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 show_installed_results():
"""
Show available results in your installation
"""
results = Result.get_all_results_as_list()
click.echo(results)
import os
from assnake.core.result import Result
result = Result.from_location(name='multiqc',
description='Multiqc report from FastQC',
result_type='quality_profile',
input_type='illumina_strand_file_set',
location=os.path.dirname(
os.path.abspath(__file__)))
import os
from assnake.core.result import Result
result = Result.from_location(name='cutadapt',
description='CUTADAPT',
result_type = 'preprocessing',
input_type='illumina_sample',
with_presets=False,
location=os.path.dirname(os.path.abspath(__file__)))
import click, os
from assnake.core.result import Result
result = Result.from_location(name='megahit',
description='Ultra-fast and memory-efficient NGS assembler',
result_type='assembly',
input_type='illumina_sample_set',
with_presets=True,
additional_inputs=[
click.option('--min-len', '-l', help='Minimum length of contigs', default=1000),
click.option('--overwrite', is_flag=True, help='Overwrite existing sample_set.tsv files', default=False)
],
location=os.path.dirname(os.path.abspath(__file__))
)
import click, glob, os
import assnake.api.loaders
import assnake
from assnake.cli.cli_utils import sample_set_construction_options, add_options, generic_command_individual_samples,\
generate_result_list, generic_command_dict_of_sample_sets, prepare_sample_set_tsv_and_get_results
from assnake.core.result import Result
@click.command('anvio-gen-db', short_help='Calculate completeness and contamination metrics for your MAGs')
@add_options(sample_set_construction_options)
@click.option('--min-len','-l', help='Minimum length of contigs', default=1000)
@click.option('--overwrite', is_flag=True, help='Overwrite existing sample_set.tsv files', default=False)
@click.pass_obj
def anvio_gen_db_invocation(config, min_len,overwrite, **kwargs):
# load sample sets
sample_sets = generic_command_dict_of_sample_sets(config, **kwargs)
sample_set_dir_wc = '{fs_prefix}/{df}/assembly/{sample_set}/'
result_wc = '{fs_prefix}/{df}/assembly/{sample_set}/megahit__v1.2.9__def/final_contigs__{mod}.db'
res_list = prepare_sample_set_tsv_and_get_results(sample_set_dir_wc, result_wc, df = kwargs['df'], sample_sets = sample_sets, mod = min_len, overwrite = overwrite)
config['requests'] += res_list
this_dir = os.path.dirname(os.path.abspath(__file__))
result = Result.from_location(name = 'anvio-gen-db', location = this_dir, input_type = 'illumina_sample_set', additional_inputs = None, invocation_command = anvio_gen_db_invocation)
import os
from assnake.core.result import Result
result = Result.from_location(name='trimmomatic',
description='Quality based trimming',
result_type='preprocessing',
input_type='illumina_sample',
with_presets=True,
static_files_dir_name='adapters',
location=os.path.dirname(
os.path.abspath(__file__)))
import click, os
from assnake.core.result import Result
result = Result.from_location(name='bwa-mem',
description='Map your samples on reference using BWA MEM',
result_type='aligner',
location=os.path.dirname(os.path.abspath(__file__)),
input_type='illumina_sample',
additional_inputs=[
click.option('--reference', help='Reference to use', required=True, type=click.STRING),
click.option('--params', help='Parameters to use', default='def', type=click.STRING ),
click.option('--version', help='Version of BWA', default='0.7.17', type=click.STRING )
])
import os
from assnake.core.result import Result
result = Result.from_location(
name='dada2-merge',
description='Merge strands of your samples with DADA2',
result_type='dada2',
input_type='illumina_sample_set',
with_presets=True,
preset_file_format='yaml',
location=os.path.dirname(os.path.abspath(__file__)))
import os
from assnake.core.result import Result
result = Result.from_location(
name='dada2-learn-errors',
description='Learn error profile of provided samples',
result_type='dada2',
input_type='illumina_sample_set',
with_presets=True,
preset_file_format='yaml',
location=os.path.dirname(os.path.abspath(__file__)))
import os
from assnake.core.result import Result
result = Result.from_location(name='count',
description='Count number of reads and basepairs in fastq file',
result_type = 'quality_profile',
input_type='illumina_strand_file',
location=os.path.dirname(os.path.abspath(__file__))
)
