def __init__(self,
input_fasta,
target,
output=None,
binary="blastn",
makeblastdb="makeblastdb",
log="/dev/null"):
self.binary = binary
self.params = ''
self.input = input_fasta
self.target = target
self.output = output
self.makeblastdb = makeblastdb
self.log = log
self.outfmt = "'6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qlen slen'"
self.binary_check()
self.version_check()
if not output:
self.output = get_temporary_file_name()
else:
self.output = output
self.search_cmd_tmpl = "%(binary)s -query %(input)s -db %(target)s -out %(output)s -outfmt %(outfmt)s %(params)s >> %(log)s 2>&1"
self.makeblastdb_cmd_tmpl = "%(makeblastdb)s -in %(target)s -dbtype nucl >> %(log)s 2>&1"
self.results_dict = {}
def __init__(self, input_fasta, target, output = None, binary = "blastn", makeblastdb = "makeblastdb", log = "/dev/null"):
self.binary = binary
self.params = ''
self.input = input_fasta
self.target = target
self.output = output
self.makeblastdb = makeblastdb
self.log = log
self.outfmt = "'6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qlen slen'"
self.binary_check()
self.version_check()
if not output:
self.output = get_temporary_file_name()
else:
self.output = output
self.search_cmd_tmpl = "%(binary)s -query %(input)s -db %(target)s -out %(output)s -outfmt %(outfmt)s %(params)s >> %(log)s 2>&1"
self.makeblastdb_cmd_tmpl = "%(makeblastdb)s -in %(target)s -dbtype nucl >> %(log)s 2>&1"
self.results_dict = {}
def generate_exclusive_figures(_object):
import Oligotyping
scripts_dir_path = os.path.dirname(Oligotyping.__file__)
exclusive_figures_dict = {}
sample_mapping_dict = get_sample_mapping_dict(_object.sample_mapping)
for category in sample_mapping_dict:
exclusive_figures_dict[category] = {}
samples = sample_mapping_dict[category].keys()
# double filter: first makes sure sample was not removed from the analysis due to losing all its reads during the
# refinement, second makes sure that sample was actually mapped to something in the sample mapping file.
samples = filter(lambda s: sample_mapping_dict[category][s],
filter(lambda s: s in _object.samples, samples))
samples.sort()
mapping_file_path = get_temporary_file_name('%s-' % category,
'-mapping.txt',
_object.tmp_directory)
mapping_file = open(mapping_file_path, 'w')
mapping_file.write('samples\t%s\n' % (category))
for sample in samples:
mapping_file.write('%s\t%s\n' %
(sample, sample_mapping_dict[category][sample]))
mapping_file.close()
if samples == _object.samples:
matrix_percent_path = _object.matrix_percent_file_path
matrix_count_path = _object.matrix_count_file_path
else:
matrix_percent_path = get_temporary_file_name(
'%s-' % category, '-matrix-percent.txt', _object.tmp_directory)
matrix_count_path = get_temporary_file_name(
'%s-' % category, '-matrix-count.txt', _object.tmp_directory)
if store_filtered_matrix(_object.matrix_percent_file_path,
matrix_percent_path, samples) < 3:
_object.logger.info("skipping exclusive figs for '%s'; less than 3 samples were left in MP"\
% (category))
continue
if store_filtered_matrix(_object.matrix_count_file_path,
matrix_count_path, samples) < 3:
_object.logger.info("skipping exclusive figs for '%s'; less than 3 samples were left in MC"\
% (category))
continue
# ready to roll.
_object.logger.info("exclusive figs for '%s' with %d samples; mapping: '%s', MP: '%s', MC: '%s'"\
% (category, len(samples), mapping_file_path, matrix_percent_path, matrix_count_path))
for (analysis, script, output_dir) in [
('NMDS Analysis', '../Scripts/R/metaMDS-analysis-with-metadata.R',
'nmds_analysis')
]:
exclusive_figures_dict[category][output_dir] = {}
target_dir = _object.generate_output_destination(
'%s/%s/%s' % (os.path.basename(
_object.figures_directory), category, output_dir),
directory=True)
for (distance_metric,
matrix_file) in [("canberra", matrix_percent_path),
("kulczynski", matrix_percent_path),
("jaccard", matrix_percent_path),
("horn", matrix_percent_path),
("bray", matrix_percent_path)]:
output_prefix = os.path.join(target_dir, distance_metric)
cmd_line = (
'%s "%s" "%s" %s "%s" "%s" "%s" >> "%s" 2>&1' %
(os.path.join(scripts_dir_path, script), matrix_file,
mapping_file_path, distance_metric, category,
_object.project, output_prefix, _object.log_file_path))
_object.progress.update('%s "%s" for "%s" ...' %
(analysis, distance_metric, category))
_object.logger.info('exclusive figure: %s' % (cmd_line))
run_command(cmd_line)
exclusive_figures_dict[category][output_dir][
distance_metric] = output_prefix
# heatmap
for (analysis, script, output_dir) in [
('Heatmap Analysis', '../Scripts/R/heatmap.R', 'heatmap_analysis')
]:
exclusive_figures_dict[category][output_dir] = {}
target_dir = _object.generate_output_destination(
'%s/%s/%s' % (os.path.basename(
_object.figures_directory), category, output_dir),
directory=True)
for (distance_metric,
matrix_file) in [("canberra", matrix_percent_path),
("kulczynski", matrix_percent_path),
("jaccard", matrix_percent_path),
("horn", matrix_percent_path),
("bray", matrix_percent_path)]:
output_prefix = os.path.join(target_dir, distance_metric)
cmd_line = (
'%s "%s" -m "%s" -d %s --title "%s" -o "%s" >> "%s" 2>&1' %
(os.path.join(scripts_dir_path, script), matrix_file,
mapping_file_path, distance_metric, _object.project,
output_prefix, _object.log_file_path))
_object.progress.update('%s "%s" for "%s" ...' %
(analysis, distance_metric, category))
_object.logger.info('exclusive figure: %s' % (cmd_line))
run_command(cmd_line)
exclusive_figures_dict[category][output_dir][
distance_metric] = output_prefix
return exclusive_figures_dict
def generate_exclusive_figures(_object):
import Oligotyping
scripts_dir_path = os.path.dirname(Oligotyping.__file__)
exclusive_figures_dict = {}
sample_mapping_dict = get_sample_mapping_dict(_object.sample_mapping)
for category in sample_mapping_dict:
exclusive_figures_dict[category] = {}
samples = sample_mapping_dict[category].keys()
