def get_contract_parser():
p = get_scatter_pbparser(Constants.TOOL_ID, Constants.VERSION,
"Scatter ContigSet",
__doc__, Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_SUBREADS, "subreads_in", "SubreadSet In",
"PacBio ContigSet")
p.add_input_file_type(FileTypes.DS_CONTIG, "fasta_in", "ContigSet",
"PacBio ContigSet")
p.add_input_file_type(FileTypes.PICKLE, "pickle_in", "Pickle",
"Cluster pickle file")
p.add_input_file_type(FileTypes.PICKLE, "nfl_pickle_in", "Pickle",
"Non-full-length pickle file")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Filtered Fasta",
"Chunked JSON ContigSet",
"pickles.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
default=Constants.DEFAULT_NCHUNKS,
name="Max NChunks",
description="Maximum number of Chunks")
return p
def get_contract_parser():
driver = "python -m pbcoretools.tasks.scatter_filter_fasta --resolved-tool-contract "
chunk_keys = ("$chunk.fasta_id", )
p = get_scatter_pbparser(TOOL_ID,
"0.1.3",
"Scatter Filter Fasta",
"Scatter Filter Fasta",
driver,
chunk_keys,
is_distributed=False)
p.add_input_file_type(FileTypes.FASTA, "fasta_in", "Fasta In",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Filtered Fasta",
"Chunked JSON Filtered Fasta", "fasta.chunked")
# max nchunks for this specific task
p.add_int("pbcoretools.task_options.dev_scatter_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
p.add_str("pbcoretools.task_options.dev_scatter_chunk_key", "chunk_key",
Constants.CHUNK_KEY, "Chunk key",
"Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
"""
input idx 0: polish_chunk_pickle_id
input idx 1: sentinel.txt
input idx 2: *.subreadset.xml
output idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID,
Constants.VERSION,
"Scatter Ice Polish Chunks",
__doc__,
Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.PICKLE, "polish_chunk_pickle", "PICKLE",
"Polish Chunk Tasks Pickle") # input idx 0
p.add_input_file_type(FileTypes.TXT, "sentinel_in", "Sentinel In",
"Setinel file") # input idx 1
p.add_input_file_type(FileTypes.DS_SUBREADS, "subreads_in",
"SubreadSet In", "PacBio SubreadSet") # input idx 2
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Polish Tasks",
"Chunked JSON Polish Tasks", "ice_polish.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
return p
def get_contract_parser(tool_id=TOOL_ID, module_name=MODULE_NAME):
p = get_scatter_pbparser(
tool_id,
"0.1.3",
"Scatter AlignmentSet",
"Pacbio DataSet AlignmentSet",
Constants.DRIVER_BASE.format(module=module_name),
Constants.CHUNK_KEYS,
is_distributed=False,
)
p.add_input_file_type(FileTypes.DS_ALIGN, "alignment_ds", "AlignmentSet", "Pacbio DataSet AlignmentSet")
p.add_input_file_type(FileTypes.DS_REF, "ds_reference", "ReferenceSet", "Pac Bio Fasta format")
p.add_output_file_type(
FileTypes.CHUNK,
"cjson_out",
"Chunk JSON Filtered Fasta",
"Chunked JSON Filtered Fasta",
"alignments_reference.chunked.json",
)
# max nchunks for this specific task
p.add_int(
Constants.OPT_MAX_NCHUNKS, "max_nchunks", Constants.DEFAULT_NCHUNKS, "Max NChunks", "Maximum number of Chunks"
)
return p
def get_contract_parser():
driver = "python -m pbsmrtpipe.tools_dev.scatter_ccs_reference --resolved-tool-contract "
p = get_scatter_pbparser(TOOL_ID, "0.1.3", "ConsensusReadSet scatter",
"Scatter ConsensusRead DataSet", driver,
Constants.CHUNK_KEYS, is_distributed=False)
p.add_input_file_type(FileTypes.DS_CCS,
"ccsset",
"ConsensusReadSet",
"Pac Bio Fasta format")
