def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent(
'''
output files:
germ-pass
database with assigned germline sequences.
germ-fail
database with records failing germline assignment.
required fields:
SEQUENCE_ID, SEQUENCE_INPUT, SEQUENCE_VDJ or SEQUENCE_IMGT,
V_CALL or V_CALL_GENOTYPED, D_CALL, J_CALL,
V_SEQ_START, V_SEQ_LENGTH, V_GERM_START_IMGT, V_GERM_LENGTH_IMGT,
D_SEQ_START, D_SEQ_LENGTH, D_GERM_START, D_GERM_LENGTH,
J_SEQ_START, J_SEQ_LENGTH, J_GERM_START, J_GERM_LENGTH
optional fields:
CLONE
output fields:
GERMLINE_VDJ, GERMLINE_VDJ_D_MASK, GERMLINE_VDJ_V_REGION,
GERMLINE_IMGT, GERMLINE_IMGT_D_MASK, GERMLINE_IMGT_V_REGION
''')
# Parent parser
parser_parent = getCommonArgParser(seq_in=False, seq_out=False, db_in=True,
annotation=False)
# Define argument parser
parser = ArgumentParser(description=__doc__, epilog=fields,
parents=[parser_parent],
formatter_class=CommonHelpFormatter)
parser.add_argument('--version', action='version',
version='%(prog)s:' + ' %s-%s' %(__version__, __date__))
parser.add_argument('-r', nargs='+', action='store', dest='repo', required=True,
help='List of folders and/or fasta files with germline sequences.')
parser.add_argument('-g', action='store', dest='germ_types', default=default_germ_types,
nargs='+', choices=('full', 'dmask', 'vonly'),
help='Specify type(s) of germlines to include full germline, \
germline with D-region masked, or germline for V region only.')
parser.add_argument('--cloned', action='store_true', dest='cloned',
help='Specify to create only one germline per clone \
(assumes input file is sorted by clone column)')
parser.add_argument('--vf', action='store', dest='v_field', default=default_v_field,
help='Specify field to use for germline V call')
parser.add_argument('--sf', action='store', dest='seq_field', default=default_seq_field,
help='Specify field to use for sequence')
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent(
'''
output files:
sequences
FASTA formatted sequences output from the subcommands fasta and clip.
<field>-<value>
database files partitioned by annotation <field> and <value>.
parse-<command>
output of the database modification functions where <command> is one of
the subcommands add, index, drop, delete, rename, select, sort or update.
required fields:
SEQUENCE_ID
optional fields:
JUNCTION, SEQUENCE_IMGT, SEQUENCE_VDJ, GERMLINE_IMGT, GERMLINE_VDJ,
GERMLINE_IMGT_D_MASK, GERMLINE_VDJ_D_MASK,
GERMLINE_IMGT_V_REGION, GERMLINE_VDJ_V_REGION
output fields:
None
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__, epilog=fields,
formatter_class=CommonHelpFormatter)
parser.add_argument('--version', action='version',
version='%(prog)s:' + ' %s-%s' %(__version__, __date__))
subparsers = parser.add_subparsers(title='subcommands', dest='command', metavar='',
help='Database operation')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Define parent parser
parser_parent = getCommonArgParser(seq_in=False, seq_out=False, db_in=True,
failed=False, log=False)
# Subparser to convert database entries to sequence file
parser_seq = subparsers.add_parser('fasta', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Creates a fasta file from database records')
parser_seq.add_argument('--if', action='store', dest='id_field',
default=default_id_field,
help='The name of the field containing identifiers')
parser_seq.add_argument('--sf', action='store', dest='seq_field',
default=default_seq_field,
help='The name of the field containing sequences')
parser_seq.add_argument('--mf', nargs='+', action='store', dest='meta_fields',
help='List of annotation fields to add to the sequence description')
parser_seq.set_defaults(func=convertDbFasta)
# Subparser to convert database entries to clip-fasta file
parser_clip = subparsers.add_parser('clip', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='''Creates a clip-fasta file from database
records, wherein germline sequences precede
each clone and are denoted by ">>" headers.''')
