def get_parser(): parser = get_default_argparser_with_base_opts( version=__version__, description=__doc__, default_level="CRITICAL") parser.add_argument('file', help="BAM, FASTA, or DataSet XML file") parser.add_argument("-c", dest="use_termcolor", action="store_true") parser.add_argument("--quick", dest="quick", action="store_true", help="Limits validation to the first 100 records "+ "(plus file header); equivalent to "+ "--max-records=100") parser.add_argument("--max", dest="max_errors", action="store", type=int, help="Exit after MAX_ERRORS have been recorded "+ "(DEFAULT: check entire file)") parser.add_argument("--max-records", dest="max_records", action="store", type=int, help="Exit after MAX_RECORDS have been inspected "+ "(DEFAULT: check entire file)") parser.add_argument("--type", dest="file_type", action="store", choices=["BAM", "Fasta"] + dataset.DatasetTypes.ALL, help="Use the specified file type instead of guessing") parser.add_argument("--index", dest="validate_index", action="store_true", help="Require index files (.fai or .pbi)") parser.add_argument("--strict", dest="strict", action="store_true", help="Turn on additional validation, primarily for "+ "DataSet XML") parser.add_argument("-x", "--xunit-out", dest="xunit_out", action="store", default=None, help="Xunit test results for Jenkins") g1 = parser.add_argument_group('bam', "BAM options") g2 = parser.add_argument_group('fasta', "Fasta options") bam.get_format_specific_args(g1) fasta.get_format_specific_args(g2) return parser
def get_parser(): p = get_default_argparser_with_base_opts( version=VERSION, description=__doc__, default_level="WARN") p.add_argument("input_bam", help="Input BAM or DataSet from which reads will be read") p.add_argument("output_bam", nargs='?', default=None, help="Output BAM or DataSet to which filtered reads will " "be written") p.add_argument("--show-zmws", action="store_true", default=False, help="Print a list of ZMWs and exit") p.add_argument("--whitelist", action="store", default=None, help="Comma-separated list of ZMWs, or file containing " + "whitelist of one hole number per line, or " + "BAM/DataSet file from which to extract ZMWs") p.add_argument("--blacklist", action="store", default=None, help="Opposite of --whitelist, specifies ZMWs to discard") p.add_argument("--percentage", action="store", type=float, default=None, help="If you prefer to recover a percentage of a SMRTcell " "rather than a specific list of reads specify that " "percentage (range 0-100) here") p.add_argument("-n", "--count", action="store", type=int, default=None, help="Recover a specific number of ZMWs picked at random") p.add_argument("-s", "--seed", action="store", type=int, default=None, help="Random seed for selecting a percentage of reads") p.add_argument("--ignore-metadata", action="store_true", help="Discard input DataSet metadata") p.add_argument("--anonymize", action="store_true", help="Randomize sequences for privacy") return p
def get_parser(): p = get_default_argparser_with_base_opts( version="0.1", description=__doc__) p.add_argument("testkit_cfg") p.add_argument("-u", "--host", dest="host", action="store", default=os.environ.get("PB_SERVICE_HOST", "http://localhost")) p.add_argument("-p", "--port", dest="port", action="store", type=int, default=int(os.environ.get("PB_SERVICE_PORT", "8081")), help="Services port number") p.add_argument("-x", "--xunit", dest="xml_out", default="test-output.xml", help="Output XUnit test results") p.add_argument("-t", "--timeout", dest="time_out", type=int, default=1800, help="Timeout for blocking after job submission") p.add_argument("-s", "--sleep", dest="sleep", type=int, default=2, help="Sleep time after job submission") p.add_argument("--ignore-test-failures", dest="ignore_test_failures", action="store_true", help="Only exit with non-zero return code if the job "+ "itself failed, regardless of test outcome") p.add_argument("--import-only", dest="import_only", action="store_true", help="Import datasets without running pipeline") p.add_argument("--only-tests", dest="test_job_id", action="store", type=int, default=None, help="Run tests on an existing smrtlink job") return p
def _get_parser(): p = get_default_argparser_with_base_opts( version="0.1", description=__doc__) p.add_argument("testkit_cfg") p.add_argument("-u", "--host", dest="host", action="store", default="http://localhost") p.add_argument("-p", "--port", dest="port", action="store", type=int, default=8081, help="Port number") p.add_argument("-x", "--xunit", dest="xml_out", default="test-output.xml", help="Output XUnit test results") p.add_argument("-t", "--timeout", dest="time_out", type=int, default=1800, help="Timeout for blocking after job submission") p.add_argument("-s", "--sleep", dest="sleep", type=int, default=2, help="Sleep time after job submission") p.add_argument("--ignore-test-failures", dest="ignore_test_failures", action="store_true", help="Only exit with non-zero return code if the job "+ "itself failed, regardless of test outcome") p.add_argument("--import-only", dest="import_only", action="store_true", help="Import datasets without running pipeline") p.add_argument("--only-tests", dest="test_job_id", action="store", type=int, default=None, help="Run tests on an existing smrtlink job") return p