p.add_input_file_type(FileTypes.DS_REF,
"ds_reference",
"ReferenceSet",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK,
"cjson_out",
"Chunk ConsensusReadSet",
"PacBio Chunked JSON ConsensusReadSet",
"ccsset_chunked.json")
# max nchunks for this specific task
# FIXME using same option names as scatter_subread_reference.py - it would
# be nice if these were more generic
p.add_int("pbsmrtpipe.task_options.scatter_subread_max_nchunks", "max_nchunks", Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
p.add_str("pbsmrtpipe.task_options.scatter_subreadset_chunk_key", "chunk_key",
"$chunk:fasta_id", "Chunk key", "Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
"""
input:
idx 0: json_id
idx 1: txt_id
output:
idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID,
Constants.VERSION,
"Scatter json with Scripts into Chunks",
__doc__,
Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.JSON, "json_with_scripts", "JSON",
"Json containing scripts") # input idx 0
p.add_input_file_type(FileTypes.TXT, "sentinel_txt", "TXT",
"Sentinel txt") # input idx 1
p.add_output_file_type(FileTypes.CHUNK, "cjson_out", "Chunk JSON",
"Chunked JSON", "json_with_scripts.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
return p
def get_contract_parser_impl(C):
p = get_scatter_pbparser(C.TOOL_ID, "0.1.3",
"%sSet ZMW scatter" % C.READ_TYPE,
"Scatter %s DataSet for barcoding" % C.READ_TYPE, C.DRIVER_EXE,
C.CHUNK_KEYS, is_distributed=False)
p.add_input_file_type(C.DATASET_TYPE,
"dataset",
"%sSet" % C.READ_TYPE,
"Pac Bio Fasta format")
p.add_input_file_type(FileTypes.DS_BARCODE,
"barcodes",
"BarcodeSet",
"Pac Bio Barcode Dataset XML")
p.add_output_file_type(FileTypes.CHUNK,
"chunk_report_json",
"Chunk %sSet" % C.READ_TYPE,
"PacBio Chunked JSON %sSet" % C.READ_TYPE,
"%sset_chunked" % C.READ_TYPE_ABBREV)
# max nchunks for this specific task
p.add_int("pbcoretools.task_options.scatter_subread_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
p.add_str("pbcoretools.task_options.scatter_subreadset_chunk_key",
"chunk_key", "$chunk:subreadset_id", "Chunk key",
"Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
"""
input idx 0: polish_chunk_pickle_id
input idx 1: sentinel.txt
input idx 2: *.subreadset.xml
output idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID, Constants.VERSION,
"Scatter Ice Polish Chunks",
__doc__, Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.PICKLE, "polish_chunk_pickle",
"PICKLE", "Polish Chunk Tasks Pickle") # input idx 0
p.add_input_file_type(FileTypes.TXT, "sentinel_in", "Sentinel In",
"Setinel file") # input idx 1
p.add_input_file_type(FileTypes.DS_SUBREADS, "subreads_in", "SubreadSet In",
"PacBio SubreadSet") # input idx 2
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Polish Tasks",
"Chunked JSON Polish Tasks",
"ice_polish.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
return p
def get_contract_parser():
"""
input:
idx 0: partial_chunk_pickle_id
idx 1: sentinel txt file
idx 2: ccs_id
output:
idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID, Constants.VERSION,
"Scatter Ice Partial Chunks",
__doc__, Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.PICKLE, "partial_chunk_pickle",
"PICKLE", "Partial Chunk Tasks Pickle") # input idx 0
p.add_input_file_type(FileTypes.TXT, "partial_sentinel_in", "Sentinel In",
"Setinel file") # input idx 1
p.add_input_file_type(FileTypes.DS_CCS, "ccs_in", "ConsensusReadSet In",
