def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - HQ isoforms fastq as gmap input
idx 1 - gmap reference set
Output:
idx 0 - gmap output SAM
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_map_isoforms_io_arguments(p.arg_parser.parser)
add_gmap_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.FASTQ, "hq_isoforms_fastq", "FASTQ In",
"HQ isoforms FASTQ file") # input 0
tcp.add_input_file_type(FileTypes.DS_GMAP_REF, "gmap_referenceset",
"GmapReferenceSet In",
"Gmap reference set file") # input 1
tcp.add_output_file_type(FileTypes.SAM,
"gmap_output_sam",
name="SAM file",
description="Gmap output sam",
default_name="gmap_output")
tcp.add_int(option_id=Constants.GMAP_NPROC_ID,
option_str="gmap_nproc",
default=Constants.GMAP_NPROC_DEFAULT,
name="GMAP nproc",
description="GMAP nproc")
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - HQ isoforms fastq as gmap input
idx 1 - gmap reference set
Output:
idx 0 - gmap output SAM
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_map_isoforms_io_arguments(p.arg_parser.parser)
add_gmap_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.FASTQ, "hq_isoforms_fastq", "FASTQ In",
"HQ isoforms FASTQ file") # input 0
tcp.add_input_file_type(FileTypes.DS_GMAP_REF, "gmap_referenceset", "GmapReferenceSet In",
"Gmap reference set file") # input 1
tcp.add_output_file_type(FileTypes.SAM, "gmap_output_sam",
name="Gmap SAM Mapping HQ Isoforms to Genome",
description="Gmap output sam mapping HQ isoforms to reference",
default_name="gmap_output")
tcp.add_int(option_id=Constants.GMAP_NPROC_ID, option_str="gmap_nproc",
default=Constants.GMAP_NPROC_DEFAULT,
name="GMAP nproc", description="GMAP nproc")
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - group file
idx 1 - pickle file
Output:
idx 0 - read stat file
idx 1 - abundance file
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_make_abundance_io_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(
FileTypes.TXT, "group_txt", "TXT In",
"Group file associating isoforms with reads") # input 0
tcp.add_input_file_type(
FileTypes.PICKLE, "hq_lq_pre_dict", "PICKLE In",
"Pickle file containing dicts mapping HQ (LQ) " +
"sample prefixes to ICE cluster output directories") # input 1
tcp.add_output_file_type(FileTypes.TXT,
"read_stat_txt",
name="TXT file",
description="Read status of FL and nFL reads",
default_name="output_mapped_read_stat")
tcp.add_output_file_type(FileTypes.TXT,
"abundance_txt",
name="TXT file",
description="Abundance file",
default_name="output_mapped_abundance")
return p
def get_contract_parser():
p = get_base_contract_parser(Constants, default_level="DEBUG")
tcp = p.tool_contract_parser
add_fofn_arguments(p.arg_parser.parser,
bas_fofn=True,
tool_contract_parser=tcp)
tcp.add_input_file_type(FileTypes.DS_CONTIG,
"consensus_fa",
name="Consensus isoforms",
description="ContigSet of consensus isoforms")
tcp.add_input_file_type(FileTypes.PICKLE,
"cluster_pickle",
name="Clusters",
description="Cluster pickle file")
tcp.add_input_file_type(
FileTypes.PICKLE,
"map_nofl_pickle",
name="Pickle file",
description="Pickle file for non-full-length read mapping")
tcp.add_input_file_type(FileTypes.JSON,
"json_in",
name="JSON file",
description="Sentinel file from ice_quiver task")
add_cluster_summary_report_arguments(p)
add_ice_post_quiver_hq_lq_arguments(p)
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - group file
idx 1 - pickle file
Output:
idx 0 - read stat file
idx 1 - abundance file
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_make_abundance_io_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.TXT, "group_txt", "TXT In",
"Group file associating isoforms with reads") # input 0
tcp.add_input_file_type(FileTypes.PICKLE, "hq_lq_pre_dict", "PICKLE In",
"Pickle file containing dicts mapping HQ (LQ) " +
"sample prefixes to ICE cluster output directories") # input 1
tcp.add_output_file_type(FileTypes.TXT, "read_stat_txt",
name="TXT file", description="Read status of FL and nFL reads",
default_name="output_mapped_read_stat")
tcp.add_output_file_type(FileTypes.TXT, "abundance_txt",