def _get_parser(): p = get_default_argparser_with_base_opts( version="0.1", description=__doc__) p.add_argument("junit_file", nargs="+", type=argparse.FileType('r')) p.add_argument("-o", "--output-file", dest="output_file", action="store", default="junit_results_merged.xml") return p
def get_parser(): """Set up and return argument parser.""" p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument("in_fn", type=str, help="Input DataSet or DataStore") p.add_argument("out_fn", type=str, help="Output DataSet or DataStore") return p
def get_parser(): p = get_default_argparser_with_base_opts(version=VERSION, description=__doc__, default_level="WARN") p.add_argument("input_bam", help="Input BAM or DataSet from which reads will be read") p.add_argument("output_bam", nargs='?', default=None, help="Output BAM or DataSet to which filtered reads will " "be written") p.add_argument("--show-zmws", action="store_true", default=False, help="Print a list of ZMWs and exit") p.add_argument("--whitelist", action="store", default=None, help="Comma-separated list of ZMWs, or file containing " + "whitelist of one hole number per line, or " + "BAM/DataSet file from which to extract ZMWs") p.add_argument("--blacklist", action="store", default=None, help="Opposite of --whitelist, specifies ZMWs to discard") p.add_argument("--percentage", action="store", type=float, default=None, help="If you prefer to recover a percentage of a SMRTcell " "rather than a specific list of reads specify that " "percentage (range 0-100) here") p.add_argument("-n", "--count", action="store", type=int, default=None, help="Recover a specific number of ZMWs picked at random") p.add_argument("-s", "--seed", action="store", type=int, default=None, help="Random seed for selecting a percentage of reads") p.add_argument("--ignore-metadata", action="store_true", help="Discard input DataSet metadata") p.add_argument("--relative", action="store_true", help="Make external resource paths relative") p.add_argument("--anonymize", action="store_true", help="Randomize sequences for privacy") p.add_argument("--barcodes", action="store_true", help="Indicates that the whitelist or blacklist contains " + "barcode indices instead of ZMW numbers") return p
def get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__) p.add_argument("testkit_cfg_fofn", nargs="+", type=argparse.FileType("r"), help="Text file listing testkit.cfg files to run; you " + "may provide more than one of these") p.add_argument("-u", "--host", dest="host", action="store", default=Constants.HOST) p.add_argument("-p", "--port", dest="port", action="store", default=Constants.PORT, help="Port number") p.add_argument("-n", "--nworkers", type=int, default=Constants.NPROC, help="Number of jobs to concurrently run.") p.add_argument("-t", "--timeout", dest="time_out", type=int, default=1800, help="Timeout for blocking after job submission") p.add_argument("-s", "--sleep", dest="sleep", type=int, default=Constants.SLEEP_TIME, help="Sleep time after job submission") p.add_argument("--ignore-test-failures", dest="ignore_test_failures", action="store_true", help="Only exit with non-zero return code if the job " + "itself failed, regardless of test outcome") p.add_argument("--import-only", dest="import_only", action="store_true", help="Import datasets without running pipelines") p.add_argument("-j", "--junit-xml", dest="junit_out", action="store", default="junit_combined_results.xml", help="JUnit output file for all tests") p.add_argument("-x", "--nunit-xml", dest="nunit_out", action="store", default="nunit_combined_results.xml", help="NUnit output file for all tests") return p
def _get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument("fastq_in", help="Input FASTQ file") p.add_argument("summary_csv", help="Input Summary CSV file") p.add_argument("subreads_in", help="Input SubreadSet XML") p.add_argument("zip_out", help="Output ZIP file") return p
def get_parser(): """Define Parser. Use the helper methods in validators to validate input""" p = get_default_argparser_with_base_opts(__version__, __doc__) f = p.add_argument f('path_to_file', type=validate_file, help="Path to File") f('output_file', help="Path to output TXT file") f('--nrecords', type=int, default=10, help="Number of records to write") return p