"PacBio ConsensusReadSet") # input idx 2
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Partial Tasks",
"Chunked JSON Partial Tasks",
"ice_partial.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
return p
def get_contract_parser():
"""Get scatter tool contract parser
Input:
idx 0 - cluster_chunks.pickle
idx 1 - ccs
Output:
idx 0 - chunk.json
"""
p = get_scatter_pbparser(Constants.TOOL_ID,
Constants.VERSION,
"Scatter Cluster Bins",
__doc__,
Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.PICKLE, "cluster_chunks_pickle",
"Pickle In", "Cluster chunks pickle file") # input 0
p.add_input_file_type(FileTypes.DS_CCS, "ccs_in", "ConsensusReadSet In",
"PacBio ConsensusReadSet") # input 1
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Cluster Bins",
"Chunked JSON Cluster Bins",
"ice_cluster.chunked") # output 0
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
return p
def get_contract_parser():
"""
input:
idx 0: json_id
idx 1: txt_id
output:
idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID, Constants.VERSION,
"Scatter json with Scripts into Chunks",
__doc__, Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.JSON, "json_with_scripts",
"JSON", "Json containing scripts") # input idx 0
p.add_input_file_type(FileTypes.TXT, "sentinel_txt",
"TXT", "Sentinel txt") # input idx 1
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON", "Chunked JSON",
"json_with_scripts.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
return p
def get_contract_parser():
driver = "python -m pbcoretools.tasks.scatter_filter_fasta --resolved-tool-contract "
chunk_keys = ("$chunk.fasta_id",)
p = get_scatter_pbparser(
TOOL_ID, "0.1.3", "Scatter Filter Fasta", "Scatter Filter Fasta", driver, chunk_keys, is_distributed=False
)
p.add_input_file_type(FileTypes.FASTA, "fasta_in", "Fasta In", "Pac Bio Fasta format")
p.add_output_file_type(
FileTypes.CHUNK, "cjson_out", "Chunk JSON Filtered Fasta", "Chunked JSON Filtered Fasta", "fasta.chunked"
)
# max nchunks for this specific task
p.add_int(
"pbcoretools.task_options.dev_scatter_max_nchunks",
"max_nchunks",
Constants.DEFAULT_NCHUNKS,
"Max NChunks",
"Maximum number of Chunks",
)
p.add_str(
"pbcoretools.task_options.dev_scatter_chunk_key",
"chunk_key",
Constants.CHUNK_KEY,
"Chunk key",
"Chunk key to use (format $chunk:{chunk-key}",
)
return p
def get_contract_parser():
"""
input:
idx 0: fastq_id
idx 1: gmap_ref_id
output:
idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID, Constants.VERSION,
"Scatter Map Isoforms Chunks",
__doc__, Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.FASTQ, "fastq_in",
"FASTQ In", "HQ isoforms FASTQ file") # input idx 0
p.add_input_file_type(FileTypes.DS_GMAP_REF, "gmap_referenceset", "GmapReferenceSet In",
"Gmap reference set file") # input 1
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Map Isoforms Tasks",
"Chunked JSON Map Isoforms Tasks",
"map_isoforms_to_genome.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
return p
def get_contract_parser():
driver = "python -m pbcoretools.tasks.scatter_ccs_reference --resolved-tool-contract "
p = get_scatter_pbparser(TOOL_ID,
"0.1.3",
"ConsensusReadSet scatter",
"Scatter ConsensusRead DataSet",
driver,
Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_CCS, "ccsset", "ConsensusReadSet",
"Pac Bio Fasta format")
p.add_input_file_type(FileTypes.DS_REF, "ds_reference", "ReferenceSet",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk ConsensusReadSet",