parser_clip.add_argument('--if', action='store', dest='id_field',
default=default_id_field,
help='The name of the field containing identifiers')
parser_clip.add_argument('--sf', action='store', dest='seq_field',
default=default_seq_field,
help='The name of the field containing reads')
parser_clip.add_argument('--gf', action='store', dest='germ_field',
default=default_germ_field,
help='The name of the field containing germline sequences')
parser_clip.add_argument('--cf', action='store', dest='cluster_field', default=None,
help='The name of the field containing containing sorted clone IDs')
parser_clip.add_argument('--mf', nargs='+', action='store', dest='meta_fields',
help='List of annotation fields to add to the sequence description')
parser_clip.set_defaults(func=convertDbClip)
# Subparser to partition files by annotation values
parser_split = subparsers.add_parser('split', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Splits database files by field values')
parser_split.add_argument('-f', action='store', dest='field', type=str, required=True,
help='Annotation field by which to split database files.')
parser_split.add_argument('--num', action='store', dest='num_split', type=float, default=None,
help='''Specify to define the field as numeric and group
records by whether they are less than or at least
(greater than or equal to) the specified value.''')
parser_split.set_defaults(func=splitDbFile)
# Subparser to add records
parser_add = subparsers.add_parser('add', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Adds field and value pairs')
parser_add.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to add.')
parser_add.add_argument('-u', nargs='+', action='store', dest='values', required=True,
help='The value to assign to all rows for each field.')
parser_add.set_defaults(func=addDbFile)
# Subparser to delete records
parser_delete = subparsers.add_parser('delete', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Deletes specific records')
parser_delete.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to check for deletion criteria.')
parser_delete.add_argument('-u', nargs='+', action='store', dest='values', default=['', 'NA'],
help='''The values defining which records to delete. A value
may appear in any of the fields specified with -f.''')
parser_delete.add_argument('--logic', action='store', dest='logic',
choices=('any', 'all'), default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).''')
parser_delete.add_argument('--regex', action='store_true', dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_delete.set_defaults(func=deleteDbFile)
# Subparser to drop fields
parser_drop = subparsers.add_parser('drop', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Deletes entire fields')
parser_drop.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to delete from the database.')
parser_drop.set_defaults(func=dropDbFile)
# Subparser to index fields
parser_index = subparsers.add_parser('index', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Adds a numeric index field')
parser_index.add_argument('-f', action='store', dest='field',
default=default_index_field,
help='The name of the index field to add to the database.')
parser_index.set_defaults(func=indexDbFile)
# Subparser to rename fields
parser_rename = subparsers.add_parser('rename', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Renames fields')
parser_rename.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='List of fields to rename.')
parser_rename.add_argument('-k', nargs='+', action='store', dest='names', required=True,
help='List of new names for each field.')
parser_rename.set_defaults(func=renameDbFile)
# Subparser to select records
parser_select = subparsers.add_parser('select', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Selects specific records')
parser_select.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to check for selection criteria.')
parser_select.add_argument('-u', nargs='+', action='store', dest='values', required=True,
help='''The values defining with records to select. A value
may appear in any of the fields specified with -f.''')
parser_select.add_argument('--logic', action='store', dest='logic',
choices=('any', 'all'), default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).''')
parser_select.add_argument('--regex', action='store_true', dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_select.set_defaults(func=selectDbFile)
# Subparser to sort file by records
parser_sort = subparsers.add_parser('sort', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Sorts records by field values')
parser_sort.add_argument('-f', action='store', dest='field', type=str, required=True,
help='The annotation field by which to sort records.')
parser_sort.add_argument('--num', action='store_true', dest='numeric', default=False,
help='''Specify to define the sort column as numeric rather
than textual.''')
parser_sort.add_argument('--descend', action='store_true', dest='descend',
help='''If specified, sort records in descending, rather
than ascending, order by values in the target field.''')