def _get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument("consensus_in", help="Input consensus FASTQ file") p.add_argument("chimeras_in", help="Input chimeras FASTQ file") p.add_argument("subreads_in", help="Input SubreadSet XML") p.add_argument("consensus_out", help="Output consensus ZIP file") p.add_argument("chimeras_out", help="Output chimeras ZIP file") return p
def _get_parser(): p = get_default_argparser_with_base_opts( version=__version__, description=__doc__, default_level="INFO") p.add_argument("ccs_in", help="Input ConsensusReadSet") p.add_argument("subreads_in", help="Input SubreadSet") p.add_argument("ccs_out", help="Output ConsensusReadSet") p.add_argument("--use-run-design-uuid", action="store_true", default=False, help="Use pre-defined UUID generated by Run Design") return p
def _get_parser(): desc = "Custom PipelineTemplate Registry to write pipeline templates to output directory" p = get_default_argparser_with_base_opts(__version__, desc, default_level=logging.ERROR) p.add_argument('output_dir', help="Path to output directory") p.add_argument('--with-xml', action="store_true", default=False, help="Also Write Pipeline Templates as XML") return p
def get_parser(): desc = "Generate Pipeline documentation from a directory of Resolved Pipeline Templates" p = get_default_argparser_with_base_opts(__version__, desc) f = p.add_argument f("pipeline_dir", type=validate_dir, help="Path to Pipeline Template JSON Dir") f('-o', "--output-dir", default="pipeline-docs", help="Path to RST Output Dir") f('-t', '--title', default="PacBio Pipelines", help="Title of Pipeline documents") f('-d', '--doc-version', default="0.1.0", help="Version of Pipeline documents") return p
def get_parser(): p = get_default_argparser_with_base_opts(__version__, "Stress Tool") f = p.add_argument f('--host', default="localhost", help="Host name") f('--port', default=8070, type=int, help="Port") f('-n', '--nprocesses', default=10, type=int, help="Number of worker processes to launch") # FIXME this naming is terrible f('-x', default=5, type=int, help="Total number of tasks will be ~ 3 x") f('--profile', default="profile.json", help="Path to output profile.json") return p
def _get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument("output_file", help="Gathered output file") p.add_argument("chunked_files", nargs="+", help="Chunked input files") p.add_argument("--join-contigs", action="store_true", default=False, help="Merge split contigs") p.add_argument("--dataset", help="Dataset XML for populating metadata") return p
def get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument("modifications", help="Base modification GFF file") p.add_argument("alignmentSummary", help="Alignment summary GFF") p.add_argument( "gff_out", help= "Coverage summary for regions (bins) spanning the reference with basemod results for each region" ) return p
def get_parser(): description = 'Run dataset.py by specifying a command.' parser = get_default_argparser_with_base_opts( version=__VERSION__, description=description, default_level="WARNING") parser.add_argument("--strict", default=False, action='store_true', help="Turn on strict tests, raise all errors") parser.add_argument("--skipCounts", default=False, action='store_true', help="Turn on strict tests, raise all errors") subparser_list = get_subparsers() parser = add_subparsers(parser, subparser_list) return parser
def get_parser(): p = get_default_argparser_with_base_opts(__version__, __doc__) f = p.add_argument f('subreadset_path', type=validate_file, help="Path to SubreadSet XML") f('--name', type=str, default="Auto Job Name", help="Job Name") f('--host', type=str, default="smrtlink-beta", help="SMRT Link host") f('--port', type=int, default=8081, help="SMRT Link port") f('-r', '--reference-set-uuid', type=str, default=Constants.DEFAULT_RSET_UUID, help="ReferenceSet UUID") f('-p', '--pipeline-id', type=str, default=Constants.DEFAULT_PIPELINE, help="Pipeline Id") f('--block', default=False, action="store_true", help="Block and Wait for job to complete") return p
def _get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument("merged", help="Name of merge datastore file") p.add_argument("chunks", nargs="+", help="Chunk datastore outputs") p.add_argument("-j", "--nproc", dest="nproc", type=int, default=1, help="Number of processors to use") return p
def _get_parser(): p = get_default_argparser_with_base_opts( version=__version__, description=__doc__, default_level="INFO") p.add_argument( "input_reads", help="SubreadSet or ConsensusReadSet use as INPUT for lima") p.add_argument("dataset_name", help="Dataset name") p.add_argument("output_file", help="Output dataset XML") p.add_argument("--biosamples-csv", action="store", default=None, help="Optional CSV file containing Barcode/BioSample list") return p