"PacBio Chunked JSON ConsensusReadSet",
"ccsset_chunked")
# max nchunks for this specific task
# FIXME using same option names as scatter_subread_reference.py - it would
# be nice if these were more generic
p.add_int("pbcoretools.task_options.scatter_subread_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
p.add_str("pbcoretools.task_options.scatter_subreadset_chunk_key",
"chunk_key", "$chunk:fasta_id", "Chunk key",
"Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
"""
input:
idx 0: fastq_id
idx 1: gmap_ref_id
output:
idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID,
Constants.VERSION,
"Scatter Map Isoforms Chunks",
__doc__,
Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.FASTQ, "fastq_in", "FASTQ In",
"HQ isoforms FASTQ file") # input idx 0
p.add_input_file_type(FileTypes.DS_GMAP_REF, "gmap_referenceset",
"GmapReferenceSet In",
"Gmap reference set file") # input 1
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Map Isoforms Tasks",
"Chunked JSON Map Isoforms Tasks",
"map_isoforms_to_genome.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
return p
def get_contract_parser():
driver = "python -m pbcoretools.tasks.scatter_subread_reference --resolved-tool-contract "
# These Keys are expected to be PipelineChunks produced by this tool
chunk_keys = ("$chunk.reference_id", "$chunk.subreadset_id")
p = get_scatter_pbparser(TOOL_ID,
"0.1.3",
"SubreadSet scatter",
"Scatter Subread DataSet",
driver,
chunk_keys,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_SUBREADS, "subreads", "SubreadSet",
"Pac Bio Fasta format")
p.add_input_file_type(FileTypes.DS_REF, "ds_reference", "ReferenceSet",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out", "Chunk SubreadSet",
"PacBio Chunked JSON SubreadSet",
"subreadset_chunked")
# max nchunks for this specific task
p.add_int("pbcoretools.task_options.scatter_subread_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
# This should only be added at the argparse level.
# Disabling for now.
# FIXME. This should support --reference-chunk-key and --subread-key
# p.arg_parser.add_str("pbcoretools.task_options.scatter_subreadset_chunk_key",
# "chunk_key",
# "$chunk:fasta_id", "Chunk key", "Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser_impl(C):
p = get_scatter_pbparser(C.TOOL_ID, "0.1.3",
"%sSet ZMW scatter" % C.READ_TYPE,
"Scatter %s DataSet for barcoding" % C.READ_TYPE, C.DRIVER_EXE,
C.CHUNK_KEYS, is_distributed=True)
p.add_input_file_type(C.DATASET_TYPE,
"dataset",
"%sSet" % C.READ_TYPE,
"Pac Bio Fasta format")
p.add_input_file_type(FileTypes.DS_BARCODE,
"barcodes",
"BarcodeSet",
"Pac Bio Barcode Dataset XML")
p.add_output_file_type(FileTypes.CHUNK,
"chunk_report_json",
"Chunk %sSet" % C.READ_TYPE,
"PacBio Chunked JSON %sSet" % C.READ_TYPE,
"%sset_chunked" % C.READ_TYPE_ABBREV)
# max nchunks for this specific task
p.add_int("pbcoretools.task_options.scatter_subread_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
p.add_str("pbcoretools.task_options.scatter_subreadset_chunk_key",
"chunk_key", "$chunk:subreadset_id", "Chunk key",
"Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
p = get_scatter_pbparser(TOOL_ID,
"0.1.3",
"H5 SubreadSet scatter",
"Scatter Hdf5 Subread DataSet",
Constants.DRIVER,
Constants.CHUNK_KEYS,
is_distributed=True,
nchunks=SymbolTypes.MAX_NCHUNKS)
p.add_input_file_type(FileTypes.DS_SUBREADS_H5, "h5_subreads",