name="TXT file", description="Abundance file",
default_name="output_mapped_abundance")
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - A FASTQ file containing uncollapsed isoforms (hq_polished)
idx 1 - A SORTED GMAP SAM file containing alignments mapping uncollapsed
isoforms to reference genomes (produced by map_isoforms_to_genome)
idx 2 - A Pickle file containing dicts mapping HQ (LQ) sample prefixes to
ICE cluster output directories(e.g., hq_lq_pre_dict.pickle)
Output:
idx 0 - A FASTQ file containing representative sequences of filtered collapsed isoforms
idx 1 - A GFF file containing collapsed filtered isoforms
idx 2 - A Abundnace file containing abundance info of collapsed filtered isoforms
idx 3 - A Group file which associates collapsed isoforms with uncollapsed isoforms
idx 4 - A ReadStat file containing FL and nFL read status
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_post_mapping_to_genome_io_arguments(p.arg_parser.parser)
add_post_mapping_to_genome_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.FASTQ, "hq_isoforms_fq", "FASTQ In",
"Input HQ polished isoforms in FASTQ file") # input 0
tcp.add_input_file_type(FileTypes.SAM, "sorted_gmap_sam", "SAM In",
"Sorted GMAP SAM file") # input 1
tcp.add_input_file_type(FileTypes.PICKLE, "hq_lq_pre_dict", "PICKLE In",
"Pickle file containing dicts mapping HQ (LQ) " +
"sample prefixes to ICE cluster output directories") # input 2
tcp.add_output_file_type(FileTypes.FASTQ, "collapsed_filtered_isoforms_fq",
name="FASTQ file",
description="Representative sequences of collapsed filtered isoforms",
default_name="output_mapped") # output 0
tcp.add_output_file_type(FileTypes.GFF, "collapsed_filtered_isoforms_gff",
name="GFF file", description="Collapsed filtered isoforms gff",
default_name="output_mapped") # output 1
tcp.add_output_file_type(FileTypes.TXT, "abundance_txt",
name="TXT file", description="Abundance file",
default_name="output_mapped_abundance") # output 2
tcp.add_output_file_type(FileTypes.TXT, "groups_txt",
name="TXT file", description="Collapsed isoform groups",
default_name="output_mapped_groups") # output 3
tcp.add_output_file_type(FileTypes.TXT, "read_stat_txt",
name="TXT file", description="Read status of FL and nFL reads",
default_name="output_mapped_read_stat") # output 3
# Add tcp options
add_post_mapping_to_genome_tcp_options(tcp)
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - group txt file
idx 1 - abundance txt file
idx 2 - gff file
idx 3 - rep fastq file
Output:
idx 0 - abundance file
idx 1 - gff file
idx 2 - rep fastq file
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_filter_collapsed_isoforms_io_arguments(p.arg_parser.parser)
add_filter_collapsed_isoforms_arguments(p.arg_parser.parser)
# DONT move --max_fuzzy_junction to add_filter_collapsed_isoforms_arguments
p.arg_parser.parser.add_argument(
"--max_fuzzy_junction",
type=int,
default=ci.Constants.MAX_FUZZY_JUNCTION_DEFAULT,
help=ci.Constants.MAX_FUZZY_JUNCTION_DESC)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(
FileTypes.TXT, "group_txt", "TXT In",
"Group file associating isoforms with reads") # input 0
tcp.add_input_file_type(FileTypes.TXT, "abundance_txt", "TXT In",
"Abundance file") # input 1
tcp.add_input_file_type(FileTypes.GFF, "collapsed_isoforms_gff", "GFF In",
"GFF file") # input 2
tcp.add_input_file_type(
FileTypes.FASTQ, "rep_fastq", "FASTQ In",
"Representative sequences of collapsed isoforms in FATSQ") # input 3
tcp.add_output_file_type(
FileTypes.TXT,
"abundance_txt",
name="TXT file",
description="Abundance file",
default_name="output_mapped_filtered_abundance") # output 0
tcp.add_output_file_type(FileTypes.GFF,
"collapsed_isoforms_gff",
name="GFF file",
description="Collapsed isoforms in GFF file",
default_name="output_mapped_filtered") # output 1
tcp.add_output_file_type(
FileTypes.FASTQ,
"rep_fastq",
name="FASTQ file",
description="Representative sequences of collapsed isoforms in FASTQ",
default_name="output_mapped_filtered") # output 2
add_filter_collapsed_isoforms_tcp_options(tcp)
return p
def get_contract_parser():
""" Return resolved tool contract.