def get_parser(): desc = "" parser = get_default_argparser_with_base_opts( version=__version__, description=__doc__) parser.add_argument('filter_summary_csv', type=validate_file, help="Filter CSV file.") parser.add_argument( '-o', "--output", dest='output_dir', default=os.getcwd(), type=validate_dir, help="Output directory for histogram images generated") parser.add_argument('-r', '--report', dest='json_report', help='Path of JSON report.') parser.add_argument("--dpi", default=60, type=int, help="dots/inch") return parser
def get_parser(): desc = "Tool to import datasets, convert/import fasta file and run analysis jobs" p = get_default_argparser_with_base_opts(__version__, desc) sp = p.add_subparsers(help='commands') def builder(subparser_id, description, options_func, exe_func): subparser_builder(sp, subparser_id, description, options_func, exe_func) status_desc = "Get System Status, DataSet and Job Summary" builder('status', status_desc, add_base_and_sal_options, args_get_sal_summary) local_desc = " The file location must be accessible from the host where the Services are running (often on a shared file system)" ds_desc = "Import Local DataSet XML." + local_desc builder('import-dataset', ds_desc, add_sal_and_xml_dir_options, args_runner_import_datasets) fasta_desc = "Import Fasta (and convert to ReferenceSet)." + local_desc builder("import-fasta", fasta_desc, add_import_fasta_opts, args_run_import_fasta) run_analysis_desc = "Run Secondary Analysis Pipeline using an analysis.json" builder("run-analysis", run_analysis_desc, add_run_analysis_job_opts, args_run_analysis_job) emit_analysis_json_desc = "Emit an analysis.json Template to stdout that can be run using 'run-analysis'" builder("emit-analysis-template", emit_analysis_json_desc, add_common_options, args_emit_analysis_template) # Get Summary Job by Id job_summary_desc = "Get Job Summary by Job Id" builder('get-job', job_summary_desc, add_get_job_options, args_get_job_summary) job_list_summary_desc = "Get Job Summary by Job Id" builder('get-jobs', job_list_summary_desc, add_get_job_list_options, args_get_job_list_summary) ds_summary_desc = "Get DataSet Summary by DataSet Id or UUID" builder('get-dataset', ds_summary_desc, add_get_dataset_options, args_run_dataset_summary) ds_list_summary_desc = "Get DataSet List Summary by DataSet Type" builder('get-datasets', ds_list_summary_desc, add_get_dataset_list_options, args_run_dataset_list_summary) return p
def get_parser(): """Util func to create an argparse instance Removing explicit usage due to issues with thirdparty argparse (Python < 2.7) usage = "usage: %prog --input=inputRgn.Fofn --outputCsv=mySubreadSummary.csv" """ desc = 'Tool for generating a CSV file of the filtered Subreads from a file name of files (FOFN).' parser = get_default_argparser_with_base_opts( version=__version__, description=__doc__) parser.add_argument('region_fofn', type=validate_fofn, help='Input Region FOFN path') parser.add_argument('-o', '--output-csv', default=None, dest='output_csv', help='Output File to write summary to') return parser
def get_parser(): description = 'Run dataset.py by specifying a command.' parser = get_default_argparser_with_base_opts(version=__VERSION__, description=description, default_level="WARNING") parser.add_argument("--strict", default=False, action='store_true', help="Turn on strict tests, raise all errors") parser.add_argument("--skipCounts", default=False, action='store_true', help="Turn on strict tests, raise all errors") subparser_list = get_subparsers() parser = add_subparsers(parser, subparser_list) return parser
def _get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument( "dataset", help="PacBio dataset XML (AlignmentSet or ConsensusAlignmentSet)") p.add_argument("csv_out", help="CSV output file") p.add_argument("--load-snr", action="store_true", default=False, help="Include per-read SNRs") p.add_argument("--load-numpasses", action="store_true", default=False, help="Include numPasses (CCS only)") return p
def get_parser(): description = 'Run dataset.py by specifying a command.' parser = get_default_argparser_with_base_opts(version=__VERSION__, description=description, default_level="WARNING") parser.add_argument("--strict", default=False, action='store_true', help="Turn on strict tests, raise all errors") parser.add_argument("--skipCounts", default=False, action='store_true', help="Skip updating NumRecords and TotalLength counts") subparser_list = get_subparsers() parser = add_subparsers(parser, subparser_list) msg = "Please specify a sub-command, or call with --help for more options" parser.set_defaults(func=lambda args: parser.error(msg)) return parser
