarise(base_list, assignments, REVERSE_PIPE,
[search_time, aln_time, taxonomic_assignment_time],
hit_read_count_list, self.args.max_samples_for_krona)
@T.timeit
def _assign_taxonomy_with_diamond(self, base_list, db_search_results,
graftm_package, graftm_files,
diamond_performance_parameters):
'''Run diamond to assign taxonomy
Parameters
----------
base_list: list of str
list of sequence block names
db_search_results: list of DBSearchResult
the result of running hmmsearches
graftm_package: GraftMPackage object
Diamond is run against this database
graftm_files: GraftMFiles object
Result files are written here
diamond_performance_parameters : str
extra args for DIAMOND
Returns
-------
list of
1. time taken for assignment
2. assignments i.e. dict of base_list entry to dict of read names to
to taxonomies, or None if there was no hit detected.
'''
runner = Diamond(graftm_package.diamond_database_path(),
self.args.threads, self.args.evalue)
taxonomy_definition = Getaxnseq().read_taxtastic_taxonomy_and_seqinfo\
(open(graftm_package.taxtastic_taxonomy_path()),
open(graftm_package.taxtastic_seqinfo_path()))
results = {}
# For each of the search results,
for i, search_result in enumerate(db_search_results):
if search_result.hit_fasta() is None:
sequence_id_to_taxonomy = {}
else:
sequence_id_to_hit = {}
# Run diamond
logging.debug("Running diamond on %s" %
search_result.hit_fasta())
diamond_result = runner.run(
search_result.hit_fasta(),
UnpackRawReads.PROTEIN_SEQUENCE_TYPE,
daa_file_basename=graftm_files.
diamond_assignment_output_basename(base_list[i]),
extra_args=diamond_performance_parameters)
for res in diamond_result.each([
SequenceSearchResult.QUERY_ID_FIELD,
SequenceSearchResult.HIT_ID_FIELD
]):
if res[0] in sequence_id_to_hit:
# do not accept duplicates
if sequence_id_to_hit[res[0]] != res[1]:
raise Exception(
"Diamond unexpectedly gave two hits for a single query sequence for %s"
% res[0])
else:
sequence_id_to_hit[res[0]] = res[1]
# Extract taxonomy of the best hit, and add in the no hits
sequence_id_to_taxonomy = {}
for seqio in SequenceIO().read_fasta_file(
search_result.hit_fasta()):
name = seqio.name
if name in sequence_id_to_hit:
# Add Root; to be in line with pplacer assignment method
sequence_id_to_taxonomy[name] = [
'Root'
] + taxonomy_definition[sequence_id_to_hit[name]]
else:
# picked up in the initial search (by hmmsearch, say), but diamond misses it
sequence_id_to_taxonomy[name] = ['Root']
results[base_list[i]] = sequence_id_to_taxonomy
return results
def main(self):
if self.args.subparser_name == 'graft':
if self.args.verbosity >= self._MIN_VERBOSITY_FOR_ART:
print('''
GRAFT
Joel Boyd, Ben Woodcroft
__/__
______|
_- - _ ________| |_____/
- - - | |____/_
- _ >>>> - >>>> ____|
- _- - - | ______
- _ |_____|
- |______
''')
self.graft()
elif self.args.subparser_name == 'create':
if self.args.verbosity >= self._MIN_VERBOSITY_FOR_ART:
print('''
CREATE
Joel Boyd, Ben Woodcroft
/
>a /
------------- /
>b | |
-------- >>> | GPKG |
>c |________|
----------
''')
if self.args.dereplication_level < 0:
logging.error(
"Invalid dereplication level selected! please enter a positive integer"
)
exit(1)
else:
if not self.args.sequences:
if not self.args.alignment and not self.args.rerooted_annotated_tree \
and not self.args.rerooted_tree:
logging.error(
"Some sort of sequence data must be provided to run graftM create"
)
exit(1)
if self.args.taxonomy:
if self.args.rerooted_annotated_tree:
logging.error(
"--taxonomy is incompatible with --rerooted_annotated_tree"
)
exit(1)
if self.args.taxtastic_taxonomy or self.args.taxtastic_seqinfo:
logging.error(
"--taxtastic_taxonomy and --taxtastic_seqinfo are incompatible with --taxonomy"
)
exit(1)
elif self.args.rerooted_annotated_tree:
if self.args.taxtastic_taxonomy or self.args.taxtastic_seqinfo:
logging.error(
"--taxtastic_taxonomy and --taxtastic_seqinfo are incompatible with --rerooted_annotated_tree"
)
exit(1)
else:
if not self.args.taxtastic_taxonomy or not self.args.taxtastic_seqinfo:
logging.error(
"--taxonomy, --rerooted_annotated_tree or --taxtastic_taxonomy/--taxtastic_seqinfo is required"
)
exit(1)
if bool(self.args.taxtastic_taxonomy) ^ bool(
self.args.taxtastic_seqinfo):
logging.error(
"Both or neither of --taxtastic_taxonomy and --taxtastic_seqinfo must be defined"
)
exit(1)
if self.args.alignment and self.args.hmm:
logging.warn(
"Using both --alignment and --hmm is rarely useful, but proceding on the assumption you understand."