"HdfSubreadSet", "Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out", "Chunk HdfSubreadSet",
"PacBio Chunked JSON HdfSubread Set",
"hdfsubreadset_chunked")
# max nchunks for this specific task
p.add_int("pbcoretools.task_options.scatter_hdfsubread_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
p.add_str("pbcoretools.task_options.dev_scatter_chunk_key", "chunk_key",
"$chunk:fasta_id", "Chunk key",
"Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
"""Get scatter tool contract parser
Input:
idx 0 - cluster_chunks.pickle
idx 1 - ccs
Output:
idx 0 - chunk.json
"""
p = get_scatter_pbparser(Constants.TOOL_ID, Constants.VERSION,
"Scatter Cluster Bins",
__doc__, Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.PICKLE, "cluster_chunks_pickle", "Pickle In",
"Cluster chunks pickle file") # input 0
p.add_input_file_type(FileTypes.DS_CCS, "ccs_in", "ConsensusReadSet In",
"PacBio ConsensusReadSet") # input 1
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Cluster Bins",
"Chunked JSON Cluster Bins",
"ice_cluster.chunked") # output 0
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS, "Max NChunks", "Maximum number of Chunks")
return p
def get_contract_parser():
driver = "python -m pbsmrtpipe.tools_dev.scatter_subread_zmws --resolved-tool-contract "
chunk_keys = ("$chunk.subreadset_id", )
p = get_scatter_pbparser(TOOL_ID, "0.1.3", "SubreadSet ZMW scatter",
"Scatter Subread DataSet by ZMWs", driver,
chunk_keys, is_distributed=False)
p.add_input_file_type(FileTypes.DS_SUBREADS,
"subreadset",
"SubreadSet",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK,
"chunk_report_json",
"Chunk SubreadSet",
"PacBio Chunked JSON SubreadSet",
"subreadset_chunked.json")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.scatter_subread_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
p.add_str("pbsmrtpipe.task_options.scatter_subreadset_chunk_key",
"chunk_key", "$chunk:subreadset_id", "Chunk key",
"Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
driver = "python -m pbsmrtpipe.tools_dev.scatter_subread_zmws --resolved-tool-contract "
chunk_keys = ("$chunk.subreadset_id", )
p = get_scatter_pbparser(TOOL_ID,
"0.1.3",
"SubreadSet ZMW scatter",
"Scatter Subread DataSet by ZMWs",
driver,
chunk_keys,
is_distributed=False)
p.add_input_file_type(FileTypes.DS_SUBREADS, "subreadset", "SubreadSet",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK, "chunk_report_json",
"Chunk SubreadSet",
"PacBio Chunked JSON SubreadSet",
"subreadset_chunked.json")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.scatter_subread_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
p.add_str("pbsmrtpipe.task_options.scatter_subreadset_chunk_key",
"chunk_key", "$chunk:subreadset_id", "Chunk key",
"Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
"""
input:
idx 0: partial_chunk_pickle_id
idx 1: sentinel txt file
idx 2: ccs_id
output:
idx 0: chunk json
"""
p = get_scatter_pbparser(Constants.TOOL_ID,
Constants.VERSION,
"Scatter Ice Partial Chunks",
__doc__,
Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.PICKLE, "partial_chunk_pickle", "PICKLE",
"Partial Chunk Tasks Pickle") # input idx 0
p.add_input_file_type(FileTypes.TXT, "partial_sentinel_in", "Sentinel In",
"Setinel file") # input idx 1
p.add_input_file_type(FileTypes.DS_CCS, "ccs_in", "ConsensusReadSet In",
"PacBio ConsensusReadSet") # input idx 2
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Partial Tasks",