def get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__) p.add_argument("testkit_cfg_fofn", type=validate_testkit_cfg_fofn, help="Text file listing testkit.cfg files to run") p.add_argument("-u", "--host", dest="host", action="store", default=Constants.HOST) p.add_argument("-p", "--port", dest="port", action="store", default=Constants.PORT, help="Port number") p.add_argument("-n", "--nworkers", type=int, default=Constants.NPROC, help="Number of jobs to concurrently run.") p.add_argument("-t", "--timeout", dest="time_out", type=int, default=1800, help="Timeout for blocking after job submission") p.add_argument("-s", "--sleep", dest="sleep", type=int, default=2, help="Sleep time after job submission") p.add_argument("--ignore-test-failures", dest="ignore_test_failures", action="store_true", help="Only exit with non-zero return code if the job " + "itself failed, regardless of test outcome") p.add_argument("--import-only", dest="import_only", action="store_true", help="Import datasets without running pipelines") return p
def get_parser(): """Util func to create an argparse instance Removing explicit usage due to issues with thirdparty argparse (Python < 2.7) usage = "usage: %prog --input=inputRgn.Fofn --outputCsv=mySubreadSummary.csv" """ desc = 'Tool for generating a CSV file of the filtered Subreads from a file name of files (FOFN).' parser = get_default_argparser_with_base_opts(version=__version__, description=__doc__) parser.add_argument('region_fofn', type=validate_fofn, help='Input Region FOFN path') parser.add_argument('-o', '--output-csv', default=None, dest='output_csv', help='Output File to write summary to') return parser
def _get_parser(): p = get_default_argparser_with_base_opts( version="0.1", description=__doc__) p.add_argument("testkit_cfg") p.add_argument("-u", "--host", dest="host", action="store", default="http://localhost") p.add_argument("-p", "--port", dest="port", action="store", type=int, default=8081, help="Port number") p.add_argument("-x", "--xunit", dest="xml_out", default="test-output.xml", help="Output XUnit test results") p.add_argument("-t", "--timeout", dest="time_out", type=int, default=1800, help="Timeout for blocking after job submission") p.add_argument("-s", "--sleep", dest="sleep", type=int, default=2, help="Sleep time after job submission") p.add_argument("--ignore-test-failures", dest="ignore_test_failures", action="store_true", help="Only exit with non-zero return code if the job "+ "itself failed, regardless of test outcome") return p
def get_parser(): p = get_default_argparser_with_base_opts( version=VERSION, description=__doc__, default_level="WARN") p.add_argument("input_bam", help="Input BAM or DataSet from which reads will be read") p.add_argument("output_bam", nargs='?', default=None, help="Output BAM or DataSet to which filtered reads will " "be written") p.add_argument("--show-zmws", action="store_true", default=False, help="Print a list of ZMWs and exit") p.add_argument("--whitelist", action="store", default=None, help="Comma-separated list of ZMWs, or file containing " + "whitelist of one hole number per line, or " + "BAM/DataSet file from which to extract ZMWs") p.add_argument("--blacklist", action="store", default=None, help="Opposite of --whitelist, specifies ZMWs to discard") p.add_argument("--percentage", action="store", type=float, default=None, help="If you prefer to recover a percentage of a SMRTcell " "rather than a specific list of reads specify that " "percentage (range 0-100) here") p.add_argument("-n", "--count", action="store", type=int, default=None, help="Recover a specific number of ZMWs picked at random") p.add_argument("-s", "--seed", action="store", type=int, default=None, help="Random seed for selecting a percentage of reads") p.add_argument("--ignore-metadata", action="store_true", help="Discard input DataSet metadata") p.add_argument("--relative", action="store_true", help="Make external resource paths relative") p.add_argument("--anonymize", action="store_true", help="Randomize sequences for privacy") p.add_argument("--barcodes", action="store_true", help="Indicates that the whitelist or blacklist contains "+ "barcode indices instead of ZMW numbers") p.add_argument("--sample-scraps", action="store_true", help="If enabled, --percentage and --count will include "+ "hole numbers from scraps BAM files when picking a "+ "random sample (default is to sample only ZMWs "+ "present in subreads BAM).") return p
def get_parser(): p = get_default_argparser_with_base_opts( version=__version__, description=__doc__) p.add_argument("testkit_cfg_fofn", type=validate_testkit_cfg_fofn, help="Text file listing testkit.cfg files to run") p.add_argument("-u", "--host", dest="host", action="store", default=Constants.HOST) p.add_argument("-p", "--port", dest="port", action="store", default=Constants.PORT, help="Port number") p.add_argument("-n", "--nworkers", type=int, default=Constants.NPROC, help="Number of jobs to concurrently run.") p.add_argument("-t", "--timeout", dest="time_out", type=int, default=1800, help="Timeout for blocking after job submission") p.add_argument("-s", "--sleep", dest="sleep", type=int, default=2, help="Sleep time after job submission") p.add_argument("--ignore-test-failures", dest="ignore_test_failures", action="store_true", help="Only exit with non-zero return code if the job "+ "itself failed, regardless of test outcome") return p