input files:
idx 0 - ChunkTasksPickle of ClusterChunkTask objects
idx 1 - sentinel txt
output files:
idx 0 - consensus_isoforms.fa
idx 1 - summary.json
idx 2 - cluster_report.csv
idx 3 - hq_isoforms.contigset.xml
idx 4 - hq_isoforms.fq
idx 5 - lq_isoforms.contigset.xml
idx 6 - lq_isoforms.fq
idx 7 - hq_lq_prefix_dict.pickle
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
p.add_input_file_type(FileTypes.PICKLE, "cluster_chunks_pickle",
"Pickle In", "Cluster chunks pickle file") # input 0
p.add_input_file_type(FileTypes.TXT, "cluster_sentinel_in", "Sentinel In",
"Setinel file") # input idx 1
# output idx 0, consensus_isoforms.contigset,
p.add_output_file_type(FileTypes.DS_CONTIG,
"consensus_isoforms",
name="Unpolished Consensus Isoforms",
description="Output unpolished consensus isoforms",
default_name="consensus_isoforms")
# output idx 1, summary.json,
# output idx 2, cluster_report.csv
add_cluster_summary_report_arguments(p)
# output idx 3, hq_isoforms_fa, idx 4, hq_isoforms_fq,
# idx 5 lq_isoforms_fa, idx 6 lq_isoforms_fq
add_ice_post_quiver_hq_lq_arguments(p)
# output idx 7, hq_lq_prefix_dict.pickle
p.add_output_file_type(
FileTypes.PICKLE,
"hq_lq_prefix_dict",
name="HQ LQ Sample Prefix Dict",
description="Pickle mapping HQ (LQ) sample prefixes to ICE dir",
default_name="hq_lq_prefix_dict")
# user specified sample name.
p.add_str(option_id=Constants.SAMPLE_NAME_ID,
option_str="sample_name",
default=Constants.SAMPLE_NAME_DEFAULT,
name="sample Name",
description="Sample Name")
return p
def get_contract_parser():
""" Return resolved tool contract.
input files:
idx 0 - ChunkTasksPickle of ClusterChunkTask objects
idx 1 - sentinel txt
output files:
idx 0 - consensus_isoforms.fa
idx 1 - summary.json
idx 2 - cluster_report.csv
idx 3 - hq_isoforms.contigset.xml
idx 4 - hq_isoforms.fq
idx 5 - lq_isoforms.contigset.xml
idx 6 - lq_isoforms.fq
idx 7 - hq_lq_prefix_dict.pickle
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
p.add_input_file_type(FileTypes.PICKLE, "cluster_chunks_pickle", "Pickle In",
"Cluster chunks pickle file") # input 0
p.add_input_file_type(FileTypes.TXT, "cluster_sentinel_in", "Sentinel In",
"Setinel file") # input idx 1
# output idx 0, consensus_isoforms.contigset,
p.add_output_file_type(FileTypes.DS_CONTIG, "consensus_isoforms",
name="Unpolished Consensus Isoforms",
description="Output unpolished consensus isoforms",
default_name="consensus_isoforms")
# output idx 1, summary.json,
# output idx 2, cluster_report.csv
add_cluster_summary_report_arguments(p)
# output idx 3, hq_isoforms_fa, idx 4, hq_isoforms_fq,
# idx 5 lq_isoforms_fa, idx 6 lq_isoforms_fq
add_ice_post_quiver_hq_lq_arguments(p)
# output idx 7, hq_lq_prefix_dict.pickle
p.add_output_file_type(FileTypes.PICKLE, "hq_lq_prefix_dict",
name="HQ LQ Sample Prefix Dict",
description="Pickle mapping HQ (LQ) sample prefixes to ICE dir",
default_name="hq_lq_prefix_dict")