"Chunked JSON Partial Tasks", "ice_partial.chunked")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
return p
def get_contract_parser(tool_id=TOOL_ID, module_name=MODULE_NAME):
p = get_scatter_pbparser(tool_id,
"0.1.3",
"Scatter AlignmentSet",
"Pacbio DataSet AlignmentSet",
Constants.DRIVER_BASE.format(module=module_name),
Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_ALIGN, "alignment_ds", "AlignmentSet",
"Pacbio DataSet AlignmentSet")
p.add_input_file_type(FileTypes.DS_REF, "ds_reference", "ReferenceSet",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Filtered Fasta",
"Chunked JSON Filtered Fasta",
"alignments_reference.chunked.json")
# max nchunks for this specific task
p.add_int(Constants.OPT_MAX_NCHUNKS, "max_nchunks",
Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
return p
def get_parser():
driver = "python -m pbcommand.cli.examples.dev_scatter_fasta_app --resolved-tool-contract "
desc = "Scatter a single fasta file to create chunk.json file"
# chunk keys that **will** be written to the file
chunk_keys = (Constants.FA_CHUNK_KEY, )
p = get_scatter_pbparser(TOOL_ID, __version__, "Fasta Scatter",
desc, driver, chunk_keys, is_distributed=False)
p.add_input_file_type(FileTypes.FASTA, "fasta_in", "Fasta In", "Fasta file to scatter")
p.add_output_file_type(FileTypes.CHUNK, "cjson", "Chunk JSON", "Scattered/Chunked Fasta Chunk.json", "fasta.chunks")
p.add_int("pbcommand.task_options.dev_scatter_fa_nchunks", "nchunks", 10, "Number of chunks",
"Suggested number of chunks. May be overridden by $max_nchunks")
return p
def get_contract_parser():
driver = "python -m pbfalcon.tasks.scatter0_run_daligner_jobs --resolved-tool-contract "
p = get_scatter_pbparser(TOOL_ID, "0.1.3", "Scatter Daligner",
"Scatter Daligner Jobs", driver, Constants.CHUNK_KEYS,
is_distributed=False)
p.add_input_file_type(FileTypes.JSON, "config", "Config",
"Pac Bio ???")
p.add_input_file_type(FileTypes.TXT, "bash", "Bash",
"Pac Bio ???")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out", "Chunk of .fasta for daligner, stage-0",
"Chunked JSON Filtered Fasta",
"fasta.chunked")
return p
def get_contract_parser():
driver = "python -m pbfalcon.tasks.scatter1_run_daligner_jobs --resolved-tool-contract "
p = get_scatter_pbparser(TOOL_ID, "0.1.3", "Scatter Daligner",
"Scatter Daligner Jobs", driver, Constants.CHUNK_KEYS,
is_distributed=False)
p.add_input_file_type(FileTypes.JSON, "config", "Config",
"Pac Bio ???")
p.add_input_file_type(FileTypes.TXT, "bash", "Bash",
"Pac Bio ???")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out", "Chunk of .fasta for daligner, stage-1",
"Chunked JSON Filtered Fasta",
"fasta.chunked")
return p
def get_contract_parser():
driver = "python -m pbsmrtpipe.tools_dev.scatter_contigset --resolved-tool-contract "
chunk_keys = ("$chunk.contigset_id", )
p = get_scatter_pbparser(TOOL_ID, "0.1.3", "Scatter ContigSet",
"Scatter ContigSet", driver, chunk_keys,
is_distributed=False)
p.add_input_file_type(FileTypes.DS_CONTIG, "dataset_in", "ContigSet In",
"PacBio ContigSet")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out", "Chunk JSON Filtered Fasta",
"Chunked JSON ContigSet",
"fasta.chunked.json")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.dev_scatter_max_nchunks", "max_nchunks", Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
p.add_str("pbsmrtpipe.task_options.dev_scatter_chunk_key", "chunk_key",