def get_parser(): """Old Usage in pbpy: usage = filter_subread.py --debug filtered_subread_summary.csv --output /path/to/outputDir --report /path/to/outputDir/junk3.json filtered_subread_summary.csv """ desc = "" parser = get_default_argparser_with_base_opts( version=__version__, description=__doc__) parser.add_argument("filter_summary_csv", help="Path to Filter Subread Summary CSV file.", type=validate_file) parser.add_argument('-o', '--output', dest='output', default=os.getcwd(), type=validate_dir, help='Output directory to write to Subread Hist plots to.') parser.add_argument('--dpi', type=int, dest='dpi', default=72, help="dpi (dots/inch) for plots that were generated.") parser.add_argument('-r', '--report', dest='report', default=None, help="Write the Json report to disk.") return parser
def _get_parser(): p = get_default_argparser_with_base_opts( version=__VERSION__, description=__doc__, default_level="INFO") p.add_argument("mode", choices=["consolidate", "fasta", "fastq"]) p.add_argument("dataset_file") p.add_argument("datastore_out") p.add_argument("--min-rq", dest="min_rq", type=float, default=Constants.HIFI_RQ, help="Sets RQ cutoff for splitting output") p.add_argument("--min-qv", dest="min_rq", type=lambda arg: phred_qv_as_accuracy(int(arg)), help="Alternative to --min-rq, on Phred scale (0-60)") p.add_argument("--no-zip", action="store_true", help="Disable ZIP output") return p
def get_parser(): sample_picker = {'first': sample_first, 'random': sample_random, 'uniform': sample_uniform} p = get_default_argparser_with_base_opts( version=__version__, description=__doc__, default_level="WARN") p.add_argument('subreadset', type=SubreadSet, help="Input SubreadSet for an Internal BAM") p.add_argument('alignmentset', type=AlignmentSet, help="Input AlignmentSet for the SubreadSet") p.add_argument('outprefix', type=str, help="Output prefix for csvs") p.add_argument('--nreads', type=int, help="The number of reads to process") p.add_argument('--sampler', default='uniform', type=lambda x: sample_picker.get(x), choices=sample_picker.keys(), help="Read sampling mechanism") p.add_argument('--search', type=int, default=25, help=('Limit the number of hns to search for a ' 'local hit')) return p
def _get_parser(): p = get_default_argparser_with_base_opts( version=__version__, description=__doc__, default_level="INFO") p.add_argument( "input_reads", help="SubreadSet or ConsensusReadSet use as INPUT for lima") p.add_argument( "lima_datastore", help="Datastore json generated by lima to demultiplex input_reads.") p.add_argument( "barcodes", help="BarcodeSet lima used to demultiplex reads") p.add_argument("out_json", help="Output datastore json") p.add_argument("--isoseq-mode", action="store_true", default=False, help="Iso-Seq mode") p.add_argument("--use-barcode-uuids", action="store_true", default=False, help="Apply pre-defined barcoded dataset UUIDs from input_reads") p.add_argument("--min-bq-filter", action="store", type=int, default=Constants.BARCODE_QUALITY_GREATER_THAN, help="Minimum barcode quality encoded in dataset filter") p.add_argument("-j", "--nproc", dest="nproc", action="store", type=int, default=1, help="Number of processors to use") p.add_argument("--outdir", action="store", default=None, help="Output directory for update datasets") return p
def _get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__) p.add_argument("subreads", type=validate_file) p.add_argument("datastore", type=_validate_output_file) return p
def get_parser(): """Define Parser. Use the helper methods in validators to validate input""" p = get_default_argparser_with_base_opts(__version__, __doc__) p.add_argument('path_to_file', type=validate_file, help="Path to File") return p
def get_base_parser(description, log_level="INFO"): from pbcommand.cli import get_default_argparser_with_base_opts from pbcoretools import __VERSION__ return get_default_argparser_with_base_opts(version=__VERSION__, description=description, default_level=log_level)