parser_sort.set_defaults(func=sortDbFile)
# Subparser to update records
parser_update = subparsers.add_parser('update', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Updates field and value pairs')
parser_update.add_argument('-f', action='store', dest='field', required=True,
help='The name of the field to update.')
parser_update.add_argument('-u', nargs='+', action='store', dest='values', required=True,
help='The values that will be replaced.')
parser_update.add_argument('-t', nargs='+', action='store', dest='updates', required=True,
help='''The new value to assign to each selected row.''')
parser_update.set_defaults(func=updateDbFile)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output fields
fields = dedent(
'''
output files:
clone-pass
database with assigned clonal group numbers.
clone-fail
database with records failing clonal grouping.
required fields:
SEQUENCE_ID, V_CALL or V_CALL_GENOTYPED, D_CALL, J_CALL, JUNCTION_LENGTH
<field>
sequence field specified by the --sf parameter
output fields:
CLONE
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__, epilog=fields,
formatter_class=CommonHelpFormatter)
parser.add_argument('--version', action='version',
version='%(prog)s:' + ' %s-%s' %(__version__, __date__))
subparsers = parser.add_subparsers(title='subcommands', dest='command', metavar='',
help='Cloning method')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Parent parser
parser_parent = getCommonArgParser(seq_in=False, seq_out=False, db_in=True,
multiproc=True)
# Distance cloning method
parser_bygroup = subparsers.add_parser('bygroup', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='''Defines clones as having same V assignment,
J assignment, and junction length with
specified substitution distance model.''')
parser_bygroup.add_argument('-f', nargs='+', action='store', dest='fields', default=None,
help='Additional fields to use for grouping clones (non VDJ)')
parser_bygroup.add_argument('--mode', action='store', dest='mode',
choices=('allele', 'gene'), default='gene',
help='''Specifies whether to use the V(D)J allele or gene for
initial grouping.''')
parser_bygroup.add_argument('--act', action='store', dest='action', default='set',
choices=('first', 'set'),
help='''Specifies how to handle multiple V(D)J assignments
for initial grouping.''')
parser_bygroup.add_argument('--model', action='store', dest='model',
choices=('aa', 'ham', 'm1n', 'hs1f', 'hs5f'),
default=default_bygroup_model,
help='''Specifies which substitution model to use for
calculating distance between sequences. Where m1n is the
mouse single nucleotide transition/trasversion model
of Smith et al, 1996; hs1f is the human single
nucleotide model derived from Yaari et al, 2013; hs5f
is the human S5F model of Yaari et al, 2013; ham is
nucleotide Hamming distance; and aa is amino acid
Hamming distance. The hs5f data should be
considered experimental.''')
parser_bygroup.add_argument('--dist', action='store', dest='distance', type=float,
default=default_distance,
help='The distance threshold for clonal grouping')
parser_bygroup.add_argument('--norm', action='store', dest='norm',
choices=('len', 'mut', 'none'), default=default_norm,
help='''Specifies how to normalize distances. One of none
(do not normalize), len (normalize by length),
or mut (normalize by number of mutations between sequences).''')
parser_bygroup.add_argument('--sym', action='store', dest='sym',
choices=('avg', 'min'), default=default_sym,
help='''Specifies how to combine asymmetric distances. One of avg
(average of A->B and B->A) or min (minimum of A->B and B->A).''')
parser_bygroup.add_argument('--link', action='store', dest='linkage',
choices=('single', 'average', 'complete'), default=default_linkage,
help='''Type of linkage to use for hierarchical clustering.''')
