4.1.1.3.1.3. datanator.data_source.process_rna_seq package

4.1.1.3.1.3.1. Submodules

4.1.1.3.1.3.2. datanator.data_source.process_rna_seq.command_line_core module

class datanator.data_source.process_rna_seq.command_line_core.App(label=None, **kw)

Bases: cement.core.foundation.App

class Meta

Bases: object

base_controller = 'base'

handlers = [<class 'datanator.data_source.process_rna_seq.command_line_core.BaseController'>, <class 'datanator.data_source.process_rna_seq.command_line_core.DownloadCDNA'>, <class 'datanator.data_source.process_rna_seq.command_line_core.DownloadFASTQ'>, <class 'datanator.data_source.process_rna_seq.command_line_core.ProcessCDNA'>, <class 'datanator.data_source.process_rna_seq.command_line_core.ProcessFASTQ'>, <class 'datanator.data_source.process_rna_seq.command_line_core.DeleteCDNAFiles'>, <class 'datanator.data_source.process_rna_seq.command_line_core.DeleteFASTQFiles'>]

label = 'datanator'

class datanator.data_source.process_rna_seq.command_line_core.BaseController(*args, **kw)

Bases: cement.ext.ext_argparse.ArgparseController

class Meta

Bases: object

description = 'Utilities for aggregating data for biochemical models'

label = 'base'

class datanator.data_source.process_rna_seq.command_line_core.DeleteCDNAFiles(*args, **kw)

Bases: cement.ext.ext_argparse.ArgparseController

class Meta

Bases: object

arguments = [(['strain_name'], {'type': <class 'str'>, 'help': 'Name of the strain'}), (['temp_directory'], {'type': <class 'str'>, 'help': 'location where strain is saved'})]

description = 'Delete CDNA files'

label = 'delete-cdna'

stacked_on = 'base'

stacked_type = 'nested'

class datanator.data_source.process_rna_seq.command_line_core.DeleteFASTQFiles(*args, **kw)

Bases: cement.ext.ext_argparse.ArgparseController

class Meta

Bases: object

arguments = [(['experiment_name'], {'type': <class 'str'>, 'help': 'Name of the experiment'}), (['sample_name'], {'type': <class 'str'>, 'help': 'Name of the sample'}), (['temp_directory'], {'type': <class 'str'>, 'help': 'location where strain is saved'})]

description = 'Delete fastq files'

label = 'delete-fastq'

stacked_on = 'base'

stacked_type = 'nested'

class datanator.data_source.process_rna_seq.command_line_core.DownloadCDNA(*args, **kw)

Bases: cement.ext.ext_argparse.ArgparseController

class Meta

Bases: object

arguments = [(['strain_name'], {'type': <class 'str'>, 'help': 'strain of the reference genome'}), (['url'], {'type': <class 'str'>, 'help': 'url to download the reference genome'}), (['temp_directory'], {'type': <class 'str'>, 'help': 'location to save the reference genome'})]

description = 'Download CDNA file into specified directory'

label = 'download-cdna'

stacked_on = 'base'

stacked_type = 'nested'

class datanator.data_source.process_rna_seq.command_line_core.DownloadFASTQ(*args, **kw)

Bases: cement.ext.ext_argparse.ArgparseController

class Meta

Bases: object

arguments = [(['experiment_name'], {'type': <class 'str'>, 'help': 'Name of the experiment'}), (['sample_name'], {'type': <class 'str'>, 'help': 'Name of the sample'}), (['temp_directory'], {'type': <class 'str'>, 'help': 'location to save the fastq files'}), (['fastq_urls'], {'type': <class 'str'>, 'help': 'space seperated list of fastq urls'})]

description = 'Download FASTQ files into specified directory'

label = 'download-fastq'

stacked_on = 'base'

stacked_type = 'nested'

class datanator.data_source.process_rna_seq.command_line_core.ProcessCDNA(*args, **kw)

Bases: cement.ext.ext_argparse.ArgparseController

class Meta

Bases: object

arguments = [(['strain_name'], {'type': <class 'str'>, 'help': 'strain of the reference genome'}), (['output_directory'], {'type': <class 'str'>, 'help': 'location to save index file'}), (['temp_directory'], {'type': <class 'str'>, 'help': 'location of the reference genomes'})]

description = 'Process a CDNA file into a kallisto index file and save it to a specified directory'

label = 'process-cdna'

stacked_on = 'base'

stacked_type = 'nested'

class datanator.data_source.process_rna_seq.command_line_core.ProcessFASTQ(*args, **kw)

Bases: cement.ext.ext_argparse.ArgparseController

class Meta

Bases: object

arguments = [(['experiment_name'], {'type': <class 'str'>, 'help': 'Name of the experiment'}), (['sample_name'], {'type': <class 'str'>, 'help': 'Name of the sample'}), (['strain_name'], {'type': <class 'str'>, 'help': 'strain name of the reference genome'}), (['num_fastq_files'], {'type': <class 'int'>, 'help': 'Number of FASTQ files for sample'}), (['read_type'], {'type': <class 'str'>, 'help': 'Read type of RNA-seq experiment'}), (['output_directory'], {'type': <class 'str'>, 'help': 'location to save the processed files'}), (['temp_directory'], {'type': <class 'str'>, 'help': 'location of the fastq files'})]

description = 'Process FASTQ files'

label = 'process-fastq'

stacked_on = 'base'

stacked_type = 'nested'

datanator.data_source.process_rna_seq.command_line_core.main()

4.1.1.3.1.3.3. datanator.data_source.process_rna_seq.core module

datanator.data_source.process_rna_seq.core.delete_cdna_files(strain_name, temp_directory)

datanator.data_source.process_rna_seq.core.delete_fastq_files(experiment_name, sample_name, temp_directory)

datanator.data_source.process_rna_seq.core.download_cdna(ref_genome, strain_name, url, temp_directory)

datanator.data_source.process_rna_seq.core.download_fastq(experiment_name, sample_name, temp_directory, fastq_urls)

datanator.data_source.process_rna_seq.core.get_processed_data_samples(samples, output_directory, temp_directory)

datanator.data_source.process_rna_seq.core.process_cdna(strain_name, output_directory, temp_directory)

datanator.data_source.process_rna_seq.core.process_fastq(experiment_name, sample_name, strain_name, num_fastq_files, read_type, output_directory, temp_directory)

4.1.1.3.1.3.4. datanator.data_source.process_rna_seq.download_cdna module

datanator.data_source.process_rna_seq.download_cdna.download_cdna(ensembl_info, top_dir)

datanator.data_source.process_rna_seq.download_cdna.process_cdna(ensembl_info, top_dir)

datanator.data_source.process_rna_seq.download_cdna.run(ensembl_info, top_dir)

Downloads the CDNA for a given sample, and creates a kallisto index file.

The CDNA file is stored in a “CDNA” subdirectory within the top directory. The kalliso index files are stored within “kallisto_index_files” subdirectory within the top directory

Parameters

• experiment (array_express.Experiment) – the array express experiment

• top_dirname (str) – the name of the directory where the overall data is being stored

4.1.1.3.1.3.5. Module contents