def parse_shapemapper_output_files(self):
shapemapper_output_dir = os.path.join(os.path.dirname(self.experiment_settings.get_shapemapper_config_file()),
'output', 'counted_mutations_columns')
sample_name = self.lib_settings.sample_name
for rRNA_name in self.experiment_settings.rRNA_seqs:
shapemapper_output_file = os.path.join(shapemapper_output_dir, sample_name+'_'+rRNA_name+'.csv')
assert mod_utils.file_exists(shapemapper_output_file)
self.rRNA_mutation_data[rRNA_name] = rRNA_mutations(self, self.lib_settings, self.experiment_settings,
shapemapper_output_file)
def need_to_run_shapemapper(self):
for lib_setting in self.settings.iter_lib_settings():
for rRNA_name in self.settings.rRNA_seqs:
expected_file_name = os.path.join(
lib_setting.get_shapemapper_out_dir(),
'Pipeline_Modified_' + rRNA_name + '_mutation_counts.txt')
if not mod_utils.file_exists(expected_file_name):
return True
return False
def need_to_run_shapemapper(self):
if self.settings.get_property('force_shapemapper'):
return True
else:
shapemapper_output_dir = os.path.join(os.path.dirname(self.settings.get_shapemapper_config_file()),
'output', 'counted_mutations_columns')
for sample_name in self.settings.get_property('experimentals') + self.settings.get_property(
'no_mod_controls')+ self.settings.get_property('with_mod_controls'):
for rRNA_name in self.settings.rRNA_seqs:
expected_file_name = os.path.join(shapemapper_output_dir, sample_name+'_'+rRNA_name+'.csv')
if not mod_utils.file_exists(expected_file_name):
return True
return False
def star_index_exists(self):
star_index = self.get_star_index()
return mod_utils.file_exists(star_index)
def process_settings(self, settings_file):
"""
- reads the settings file and converts str to float, list, etc.
- stores result in self.settings as a dict()
"""
int_keys = [ 'first_base_to_keep', 'last_base_to_keep', 'min_post_adaptor_length', 'min_base_quality', 'min_mapping_quality']
float_keys = ['confidence_interval_cutoff', 'fold_change_cutoff']
str_keys = ['adaptor_sequence', 'rrna_fasta', 'experiment_name', 'shapemapper_ref_file', 'affected_nucleotides', 'pymol_base_script', 'pymol_base_script_colorchange', 'tptn_file_18s', 'tptn_file_25s', 'functional_groupings']
boolean_keys = ['collapse_identical_reads', 'force_read_resplit', 'force_remapping', 'force_recollapse',
'force_recount', 'force_index_rebuild', 'force_retrim', 'trim_adaptor', 'discard_untrimmed', 'force_shapemapper',
'make_interactive_plots']
list_str_keys = ['fastq_gz_files', 'sample_names', 'experimentals', 'no_mod_controls', 'with_mod_controls', 'exclude_constitutive']
#list_float_keys = ['probe_concentrations']
config = ConfigParser.ConfigParser()
config.read(settings_file)
settings = {}
for section in config.sections():
for option in config.options(section):
settings[option] = config.get(section, option)
settings[section] = True
for k in int_keys:
settings[k] = int(settings[k])
for k in str_keys:
settings[k] = settings[k]
for k in float_keys:
settings[k] = float(settings[k])
for k in boolean_keys:
if not settings[k].lower() in ['true', 'false']:
raise ValueError(
'Boolean value %s must be "true" or "false"' % k)
settings[k] = settings[k].lower() == 'true'
#for k in list_float_keys:
# settings[k] = map(float, simplejson.loads(settings[k]))
#for k in list_int_keys:
# settings[k] = map(int, simplejson.loads(settings[k]))
for k in list_str_keys:
settings[k] = simplejson.loads(settings[k])
self.fqdir = settings['fastq_dir']
self.sample_names = settings['sample_names']
self.experimentals = settings['experimentals']
self.no_mod_controls = settings['no_mod_controls']
self.with_mod_controls = settings['with_mod_controls']
self.exclude_constitutive = settings['exclude_constitutive']
try:
assert len(self.experimentals) == len(self.no_mod_controls)
assert len(self.experimentals) == len(self.with_mod_controls)
except:
print 'error: experimentals, no_mod_controls, and with_mod_controls should all be the same length'
print 'for mutation rate purposes, its ok to reuse a dataset here, it really doesnt matter'
try:
for sample_name in self.experimentals+self.no_mod_controls+self.with_mod_controls:
assert sample_name in self.sample_names
except:
print sample_name, ' not in sample names, make sure you are using regular quotation marks'
self.fastq_gz_file_handles = [os.path.join(self.fqdir, fastq_gz_file) for fastq_gz_file in
settings['fastq_gz_files']]
for file_handle in self.fastq_gz_file_handles:
assert mod_utils.file_exists(file_handle)
self.settings = settings
self.rdir = settings['results_dir']
mod_utils.make_dir(self.rdir)