def get_parser(): p = get_default_argparser_with_base_opts(version="0.1", description=__doc__) p.add_argument("testkit_cfg") p.add_argument( "-u", "--host", dest="host", action="store", default=os.environ.get("PB_SERVICE_HOST", "localhost"), help= "Hostname of SMRT Link server. If this is anything other than 'localhost' you must supply authentication." ) p.add_argument("-p", "--port", dest="port", action="store", type=int, default=int(os.environ.get("PB_SERVICE_PORT", "8081")), help="Services port number") p.add_argument("--user", dest="user", action="store", default=os.environ.get("PB_SERVICE_AUTH_USER", None), help="User to authenticate with (if using HTTPS)") p.add_argument("--password", dest="password", action="store", default=os.environ.get("PB_SERVICE_AUTH_PASSWORD", None), help="Password to authenticate with (if using HTTPS)") p.add_argument("-x", "--xunit", dest="xml_out", default="test-output.xml", help="Output XUnit test results") p.add_argument( "-n", "--nunit", dest="nunit_out", default="nunit_out.xml", help= "Optional NUnit output file, used for JIRA/Xray integration; will be written only if the 'xray_tests' field is populated." ) p.add_argument("-t", "--timeout", dest="time_out", type=int, default=1800, help="Timeout for blocking after job submission") p.add_argument("-s", "--sleep", dest="sleep", type=int, default=2, help="Sleep time after job submission") p.add_argument("--ignore-test-failures", dest="ignore_test_failures", action="store_true", help="Only exit with non-zero return code if the job " + "itself failed, regardless of test outcome") p.add_argument("--import-only", dest="import_only", action="store_true", help="Import datasets without running pipeline") p.add_argument("--only-tests", dest="test_job_id", action="store", type=int, default=None, help="Run tests on an existing smrtlink job") return p
def get_parser(): p = get_default_argparser_with_base_opts(version=VERSION, description=__doc__, default_level="WARN") p.add_argument("input_bam", help="Input BAM or DataSet from which reads will be read") p.add_argument("output_bam", nargs='?', default=None, help="Output BAM or DataSet to which filtered reads will " "be written") p.add_argument("--show-zmws", action="store_true", default=False, help="Print a list of ZMWs and exit") p.add_argument("--whitelist", action="store", default=None, help="Comma-separated list of ZMWs, or file containing " + "whitelist of one hole number per line, or " + "BAM/DataSet file from which to extract ZMWs") p.add_argument("--blacklist", action="store", default=None, help="Opposite of --whitelist, specifies ZMWs to discard") p.add_argument( "--subreads", action="store_true", help="If set, the whitelist or blacklist will be assumed to contain " + "one subread name per line, or " + "a BAM/DataSet file from which to extract subreads") p.add_argument("--percentage", action="store", type=float, default=None, help="If you prefer to recover a percentage of a SMRTcell " "rather than a specific list of reads specify that " "percentage (range 0-100) here") p.add_argument("-n", "--count", action="store", type=int, default=None, help="Recover a specific number of ZMWs picked at random") p.add_argument("-s", "--seed", action="store", type=int, default=None, help="Random seed for selecting a percentage of reads") p.add_argument("--ignore-metadata", action="store_true", help="Discard input DataSet metadata") p.add_argument("--relative", action="store_true", help="Make external resource paths relative") p.add_argument("--anonymize", action="store_true", help="Randomize sequences for privacy") p.add_argument("--barcodes", action="store_true", help="Indicates that the whitelist or blacklist contains " + "barcode indices instead of ZMW numbers") p.add_argument("--sample-scraps", action="store_true", help="If enabled, --percentage and --count will include " + "hole numbers from scraps BAM files when picking a " + "random sample (default is to sample only ZMWs " + "present in subreads BAM).") p.add_argument("--keep-uuid", action="store_true", help="If enabled, the UUID from the input dataset will " + "be used for the output as well.") p.add_argument("--min-adapters", action="store", type=int, default=None, help="Minimum number of adapters to filter for") return p
def get_parser(): p = get_default_argparser_with_base_opts(version=__version__, description=__doc__, default_level="INFO") p.add_argument("alignment_set", help="BAM or Alignment DataSet") p.add_argument("--reference", action="store", required=True, type=validateFile, help="Fasta or Reference DataSet") p.add_argument("--gff", action="store", default=None, help="Output GFF file of modified bases") p.add_argument("--csv", action="store", default=None, help="Output CSV file out per-nucleotide information") p.add_argument( "--bigwig", action="store", default=None, help="Output BigWig file encoding IpdRatio for both strands") # FIXME use central --nproc option p.add_argument('--numWorkers', '-j', dest='numWorkers', default=1, type=int, help='Number of thread to use (-1 uses all logical cpus)') # common options p.add_argument("--pvalue", type=float, default=Constants.PVALUE_DEFAULT, help="P-value cutoff") p.add_argument("--maxLength", type=int, default=Constants.MAX_LENGTH_DEFAULT, help="Maximum number of bases to process per contig") p.add_argument( "--identify", action="store", default="m6A,m4C", help="Specific modifications to identify (comma-separated " + "list). Currrent options are m6A, m4C, m5C_TET. Using --control " + "overrides this option.") _DESC = "In