# user specified sample name.
p.add_str(option_id=Constants.SAMPLE_NAME_ID, option_str="sample_name",
default=Constants.SAMPLE_NAME_DEFAULT, name="sample Name",
description="Sample Name")
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - group txt file
idx 1 - abundance txt file
idx 2 - gff file
idx 3 - rep fastq file
Output:
idx 0 - abundance file
idx 1 - gff file
idx 2 - rep fastq file
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_filter_collapsed_isoforms_io_arguments(p.arg_parser.parser)
add_filter_collapsed_isoforms_arguments(p.arg_parser.parser)
# DONT move --max_fuzzy_junction to add_filter_collapsed_isoforms_arguments
p.arg_parser.parser.add_argument("--max_fuzzy_junction", type=int,
default=ci.Constants.MAX_FUZZY_JUNCTION_DEFAULT,
help=ci.Constants.MAX_FUZZY_JUNCTION_DESC)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.TXT, "group_txt", "TXT In",
"Group file associating isoforms with reads") # input 0
tcp.add_input_file_type(FileTypes.TXT, "abundance_txt", "TXT In",
"Abundance file") # input 1
tcp.add_input_file_type(FileTypes.GFF, "collapsed_isoforms_gff", "GFF In",
"GFF file") # input 2
tcp.add_input_file_type(FileTypes.FASTQ, "rep_fastq", "FASTQ In",
"Representative sequences of collapsed isoforms in FATSQ") # input 3
tcp.add_output_file_type(FileTypes.TXT, "abundance_txt",
name="TXT file", description="Abundance file",
default_name="output_mapped_filtered_abundance") # output 0
tcp.add_output_file_type(FileTypes.GFF, "collapsed_isoforms_gff",
name="GFF file", description="Collapsed isoforms in GFF file",
default_name="output_mapped_filtered") # output 1
tcp.add_output_file_type(FileTypes.FASTQ, "rep_fastq", name="FASTQ file",
description="Representative sequences of collapsed isoforms in FASTQ",
default_name="output_mapped_filtered") # output 2
add_filter_collapsed_isoforms_tcp_options(tcp)
return p
def get_contract_parser():
p = get_base_contract_parser(Constants, default_level="DEBUG")
arg_parser = p.arg_parser.parser
tcp = p.tool_contract_parser
add_fofn_arguments(arg_parser, bas_fofn=True,
tool_contract_parser=tcp)
tcp.add_input_file_type(FileTypes.DS_CONTIG, "consensus_fa",
name="ContigSet", description="Consensus isoforms")
tcp.add_input_file_type(FileTypes.PICKLE, "cluster_pickle",
name="Clusters",
description="Cluster pickle file")
tcp.add_input_file_type(FileTypes.PICKLE, "map_nofl_pickle",
name="Pickle file",
description="Pickle file for non-full-length read mapping")
# XXX this file does nothing other than connect this task to
# ice_quiver_postprocess in pbsmrtpipe
tcp.add_output_file_type(FileTypes.JSON, "json_out", "JSON file",
"JSON sentinel file", default_name="quiver_out")
return p
def get_contract_parser():
p = get_base_contract_parser(Constants, default_level="DEBUG")
tcp = p.tool_contract_parser
add_fofn_arguments(p.arg_parser.parser, bas_fofn=True,
tool_contract_parser=tcp)
tcp.add_input_file_type(FileTypes.DS_CONTIG, "consensus_fa",
name="Consensus isoforms",
description="ContigSet of consensus isoforms")
tcp.add_input_file_type(FileTypes.PICKLE, "cluster_pickle",
name="Clusters",
description="Cluster pickle file")
tcp.add_input_file_type(FileTypes.PICKLE, "map_nofl_pickle",
name="Pickle file",
description="Pickle file for non-full-length read mapping")
tcp.add_input_file_type(FileTypes.JSON, "json_in", name="JSON file",
description="Sentinel file from ice_quiver task")
add_cluster_summary_report_arguments(p)
add_ice_post_quiver_hq_lq_arguments(p)
return p
def get_contract_parser():
""" Return resolved tool contract.