parser_bygroup.add_argument('--sf', action='store', dest='seq_field',
default=default_seq_field,
help='''The name of the field to be used to calculate
distance between records''')
parser_bygroup.set_defaults(feed_func=feedQueue)
parser_bygroup.set_defaults(work_func=processQueue)
parser_bygroup.set_defaults(collect_func=collectQueue)
parser_bygroup.set_defaults(group_func=indexJunctions)
parser_bygroup.set_defaults(clone_func=distanceClones)
# Hierarchical clustering cloning method
parser_hclust = subparsers.add_parser('hclust', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Defines clones by specified distance metric on CDR3s and \
cutting of hierarchical clustering tree')
# parser_hclust.add_argument('-f', nargs='+', action='store', dest='fields', default=None,
# help='Fields to use for grouping clones (non VDJ)')
parser_hclust.add_argument('--method', action='store', dest='method',
choices=('chen2010', 'ademokun2011'), default=default_hclust_model,
help='Specifies which cloning method to use for calculating distance \
between CDR3s, computing linkage, and cutting clusters')
parser_hclust.set_defaults(feed_func=feedQueueClust)
parser_hclust.set_defaults(work_func=processQueueClust)
parser_hclust.set_defaults(collect_func=collectQueueClust)
parser_hclust.set_defaults(cluster_func=hierClust)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define output file names and header fields
fields = dedent('''
output files:
align-pass
database with multiple aligned sequences.
align-fail
database with records failing alignment.
required fields:
sequence_id, v_call, j_call
<field>
user specified sequence fields to align.
output fields:
<field>_align
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__,
epilog=fields,
formatter_class=CommonHelpFormatter,
add_help=False)
group_help = parser.add_argument_group('help')
group_help.add_argument('--version',
action='version',
version='%(prog)s:' + ' %s %s' %
(__version__, __date__))
group_help.add_argument('-h',
'--help',
action='help',
help='show this help message and exit')
subparsers = parser.add_subparsers(title='subcommands',
dest='command',
metavar='',
help='alignment method')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Parent parser
parser_parent = getCommonArgParser(format=True, multiproc=True)
# Argument parser for column-wise alignment across records
parser_across = subparsers.add_parser(
'across',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='''Multiple aligns sequence columns within groups
and across rows using MUSCLE.'''
)
group_across = parser_across.add_argument_group('alignment arguments')
group_across.add_argument(
'--sf',
nargs='+',
action='store',
dest='seq_fields',
required=True,
help='The sequence fields to multiple align within each group.')
group_across.add_argument(
'--gf',
nargs='+',
action='store',
dest='group_fields',
default=None,
help='Additional (not allele call) fields to use for grouping.')
group_across.add_argument(
'--calls',
nargs='+',
action='store',
dest='calls',
choices=('v', 'd', 'j'),
default=['v', 'j'],
help='Segment calls (allele assignments) to use for grouping.')
group_across.add_argument(
'--mode',
action='store',
dest='mode',
choices=('allele', 'gene'),
default='gene',
help='''Specifies whether to use the V(D)J allele or gene when
an allele call field (--calls) is specified.'''
)
group_across.add_argument(
'--act',
action='store',
dest='action',
default='first',
choices=('first', ),
help='''Specifies how to handle multiple values within default
allele call fields. Currently, only "first" is supported.'''
)
group_across.add_argument('--exec',
action='store',
dest='muscle_exec',
default=default_muscle_exec,
help='The location of the MUSCLE executable')
parser_across.set_defaults(group_func=groupRecords, align_func=alignAcross)
# Argument parser for alignment of fields within records
parser_within = subparsers.add_parser(
'within',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Multiple aligns sequence fields within rows using MUSCLE')
group_within = parser_within.add_argument_group('alignment arguments')
group_within.add_argument(
'--sf',
nargs='+',
action='store',
dest='seq_fields',
required=True,
help='The sequence fields to multiple align within each record.')
group_within.add_argument('--exec',
action='store',
dest='muscle_exec',
default=default_muscle_exec,
help='The location of the MUSCLE executable')
parser_within.set_defaults(group_func=None, align_func=alignWithin)
# Argument parser for column-wise alignment across records
parser_block = subparsers.add_parser(
'block',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='''Multiple aligns sequence groups across both
columns and rows using MUSCLE.''')
group_block = parser_block.add_argument_group('alignment arguments')
group_block.add_argument(
'--sf',
nargs='+',
action='store',
dest='seq_fields',
required=True,
help='The sequence fields to multiple align within each group.')
