def dada2_full(config, sample_set_name, learn_errors_preset, core_algo_preset, merged_preset, nonchim_preset, **kwargs):
# check if database initialized
if config['config'].get('dada2-silva_nr_v132', None) is None:
click.secho('Silva database not initialized!', fg='red')
click.echo('run ' + click.style('assnake init dada2-silva-db', bg='blue') + ' and follow instructions')
exit()
# load sample set
sample_set, sample_set_name_gen = generic_command_individual_samples(config, **kwargs)
if sample_set_name == '':
sample_set_name = sample_set_name_gen
learn_errors_result = Result.get_result_by_name('dada2-learn-errors')
learn_errors_preset = learn_errors_result.preset_manager.find_preset_by_name(learn_errors_preset)
if learn_errors_preset is not None:
learn_errors_preset = learn_errors_preset['full_name']
else:
click.secho('NO SUCH PRESET', fg='red')
exit()
# Prepare sample set file
res_list = prepare_sample_set_tsv_and_get_results(sample_set, sample_set_name,
wc_config = config['wc_config'],
learn_errors_preset = learn_errors_preset,
core_algo_preset = core_algo_preset,
merged_preset = merged_preset,
nonchim_preset = nonchim_preset)
config['requests'] += res_list
def map_bowtie2(config, **kwargs):
wc_str = '{fs_prefix}/{df}/mapped/bowtie2__{params}__{version}/{reference}/{df_sample}/{preproc}/{df_sample}.sam'
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
config['requests'] += generate_result_list(sample_set, wc_str, **kwargs)
config['requested_results'] += [{
'result': 'map-bowtie2',
'sample_set': sample_set
}]
def centrifuge_invocation(config, **kwargs):
wc_str = '{fs_prefix}/{df}/taxa/centr__{params}__v1.0.4_beta/{database}/{df_sample}/{preproc}/{df_sample}_report.tsv'
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
config['requests'] += generate_result_list(sample_set, wc_str, **kwargs)
config['requested_results'] += [{
'result': 'centrifuge',
'sample_set': sample_set
}]
def mp2_invocation(config, **kwargs):
wc_str = '{fs_prefix}/{df}/taxa/mp2__{params}__v3.0/{database}/{df_sample}/{preproc}/{df_sample}.mp2'
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
config['requests'] += generate_result_list(sample_set, wc_str, **kwargs)
config['requested_results'] += [{
'result': 'metaphlan2',
'sample_set': sample_set
}]
def mp2_rare_invocation(config, **kwargs):
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
props = ['0.1', '0.2', '0.3', '0.4', '0.5', '0.6', '0.7', '0.8', '0.9']
for p in props:
wc_str = '{{fs_prefix}}/{{df}}/taxa/mp2__{{params}}__v2.96.1/{{database}}/{{df_sample}}/{{preproc}}/{{df_sample}}_sbsmpl{prop}.mp2'.format(
prop=p)
config['requests'] += generate_result_list(sample_set, wc_str,
**kwargs)
config['requested_results'] += [{
'result': 'metaphlan2',
'sample_set': sample_set
}]
def bbtools_tadpole_invocation(config, params, **kwargs):
wc_str = '{fs_prefix}/{df}/reads/{preproc}__bbtdpl_{params}/{df_sample}_R1.fastq.gz'
kwargs.update({'params': params})
if (kwargs['df'] is None):
previous_requested_result = config['requested_results'][-1]
if previous_requested_result['preprocessing']:
sample_set = previous_requested_result['sample_set']
sample_set['preproc'] = sample_set['preproc']+'__'+previous_requested_result['preprocessing_addition']
else:
sample_set, sample_set_name = generic_command_individual_samples(config, **kwargs)
config['requests'] += generate_result_list(sample_set, wc_str, **kwargs)
config['requested_results'] += [{'result': 'bbtools-tadpole', 'sample_set': sample_set, 'preprocessing': True}]
def result_invocation(config, **kwargs):
# kwargs.update({'params': params})
if 'preset' in kwargs.keys(
) and self.preset_manager is not None:
preset = self.preset_manager.find_preset_by_name(
kwargs['preset'])
if preset is not None:
kwargs['preset'] = preset['full_name']
else:
click.secho('NO SUCH PRESET', fg='red')
exit()
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
config['requests'] += generate_result_list(
sample_set, self.result_wc, **kwargs)
def map_bwa(config, reference, params, version, **kwargs):
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
res_list = []
for s in sample_set.samples_pd.to_dict(orient='records'):
preprocessing = s['preproc']
res_list.append(
'{fs_prefix}/{df}/mapped/bwa__{version}__{params}/{reference}/{sample}/{preproc}/{sample}.bam'
.format(fs_prefix=s['fs_prefix'].rstrip('\/'),
df=s['df'],
preproc=preprocessing,
sample=s['fs_name'],
reference=reference,
params=params,
version=version))
config['requests'] += res_list
def feature_counts(config, reference, **kwargs):
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
res_list = []
for s in sample_set.to_dict(orient='records'):
preprocessing = s['preproc']
res_list.append(
'{fs_prefix}/{df}/mapped/{mapper}__{version}__{params}/{reference}/{df_sample}/{preproc}/{df_sample}_feature_counts.tsv'
.format(fs_prefix=s['fs_prefix'].rstrip('\/'),
df=s['df'],
preproc=preprocessing,
df_sample=s['df_sample'],
reference=reference,
mapper='bwa',
params='def',
version='0.7.17'))
print(res_list)
config['requests'] += res_list
def bbtools_tadpole_invocation(config, params, **kwargs):
wc_str = '{fs_prefix}/{df}/reads/{preproc}__bbtsbsmpl_{params}/{df_sample}_R1.fastq.gz'
kwargs.update({'params': params})
sample_set, sample_set_name = generic_command_individual_samples(config, **kwargs)
config['requests'] += generate_result_list(sample_set, wc_str, **kwargs)
def result_invocation(config, strand, **kwargs):
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
config['requests'] += generate_result_list(sample_set,
self.result_wc,
strand=strand)
def seqtk_subsample_invocation(config, **kwargs):
# print(config['wc_config'])
wc_str = '{fs_prefix}/{df}/reads/{preproc}__seqtk_sbsmpl/{df_sample}_R1.fastq.gz'
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
config['requests'] += generate_result_list(sample_set, wc_str, **kwargs)
def rmhumbbmap_invocation(config, **kwargs):
wc_str = '{fs_prefix}/{df}/reads/{preproc}__rmhum_bbmap/{df_sample}_R1.fastq.gz'
sample_set, sample_set_name = generic_command_individual_samples(
config, **kwargs)
config['requests'] += generate_result_list(sample_set, wc_str, **kwargs)