input files:
idx 0 - ChunkTasksPickle of ClusterChunkTask objects
idx 1 - ice_polish_cluster_bins sentinel txt
output files:
idx 0 - sentinal
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
p.add_input_file_type(FileTypes.PICKLE, "cluster_chunks_pickle", "Pickle In",
"Cluster chunks pickle file") # input idx 0
p.add_input_file_type(FileTypes.TXT, "ice_polish_cluster_bins_sentinel", "Sentinel In",
"Setinel file") # input idx 1
# output idx 0, consensus_isoforms.contigset,
p.add_output_file_type(FileTypes.TXT, "ice_cleanup_sentinel",
name="Sentinel file",
description="Output sentinel file",
default_name="ice_cleanup_done")
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 -
Output:
idx 0 - reads which can represent collapsed isoforms in CONTIGSET
idx 1 - collapsed isoforms in GFF
idx 2 - collapsed isoform groups in TXT
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_collapse_mapped_isoforms_io_arguments(p.arg_parser.parser)
add_collapse_mapped_isoforms_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(
FileTypes.DS_CONTIG, "hq_isoforms_ds", "ContigSet In",
"Input HQ polished isoforms in ContigSet file") # input 0
tcp.add_input_file_type(FileTypes.SAM, "sorted_gmap_sam", "SAM In",
"Sorted GMAP SAM file") # input 1
tcp.add_output_file_type(
FileTypes.DS_CONTIG,
"collapsed_isoforms_rep_ds",
name="Collapsed isoforms",
description="Representative reads of collapsed isoforms",
default_name="output") # output 0
tcp.add_output_file_type(FileTypes.GFF,
"collapsed_isoforms_gff",
name="Collapsed isoforms GFF",
description="Collapsed isoforms gff",
default_name="output") # output 1
tcp.add_output_file_type(FileTypes.TXT,
"groups_txt",
name="TXT file",
description="Collapsed isoform groups",
default_name="output_groups") # output 2
add_collapse_mapped_isoforms_tcp_options(tcp)
return p
def get_contract_parser():
"""
Return tool contract parser for running ICE clustering
no quiver, no sge setting needed.
The tool contract parser has 2 inputs:
idx 0 - cluster_chunks.pickle (original or spawned)
idx 1 - ccs,
and has one outputs:
idx 0 - cluster_chunk_done.txt, a sential file which does nothing
but connect ICE cluster and the subsequence ice_partial
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
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.TXT, "cluster done txt",
name="Cluster Done Txt file",
description="Cluster Done Txt file.",
default_name="cluster_chunks_done")
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_base_contract_parser(Constants, default_level="DEBUG")
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
# this file does nothing other than connect pbsmrtpipe tasks
p.add_output_file_type(FileTypes.TXT, "polish done txt",
name="Polish Done Txt file",
description="Polish Done Txt file.",
default_name="polish_chunks_done")
return p
def get_contract_parser():
p = get_base_contract_parser(Constants, default_level="DEBUG")
add_cluster_arguments(p)
p.tool_contract_parser.add_output_file_type(
FileTypes.PICKLE, "pickle_fn",
name="Clusters pickle file",
description="Python pickle file of clusters",
default_name="final_clusters")
# rtc has 4 inputs:
# idx 0 - flnc.contigset,
# idx 1 - nfl.contigset,
# idx 2 - ccs,
# idx 3 - subreads
#
# rtc has 4 outputs:
# idx 0 - consensus_isoform.contigset,
# idx 1 - output.json,
# idx 2 - output.csv
# idx 3 - output.pickle
return p
def get_contract_parser():
"""Return a tool contract parser for separate_flnc.