# double filter: first makes sure sample was not removed from the analysis due to losing all its reads during the
#  refinement, second makes sure that sample was actually mapped to something in the sample mapping file.
samples = filter(lambda s: sample_mapping_dict[category][s], filter(lambda s: s in _object.samples, samples))
samples.sort()
mapping_file_path = get_temporary_file_name("%s-" % category, "-mapping.txt", _object.tmp_directory)
mapping_file = open(mapping_file_path, "w")
mapping_file.write("samples\t%s\n" % (category))
for sample in samples:
mapping_file.write("%s\t%s\n" % (sample, sample_mapping_dict[category][sample]))
mapping_file.close()
if samples == _object.samples:
matrix_percent_path = _object.matrix_percent_file_path
matrix_count_path = _object.matrix_count_file_path
else:
matrix_percent_path = get_temporary_file_name(
"%s-" % category, "-matrix-percent.txt", _object.tmp_directory
)
matrix_count_path = get_temporary_file_name("%s-" % category, "-matrix-count.txt", _object.tmp_directory)
if store_filtered_matrix(_object.matrix_percent_file_path, matrix_percent_path, samples) < 3:
_object.logger.info(
"skipping exclusive figs for '%s'; less than 3 samples were left in MP" % (category)
)
continue
if store_filtered_matrix(_object.matrix_count_file_path, matrix_count_path, samples) < 3:
_object.logger.info(
"skipping exclusive figs for '%s'; less than 3 samples were left in MC" % (category)
)
continue
# ready to roll.
_object.logger.info(
"exclusive figs for '%s' with %d samples; mapping: '%s', MP: '%s', MC: '%s'"
% (category, len(samples), mapping_file_path, matrix_percent_path, matrix_count_path)
)
for (analysis, script, output_dir) in [
("NMDS Analysis", "../Scripts/R/metaMDS-analysis-with-metadata.R", "nmds_analysis")
]:
exclusive_figures_dict[category][output_dir] = {}
target_dir = _object.generate_output_destination(
"%s/%s/%s" % (os.path.basename(_object.figures_directory), category, output_dir), directory=True
)
for (distance_metric, matrix_file) in [
("canberra", matrix_percent_path),
("kulczynski", matrix_percent_path),
("jaccard", matrix_percent_path),
("horn", matrix_percent_path),
("bray", matrix_percent_path),
]:
output_prefix = os.path.join(target_dir, distance_metric)
cmd_line = '%s -o "%s" -d "%s" -m "%s" --title "%s" "%s" "%s" >> "%s" 2>&1' % (
os.path.join(scripts_dir_path, script),
output_prefix,
distance_metric,
category,
_object.project,
matrix_file,
mapping_file_path,
_object.log_file_path,
)
_object.progress.update('%s "%s" for "%s" ...' % (analysis, distance_metric, category))
_object.logger.info("exclusive figure: %s" % (cmd_line))
run_command(cmd_line)
exclusive_figures_dict[category][output_dir][distance_metric] = output_prefix
# heatmap
for (analysis, script, output_dir) in [("Heatmap Analysis", "../Scripts/R/heatmap.R", "heatmap_analysis")]:
exclusive_figures_dict[category][output_dir] = {}
target_dir = _object.generate_output_destination(
"%s/%s/%s" % (os.path.basename(_object.figures_directory), category, output_dir), directory=True
)
for (distance_metric, matrix_file) in [
("canberra", matrix_percent_path),
("kulczynski", matrix_percent_path),
("jaccard", matrix_percent_path),
("horn", matrix_percent_path),
("bray", matrix_percent_path),
]:
output_prefix = os.path.join(target_dir, distance_metric)
cmd_line = '%s "%s" -m "%s" -d %s --title "%s" -o "%s" >> "%s" 2>&1' % (
os.path.join(scripts_dir_path, script),
matrix_file,
mapping_file_path,
distance_metric,
_object.project,
output_prefix,
_object.log_file_path,
)
_object.progress.update('%s "%s" for "%s" ...' % (analysis, distance_metric, category))
_object.logger.info("exclusive figure: %s" % (cmd_line))
run_command(cmd_line)
exclusive_figures_dict[category][output_dir][distance_metric] = output_prefix
return exclusive_figures_dict