)
if len([
_f for _f in [
self.args.rerooted_tree,
self.args.rerooted_annotated_tree, self.args.tree
] if _f
]) > 1:
logging.error("Only 1 input tree can be specified")
exit(1)
self.create.main(
dereplication_level=self.args.dereplication_level,
sequences=self.args.sequences,
alignment=self.args.alignment,
taxonomy=self.args.taxonomy,
rerooted_tree=self.args.rerooted_tree,
unrooted_tree=self.args.tree,
tree_log=self.args.tree_log,
prefix=self.args.output,
rerooted_annotated_tree=self.args.rerooted_annotated_tree,
min_aligned_percent=float(self.args.min_aligned_percent) /
100,
taxtastic_taxonomy=self.args.taxtastic_taxonomy,
taxtastic_seqinfo=self.args.taxtastic_seqinfo,
hmm=self.args.hmm,
search_hmm_files=self.args.search_hmm_files,
force=self.args.force,
threads=self.args.threads)
elif self.args.subparser_name == 'update':
logging.info(
"GraftM package %s specified to update with sequences in %s" %
(self.args.graftm_package, self.args.sequences))
if self.args.regenerate_diamond_db:
gpkg = GraftMPackage.acquire(self.args.graftm_package)
logging.info("Regenerating diamond DB..")
gpkg.create_diamond_db()
logging.info("Diamond database regenerated.")
return
elif not self.args.sequences:
logging.error(
"--sequences is required unless regenerating the diamond DB"
)
exit(1)
if not self.args.output:
if self.args.graftm_package.endswith(".gpkg"):
self.args.output = self.args.graftm_package.replace(
".gpkg", "-updated.gpkg")
else:
self.args.output = self.args.graftm_package + '-update.gpkg'
Update(
ExternalProgramSuite([
'taxit', 'FastTreeMP', 'hmmalign', 'mafft'
])).update(input_sequence_path=self.args.sequences,
input_taxonomy_path=self.args.taxonomy,
input_graftm_package_path=self.args.graftm_package,
output_graftm_package_path=self.args.output)
elif self.args.subparser_name == 'expand_search':
args = self.args
if not args.graftm_package and not args.search_hmm_files:
logging.error(
"expand_search mode requires either --graftm_package or --search_hmm_files"
)
exit(1)
if args.graftm_package:
pkg = GraftMPackage.acquire(args.graftm_package)
else:
pkg = None
expandsearcher = ExpandSearcher(
search_hmm_files=args.search_hmm_files,
maximum_range=args.maximum_range,
threads=args.threads,
evalue=args.evalue,
min_orf_length=args.min_orf_length,
graftm_package=pkg)
expandsearcher.generate_expand_search_database_from_contigs(
args.contigs,
args.output_hmm,
search_method=ExpandSearcher.HMM_SEARCH_METHOD)
elif self.args.subparser_name == 'tree':
if self.args.graftm_package:
# shim in the paths from the graftm package, not overwriting
# any of the provided paths.
gpkg = GraftMPackage.acquire(self.args.graftm_package)
if not self.args.rooted_tree:
self.args.rooted_tree = gpkg.reference_package_tree_path()
if not self.args.input_greengenes_taxonomy:
if not self.args.input_taxtastic_seqinfo:
self.args.input_taxtastic_seqinfo = gpkg.taxtastic_seqinfo_path(
)
if not self.args.input_taxtastic_taxonomy:
self.args.input_taxtastic_taxonomy = gpkg.taxtastic_taxonomy_path(
)
if self.args.rooted_tree:
if self.args.unrooted_tree:
logging.error(
"Both a rooted tree and an un-rooted tree were provided, so it's unclear what you are asking GraftM to do. \
If you're unsure see graftM tree -h")
exit(1)
elif self.args.reference_tree:
logging.error(
"Both a rooted tree and reference tree were provided, so it's unclear what you are asking GraftM to do. \
If you're unsure see graftM tree -h")
exit(1)
if not self.args.decorate:
logging.error(
"It seems a rooted tree has been provided, but --decorate has not been specified so it is unclear what you are asking graftM to do."
)
exit(1)
dec = Decorator(tree_path=self.args.rooted_tree)
elif self.args.unrooted_tree and self.args.reference_tree:
logging.debug(
"Using provided reference tree %s to reroot %s" %
(self.args.reference_tree, self.args.unrooted_tree))
dec = Decorator(reference_tree_path=self.args.reference_tree,
tree_path=self.args.unrooted_tree)
else:
logging.error(
"Some tree(s) must be provided, either a rooted tree or both an unrooted tree and a reference tree"
)
exit(1)
if self.args.output_taxonomy is None and self.args.output_tree is None:
logging.error(
"Either an output tree or taxonomy must be provided")
exit(1)
if self.args.input_greengenes_taxonomy:
if self.args.input_taxtastic_seqinfo or self.args.input_taxtastic_taxonomy:
logging.error(
"Both taxtastic and greengenes taxonomy were provided, so its unclear what taxonomy you want graftM to decorate with"
)
exit(1)
logging.debug("Using input GreenGenes style taxonomy file")
dec.main(self.args.input_greengenes_taxonomy,
self.args.output_tree, self.args.output_taxonomy,
self.args.no_unique_tax, self.args.decorate, None)
elif self.args.input_taxtastic_seqinfo and self.args.input_taxtastic_taxonomy:
logging.debug("Using input taxtastic style taxonomy/seqinfo")
dec.main(self.args.input_taxtastic_taxonomy,
self.args.output_tree, self.args.output_taxonomy,
self.args.no_unique_tax, self.args.decorate,
self.args.input_taxtastic_seqinfo)
else:
logging.error(
"Either a taxtastic taxonomy or seqinfo file was provided. GraftM cannot continue without both."
)
exit(1)
elif self.args.subparser_name == 'archive':
# Back slashes in the ASCII art are escaped.
if self.args.verbosity >= self._MIN_VERBOSITY_FOR_ART:
print("""
ARCHIVE
Joel Boyd, Ben Woodcroft
____.----.
____.----' \\
\\ \\
\\ \\
\\ \\
\\ ____.----'`--.__
\\___.----' | `--.____
/`-._ | __.-' \\
/ `-._ ___.---' \\
/ `-.____.---' \\ +------+
/ / | \\ \\ |`. |`.
/ / | \\ _.--' <===> | `+--+---+
`-. / | \\ __.--' | | | |
`-._ / | \\ __.--' | | | | |
| `-./ | \\_.-' | +---+--+ |
| | | `. | `. |
| | | `+------+
| | |
| | |
| | |
| | |
| | |
`-. | _.-'
`-. | __..--'
`-. | __.-'
`-|__.--'
""")
if self.args.create:
if self.args.extract:
logging.error(
"Please specify whether to either create or export a GraftM package"
)
exit(1)
if not self.args.graftm_package:
logging.error(
"Creating a GraftM package archive requires an package to be specified"
)
exit(1)
if not self.args.archive:
logging.error(
"Creating a GraftM package archive requires an output archive path to be specified"
)
exit(1)
archive = Archive()
archive.create(self.args.graftm_package,
self.args.archive,
force=self.args.force)
elif self.args.extract:
archive = Archive()
archive.extract(self.args.archive,
self.args.graftm_package,
force=self.args.force)
else:
logging.error(
"Please specify whether to either create or export a GraftM package"
)
exit(1)
else:
raise Exception("Unexpected subparser name %s" %
self.args.subparser_name)