Input:
idx 0 - flnc.fa|fq|ds
Output:
idx 0 - out.pickle
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
add_separate_flnc_io_arguments(p.arg_parser.parser)
add_separate_flnc_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.DS_CONTIG, "flnc_fa",
name="FASTA or ContigSet file",
description="FLNC reads ContigSet")
tcp.add_output_file_type(FileTypes.PICKLE, "out_pickle",
default_name="separate_flnc",
name="Bins of FLNC Reads", description="output bins in pickle.")
add_separate_flnc_tcp_options(tcp)
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_base_contract_parser(Constants, default_level="DEBUG")
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
# this file does nothing other than connect pbsmrtpipe tasks
p.add_output_file_type(FileTypes.TXT,
"polish done txt",
name="Polish Done Txt file",
description="Polish Done Txt file.",
default_name="polish_chunks_done")
return p
def get_contract_parser():
"""
Return tool contract parser for running ICE clustering
no quiver, no sge setting needed.
The tool contract parser has 2 inputs:
idx 0 - cluster_chunks.pickle (original or spawned)
idx 1 - ccs,
and has one outputs:
idx 0 - cluster_chunk_done.txt, a sential file which does nothing
but connect ICE cluster and the subsequence ice_partial
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
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.TXT,
"cluster done txt",
name="Cluster Done Txt file",
description="Cluster Done Txt file.",
default_name="cluster_chunks_done")
return p
def get_contract_parser():
"""Tool contract should have the following inputs and outputs.
input:
idx 0: partial_chunks.pickle
idx 1: ccs
idx 2: sentinel txt file
output
idx 0 - partial_chunk_done.txt, a sential file which does nothing
but connect ice_partial and the subsequence task
combine_ice_partial
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
p.add_input_file_type(FileTypes.PICKLE, "partial_chunks_pickle", "Pickle In",
"Partial chunks pickle file") # input 0
p.add_input_file_type(FileTypes.TXT, "partial_sentinel_in", "Sentinel In",
"Setinel file") # input 1
p.add_input_file_type(FileTypes.DS_CCS, "ccs_in", "ConsensusReadSet In",
"PacBio ConsensusReadSet") # input 2
p.add_output_file_type(FileTypes.TXT, "partial done txt",
name="Partial Done Txt file",
description="Partial Done Txt file.",
default_name="partial_chunks_done")
return p
def get_contract_parser():
"""Tool contract should have the following inputs and outputs.
input:
idx 0: partial_chunks.pickle
idx 1: ccs
idx 2: sentinel txt file
output
idx 0 - partial_chunk_done.txt, a sential file which does nothing
but connect ice_partial and the subsequence task
combine_ice_partial
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
p.add_input_file_type(FileTypes.PICKLE, "partial_chunks_pickle",
"Pickle In", "Partial chunks pickle file") # input 0
p.add_input_file_type(FileTypes.TXT, "partial_sentinel_in", "Sentinel In",
"Setinel file") # input 1
p.add_input_file_type(FileTypes.DS_CCS, "ccs_in", "ConsensusReadSet In",
"PacBio ConsensusReadSet") # input 2
p.add_output_file_type(FileTypes.TXT,
"partial done txt",
name="Partial Done Txt file",
description="Partial Done Txt file.",
default_name="partial_chunks_done")
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 -
Output:
idx 0 - reads which can represent collapsed isoforms in CONTIGSET
idx 1 - collapsed isoforms in GFF
idx 2 - collapsed isoform groups in TXT
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_collapse_mapped_isoforms_io_arguments(p.arg_parser.parser)
add_collapse_mapped_isoforms_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.DS_CONTIG, "hq_isoforms_ds", "ContigSet In",
"Input HQ polished isoforms in ContigSet file") # input 0
tcp.add_input_file_type(FileTypes.SAM, "sorted_gmap_sam", "SAM In",
"Sorted GMAP SAM file") # input 1
tcp.add_output_file_type(FileTypes.DS_CONTIG, "collapsed_isoforms_rep_ds",
name="Collapsed isoforms",
description="Representative reads of collapsed isoforms",
default_name="output") # output 0
tcp.add_output_file_type(FileTypes.GFF, "collapsed_isoforms_gff",
name="Collapsed isoforms GFF",
description="Collapsed isoforms gff",
default_name="output") # output 1
tcp.add_output_file_type(FileTypes.TXT, "groups_txt",
name="TXT file",
description="Collapsed isoform groups",
default_name="output_groups") # output 2
add_collapse_mapped_isoforms_tcp_options(tcp)
return p
def get_contract_parser():
"""Return a tool contract parser for separate_flnc.