the --identify mode, add --methylFraction to " +\ "command line to estimate the methylated fraction, along with " +\ "95%% confidence interval bounds." p.add_argument("--methylFraction", action="store_true", help=_DESC) p.add_argument( '--outfile', dest='outfile', default=None, help= 'Use this option to generate all possible output files. Argument here is the root filename of the output files.' ) # FIXME: Need to add an extra check for this; it can only be used if # --useLDA flag is set. p.add_argument('--m5Cgff', dest='m5Cgff', default=None, help='Name of output GFF file containing m5C scores') # FIXME: Make sure that this is specified if --useLDA flag is set. p.add_argument('--m5Cclassifier', dest='m5Cclassifier', default=None, help='Specify csv file containing a 127 x 2 matrix') p.add_argument('--pickle', dest='pickle', default=None, help='Name of output pickle file.') p.add_argument('--ms_csv', dest='ms_csv', default=None, help='Multisite detection CSV file.') # Calculation options: p.add_argument( '--control', dest='control', default=None, type=validateNoneOrFile, help= 'AlignmentSet or mapped BAM file containing a control sample. Tool will perform a case-control analysis' ) # Temporary addition to test LDA for Ca5C detection: p.add_argument('--useLDA', action="store_true", dest='useLDA', default=False, help='Set this flag to debug LDA for m5C/Ca5C detection') # Parameter options: defaultParamsPathSpec = _getResourcePathSpec() p.add_argument( '--paramsPath', dest='paramsPath', default=defaultParamsPathSpec, type=validateNoneOrPathSpec, help= 'List of :-delimited directory paths containing in-silico trained models (default is "%s")' % defaultParamsPathSpec) # XXX hacky workaround for running tests using obsolete chemistry inputs p.add_argument("--useChemistry", dest="useChemistry", default=None, help=argparse.SUPPRESS) p.add_argument('--minCoverage', dest='minCoverage', default=3, type=int, help='Minimum coverage required to call a modified base') p.add_argument('--maxQueueSize', dest='maxQueueSize', default=20, type=int, help='Max Queue Size') p.add_argument('--maxCoverage', dest='maxCoverage', type=int, default=-1, help='Maximum coverage to use at each site') p.add_argument('--mapQvThreshold', dest='mapQvThreshold', type=float, default=-1.0) p.add_argument('--ipdModel', dest='ipdModel', default=None, type=validateNoneOrFile, help='Alternate synthetic IPD model HDF5 file') p.add_argument('--modelIters', dest='modelIters', type=int, default=-1, help='[Internal] Number of GBM model iteration to use') p.add_argument('--cap_percentile', dest='cap_percentile', type=float, default=99.0, help='Global IPD percentile to cap IPDs at') p.add_argument( "--methylMinCov", type=int, dest='methylMinCov', default=10, help= "Do not try to estimate methylFraction unless coverage is at least this." ) p.add_argument( "--identifyMinCov", type=int, dest='identifyMinCov', default=5, help= "Do not try to identify the modification type unless coverage is at least this." ) p.add_argument( "--maxAlignments", type=int, dest="maxAlignments", default=1500, help="Maximum number of alignments to use for a given window") # Computation management options: p.add_argument("-w", "--referenceWindow", "--referenceWindows", "--refContigs", # backwards compatibility type=str, dest='referenceWindowsAsString', default=None, help="The window (or multiple comma-delimited windows) of the reference to " + \ "be processed, in the format refGroup[:refStart-refEnd] " + \ "(default: entire reference).") def slurpWindowFile(fname): return ",".join(map(str.strip, open(fname).readlines())) p.add_argument( "--refContigIndex", type=int, dest='refContigIndex', default=-1, help= "For debugging purposes only - rather than enter a reference contig name, simply enter an index" ) p.add_argument( "-W", "--referenceWindowsFile", "--refContigsFile", # backwards compatibility type=slurpWindowFile, dest='referenceWindowsAsString', default=None, help="A file containing reference window designations, one per line") p.add_argument( "--skipUnrecognizedContigs", type=bool, default=False, help= "Whether to skip, or abort, unrecognized contigs in the -w/-W flags") # FIXME shouldn't it always do this? p.add_argument("--alignmentSetRefWindows", action="store_true", dest="referenceWindowsFromAlignment", help="Use refWindows in dataset") # Debugging help options: p.add_argument("--profile", action="store_true", dest="doProfiling", default=False, help="Enable Python-level profiling (using cProfile).") add_debug_option(p) p.add_argument( "--seed", action="store", dest="randomSeed", type=int, default=None, help="Random seed (for development and debugging purposes only)") p.add_argument("--referenceStride", action="store", type=int, default=1000, help="Size of reference window in internal " + "parallelization. For testing purposes only.") return p