shutil.copy(settings_file, self.rdir)
def mapped_reads_exist(self):
mapped_reads = self.get_mapped_reads_sam_gz()
return mod_utils.file_exists(mapped_reads)
def mapped_reads_exist(self):
mapped_reads = self.get_mapped_reads()
return mod_utils.file_exists(mapped_reads)
def adaptorless_reads_exist(self):
adaptorless_reads = self.get_adaptor_trimmed_reads()
return mod_utils.file_exists(adaptorless_reads)
def adaptorless_reads_exist(self):
adaptorless_reads = self.get_adaptor_trimmed_reads()
return mod_utils.file_exists(adaptorless_reads)
def collapsed_reads_exist(self):
collapsed_reads = self.get_collapsed_reads()
return mod_utils.file_exists(collapsed_reads)
def split_reads_exist(self):
split_reads = self.get_split_reads()
return mod_utils.file_exists(split_reads)
def mutation_counts_exists(self):
return mod_utils.file_exists(self.get_mutation_counts())
def positional_coverage_exists(self):
return mod_utils.file_exists(self.get_positional_coverage())
def read_5p_counts_exists(self):
return mod_utils.file_exists(self.get_read_5p_counts())
def rRNA_bowtie_index_exists(self):
return mod_utils.file_exists(self.get_rRNA_bowtie_index()+'.1.bt2')
def read_5p_counts_exists(self):
return mod_utils.file_exists(self.get_read_5p_counts())
def mutation_counts_exists(self):
return mod_utils.file_exists(self.get_mutation_counts())
def primerless_reads_exist(self):
primerless_reads = self.get_primer_trimmed_reads()
return mod_utils.file_exists(primerless_reads)
def trimmed_reads_exist(self):
trimmed_reads = self.get_trimmed_reads()
return mod_utils.file_exists(trimmed_reads)
def trimmed_reads_exist(self):
trimmed_reads = self.get_trimmed_reads()
return mod_utils.file_exists(trimmed_reads)
def process_settings(self, settings_file):
"""
- reads the settings file and converts str to float, list, etc.
- stores result in self.settings as a dict()
"""
int_keys = [
'first_base_to_keep', 'last_base_to_keep',
'min_post_adaptor_length', 'min_base_quality',
'min_mapping_quality'
]
float_keys = [
'confidence_interval_cutoff', 'fold_change_cutoff',
'winsorization_upper_limit'
]
str_keys = [
'adaptor_sequence', 'rrna_fasta', 'experiment_name',
'affected_nucleotides', 'pymol_base_script',
'pymol_base_script_colorchange', 'tptn_file_18s', 'tptn_file_25s'
]
boolean_keys = ['make_interactive_plots']
list_str_keys = [
'fastq_gz_files', 'sample_names', 'experimentals',
'no_mod_controls', 'with_mod_controls', 'exclude_constitutive'
]
#list_float_keys = ['probe_concentrations']
config = ConfigParser.ConfigParser()
config.read(settings_file)
settings = {}
for section in config.sections():
for option in config.options(section):
settings[option] = config.get(section, option)
settings[section] = True
for k in int_keys:
settings[k] = int(settings[k])
for k in str_keys:
settings[k] = settings[k]
for k in float_keys:
settings[k] = float(settings[k])
for k in boolean_keys:
if not settings[k].lower() in ['true', 'false']:
raise ValueError('Boolean value %s must be "true" or "false"' %
k)
settings[k] = settings[k].lower() == 'true'
#for k in list_float_keys:
# settings[k] = map(float, simplejson.loads(settings[k]))
#for k in list_int_keys:
# settings[k] = map(int, simplejson.loads(settings[k]))
for k in list_str_keys:
settings[k] = simplejson.loads(settings[k])
self.fqdir = settings['fastq_dir']
self.sample_names = settings['sample_names']
self.experimentals = settings['experimentals']
self.no_mod_controls = settings['no_mod_controls']
self.with_mod_controls = settings['with_mod_controls']
self.exclude_constitutive = settings['exclude_constitutive']
try:
assert len(self.experimentals) == len(self.no_mod_controls)
assert len(self.experimentals) == len(self.with_mod_controls)
except:
print 'error: experimentals, no_mod_controls, and with_mod_controls should all be the same length'
print 'for mutation rate purposes, its ok to reuse a dataset here, it really doesnt matter'
try:
for sample_name in self.experimentals + self.no_mod_controls + self.with_mod_controls:
assert sample_name in self.sample_names
except:
print sample_name, ' not in sample names, make sure you are using regular quotation marks'
self.fastq_gz_file_handles = [
os.path.join(self.fqdir, fastq_gz_file)
for fastq_gz_file in settings['fastq_gz_files']
]
for file_handle in self.fastq_gz_file_handles:
assert mod_utils.file_exists(file_handle)
self.settings = settings
self.rdir = settings['results_dir']
mod_utils.make_dir(self.rdir)
shutil.copy(settings_file, self.rdir)
def filtered_reads_exist(self):
filtered_reads = self.get_filtered_reads()
return mod_utils.file_exists(filtered_reads)