Input:
idx 0 - flnc.fa|fq|ds
Output:
idx 0 - out.pickle
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
add_separate_flnc_io_arguments(p.arg_parser.parser)
add_separate_flnc_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.DS_CONTIG,
"flnc_fa",
name="FASTA or ContigSet file",
description="FLNC reads ContigSet")
tcp.add_output_file_type(FileTypes.PICKLE,
"out_pickle",
default_name="separate_flnc",
name="Binned transcripts pickle file",
description="output bins in pickle.")
add_separate_flnc_tcp_options(tcp)
return p
def get_contract_parser():
p = get_base_contract_parser(Constants, default_level="INFO")
add_ice_partial_one_arguments(p)
return p
def get_contract_parser():
p = get_base_contract_parser(Constants)
add_subset_arguments(p)
return p
def get_contract_parser():
p = get_base_contract_parser(Constants)
add_subset_arguments(p)
return p
def get_contract_parser():
p = get_base_contract_parser(Constants, default_level="INFO")
add_ice_partial_one_arguments(p)
return p
def get_contract_parser():
"""Get tool contract parser.
Input:
idx 0 - A FASTQ file containing uncollapsed isoforms (hq_polished)
idx 1 - A SORTED GMAP SAM file containing alignments mapping uncollapsed
isoforms to reference genomes (produced by map_isoforms_to_genome)
idx 2 - A Pickle file containing dicts mapping HQ (LQ) sample prefixes to
ICE cluster output directories(e.g., hq_lq_pre_dict.pickle)
Output:
idx 0 - A FASTQ file containing representative sequences of filtered collapsed isoforms
idx 1 - A GFF file containing collapsed filtered isoforms
idx 2 - A Abundnace file containing abundance info of collapsed filtered isoforms
idx 3 - A Group file which associates collapsed isoforms with uncollapsed isoforms
idx 4 - A ReadStat file containing FL and nFL read status
"""
p = get_base_contract_parser(Constants, default_level="DEBUG")
# argument parser
add_post_mapping_to_genome_io_arguments(p.arg_parser.parser)
add_post_mapping_to_genome_arguments(p.arg_parser.parser)
# tool contract parser
tcp = p.tool_contract_parser
tcp.add_input_file_type(
FileTypes.FASTQ, "hq_isoforms_fq", "FASTQ In",
"Input HQ polished isoforms in FASTQ file") # input 0
tcp.add_input_file_type(FileTypes.SAM, "sorted_gmap_sam", "SAM In",
"Sorted GMAP SAM file") # input 1
tcp.add_input_file_type(
FileTypes.PICKLE, "hq_lq_pre_dict", "PICKLE In",
"Pickle file containing dicts mapping HQ (LQ) " +
"sample prefixes to ICE cluster output directories") # input 2
tcp.add_output_file_type(
FileTypes.FASTQ,
"collapsed_filtered_isoforms_fq",
name="Collapsed Filtered Isoforms",
description="Representative sequences of collapsed filtered isoforms",
default_name="output_mapped") # output 0
tcp.add_output_file_type(FileTypes.GFF,
"collapsed_filtered_isoforms_gff",
name="Collapsed Filtered Isoforms",
description="Collapsed filtered isoforms gff",
default_name="output_mapped") # output 1
tcp.add_output_file_type(
FileTypes.TXT,
"abundance_txt",
name="Isoform Abundance",
description="Abundance file",
default_name="output_mapped_abundance") # output 2
tcp.add_output_file_type(FileTypes.TXT,
"groups_txt",
name="Collapsed Isoform Groups",
description="Collapsed isoform groups",
default_name="output_mapped_groups") # output 3
tcp.add_output_file_type(
FileTypes.TXT,
"read_stat_txt",
name="FL nFL Reads Status",
description="Read status of FL and nFL reads",
default_name="output_mapped_read_stat") # output 4
# Add tcp options
add_post_mapping_to_genome_tcp_options(tcp)
return p
def get_contract_parser():
"""Get PbParser for classify."""
p = get_base_contract_parser(Constants, default_level="DEBUG")
add_classify_arguments(p)
return p