import click, os
from assnake.core.result import Result
result = Result.from_location(name='salmon',
description='Quasi transcript aligner',
result_type='aligner',
location=os.path.dirname(os.path.abspath(__file__)),
input_type='illumina_sample',
additional_inputs=[
click.option('--reference', help='Reference to use', required=True, type=click.STRING)
])
import click, os
from assnake.core.result import Result
result = Result.from_location(
name='metaphlan',
description='Taxonomic annotation based on marker genes with MetaPhlan 3',
result_type='taxonomy',
location=os.path.dirname(os.path.abspath(__file__)),
input_type='illumina_sample',
additional_inputs=[
click.option('--preset',
help='Preset to use. Available presets: ',
default='def'),
click.option('--version',
help='Version of metaphlan to use',
default='v3.0.0'),
click.option('--database',
help='Metaphlan database to use',
required=True,
default='v30_CHOCOPhlAn_201901')
])
import click, os
from assnake.core.result import Result
result = Result.from_location(
name='deblur',
description='Ultra-fast and memory-efficient NGS assembler',
result_type='assembly',
input_type='illumina_sample_set',
with_presets=True,
location=os.path.dirname(os.path.abspath(__file__)))
import click, glob, os
from assnake.core.sample_set import generic_command_individual_samples, generate_result_list
from assnake.core.command_builder import sample_set_construction_options, add_options
from assnake.core.result import Result
@click.command('seqtk-subsample', short_help='Subsample your reads')
@add_options(sample_set_construction_options)
@click.pass_obj
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)
this_dir = os.path.dirname(os.path.abspath(__file__))
result = Result.from_location(name='seqtk-subsample',
location=this_dir,
input_type='illumina_sample',
additional_inputs=None,
invocation_command=seqtk_subsample_invocation)
import click, glob, os
from assnake.core.sample_set import generic_command_individual_samples, generate_result_list
from assnake.core.command_builder import sample_set_construction_options, add_options
from assnake.core.result import Result
@click.command('remove-human-bbmap', short_help='Quality based trimming')
@add_options(sample_set_construction_options)
@click.pass_obj
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)
this_dir = os.path.dirname(os.path.abspath(__file__))
result = Result.from_location(name='remove-human-bbmap',
location=this_dir,
input_type='illumina_sample',
additional_inputs=None,
invocation_command=rmhumbbmap_invocation)
import os
from assnake.core.result import Result
result = Result.from_location(
name='vsearch-merge-pairs',
description='Merge paired-end reads into one sequence with Vsearch',
result_type='preprocessing',
input_type='illumina_sample',
with_presets=True,
preset_file_format='yaml',
location=os.path.dirname(os.path.abspath(__file__)))
import click, glob, os
from assnake.core.sample_set import generic_command_individual_samples, generate_result_list
from assnake.core.command_builder import sample_set_construction_options, add_options
from assnake.core.result import Result
this_dir = os.path.dirname(os.path.abspath(__file__))
result = Result.from_location(
name='remove-human-bbmap',
location=this_dir,
description='Human DNA removal',
result_type='preprocessing',
input_type='illumina_sample',
)
from assnake.core.sample_set import generic_command_individual_samples, generate_result_list
from assnake.core.command_builder import sample_set_construction_options, add_options
from assnake.core.result import Result
parameters = []
@click.command('bbtools-tadpole', short_help='Tadpole')
@click.option('--params', help='Parameters id to use. Available parameter sets: ' + str(parameters), required=False, default = 'def')
@add_options(sample_set_construction_options)
@click.pass_obj
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}]
this_dir = os.path.dirname(os.path.abspath(__file__))
result = Result.from_location(name = 'bbtools_tadpole', location = this_dir, input_type = 'illumina_sample', additional_inputs = None, invocation_command = bbtools_tadpole_invocation)
import os
from assnake.core.result import Result
result = Result.from_location(
name='fastqc',
description='Quality control checks on raw sequence data',
result_type='quality_profile',
input_type='illumina_strand_file',
location=os.path.dirname(os.path.abspath(__file__)))