Constants.CHUNK_KEY, "Chunk key", "Chunk key to use (format $chunk:{chunk-key}")
return p
def get_contract_parser():
p = get_scatter_pbparser(Constants.TOOL_ID, Constants.VERSION,
"Scatter ContigSet for GMAP",
__doc__, Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_CONTIG, "dataset_in", "ContigSet In",
"PacBio ContigSet")
p.add_input_file_type(FileTypes.DS_REF, "ref_in", "ReferenceSet",
"PacBio ReferenceSet")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Filtered Fasta",
"Chunked JSON ContigSet",
"fasta.chunked")
# max nchunks for this specific task
p.add_int("pbcoretools.task_options.dev_scatter_max_nchunks", "max_nchunks",
Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
return p
def get_contract_parser():
p = get_scatter_pbparser(
TOOL_ID,
"0.1.3",
"H5 SubreadSet scatter",
"Scatter Hdf5 Subread DataSet",
Constants.DRIVER,
Constants.CHUNK_KEYS,
is_distributed=False,
nchunks=SymbolTypes.MAX_NCHUNKS,
)
p.add_input_file_type(FileTypes.DS_SUBREADS_H5, "h5_subreads", "HdfSubreadSet", "Pac Bio Fasta format")
p.add_output_file_type(
FileTypes.CHUNK,
"cjson_out",
"Chunk HdfSubreadSet",
"PacBio Chunked JSON HdfSubread Set",
"hdfsubreadset_chunked.json",
)
# max nchunks for this specific task
p.add_int(
"pbsmrtpipe.task_options.scatter_hdfsubread_max_nchunks",
"max_nchunks",
Constants.DEFAULT_NCHUNKS,
"Max NChunks",
"Maximum number of Chunks",
)
p.add_str(
"pbsmrtpipe.task_options.dev_scatter_chunk_key",
"chunk_key",
"$chunk:fasta_id",
"Chunk key",
"Chunk key to use (format $chunk:{chunk-key}",
)
return p
def get_contract_parser():
p = get_scatter_pbparser(Constants.TOOL_ID,
Constants.VERSION,
"Scatter ContigSet for GMAP",
__doc__,
Constants.DRIVER_EXE,
chunk_keys=Constants.CHUNK_KEYS,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_CONTIG, "dataset_in", "ContigSet In",
"PacBio ContigSet")
p.add_input_file_type(FileTypes.DS_REF, "ref_in", "ReferenceSet",
"PacBio ReferenceSet")
p.add_output_file_type(FileTypes.CHUNK, "cjson_out",
"Chunk JSON Filtered Fasta",
"Chunked JSON ContigSet", "fasta.chunked")
# max nchunks for this specific task
p.add_int("pbcoretools.task_options.dev_scatter_max_nchunks",
"max_nchunks", Constants.DEFAULT_NCHUNKS, "Max NChunks",
"Maximum number of Chunks")
return p
def get_contract_parser():
driver = "python -m pbsmrtpipe.tools_dev.scatter_subread_reference --resolved-tool-contract "
# These Keys are expected to be PipelineChunks produced by this tool
chunk_keys = ("$chunk.reference_id", "$chunk.subreadset_id")
p = get_scatter_pbparser(TOOL_ID, "0.1.3", "SubreadSet scatter",
"Scatter Subread DataSet", driver, chunk_keys,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_SUBREADS,
"subreads",
"SubreadSet",
"Pac Bio Fasta format")
p.add_input_file_type(FileTypes.DS_REF,
"ds_reference",
"ReferenceSet",
"Pac Bio Fasta format")
p.add_output_file_type(FileTypes.CHUNK,
"cjson_out",
"Chunk SubreadSet",
"PacBio Chunked JSON SubreadSet",
"subreadset_chunked.json")
# max nchunks for this specific task
p.add_int("pbsmrtpipe.task_options.scatter_subread_max_nchunks", "max_nchunks", Constants.DEFAULT_NCHUNKS,
"Max NChunks", "Maximum number of Chunks")
# This should only be added at the argparse level.
# Disabling for now.
# FIXME. This should support --reference-chunk-key and --subread-key
# p.arg_parser.add_str("pbsmrtpipe.task_options.scatter_subreadset_chunk_key",
# "chunk_key",
# "$chunk:fasta_id", "Chunk key", "Chunk key to use (format $chunk:{chunk-key}")
return p