group_block.add_argument(
'--gf',
nargs='+',
action='store',
dest='group_fields',
default=None,
help='Additional (not allele call) fields to use for grouping.')
group_block.add_argument(
'--calls',
nargs='+',
action='store',
dest='calls',
choices=('v', 'd', 'j'),
default=['v', 'j'],
help='Segment calls (allele assignments) to use for grouping.')
group_block.add_argument(
'--mode',
action='store',
dest='mode',
choices=('allele', 'gene'),
default='gene',
help='''Specifies whether to use the V(D)J allele or gene when
an allele call field (--calls) is specified.'''
)
group_block.add_argument(
'--act',
action='store',
dest='action',
default='first',
choices=('first', ),
help='''Specifies how to handle multiple values within default
allele call fields. Currently, only "first" is supported.'''
)
group_block.add_argument('--exec',
action='store',
dest='muscle_exec',
default=default_muscle_exec,
help='The location of the MUSCLE executable')
parser_block.set_defaults(group_func=groupRecords, align_func=alignBlocks)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent('''
output files:
sequences
FASTA formatted sequences output from the subcommands fasta and clip.
<field>-<value>
database files partitioned by annotation <field> and <value>.
parse-<command>
output of the database modification functions where <command> is one of
the subcommands add, index, drop, delete, rename, select, sort or update.
required fields:
sequence_id
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__,
epilog=fields,
formatter_class=CommonHelpFormatter,
add_help=False)
group_help = parser.add_argument_group('help')
group_help.add_argument('--version',
action='version',
version='%(prog)s:' + ' %s %s' %
(__version__, __date__))
group_help.add_argument('-h',
'--help',
action='help',
help='show this help message and exit')
subparsers = parser.add_subparsers(title='subcommands',
dest='command',
metavar='',
help='Database operation')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Define parent parsers
default_parent = getCommonArgParser(failed=False, log=False, format=False)
multi_parent = getCommonArgParser(out_file=False,
failed=False,
log=False,
format=False)
# Subparser to add records
parser_add = subparsers.add_parser(
'add',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Adds field and value pairs.',
description='Adds field and value pairs.')
group_add = parser_add.add_argument_group('parsing arguments')
group_add.add_argument('-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to add.')
group_add.add_argument(
'-u',
nargs='+',
action='store',
dest='values',
required=True,
help='The value to assign to all rows for each field.')
parser_add.set_defaults(func=addDbFile)
# Subparser to delete records
parser_delete = subparsers.add_parser(
'delete',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Deletes specific records.',
description='Deletes specific records.')
group_delete = parser_delete.add_argument_group('parsing arguments')
group_delete.add_argument(
'-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to check for deletion criteria.')
group_delete.add_argument(
'-u',
nargs='+',
action='store',
dest='values',
default=['', 'NA'],
help='''The values defining which records to delete. A value
may appear in any of the fields specified with -f.'''
)
group_delete.add_argument(
'--logic',
action='store',
dest='logic',
choices=('any', 'all'),
default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).'''
)
group_delete.add_argument(
'--regex',
action='store_true',
dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_delete.set_defaults(func=deleteDbFile)
# Subparser to drop fields
parser_drop = subparsers.add_parser('drop',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Deletes entire fields.',
description='Deletes entire fields.')
group_drop = parser_drop.add_argument_group('parsing arguments')
group_drop.add_argument(
'-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to delete from the database.')
parser_drop.set_defaults(func=dropDbFile)
# Subparser to index fields
parser_index = subparsers.add_parser(
'index',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Adds a numeric index field.',
description='Adds a numeric index field.')
group_index = parser_index.add_argument_group('parsing arguments')
group_index.add_argument(
'-f',
action='store',
dest='field',
default=default_index_field,
help='The name of the index field to add to the database.')
parser_index.set_defaults(func=indexDbFile)
# Subparser to rename fields
parser_rename = subparsers.add_parser('rename',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Renames fields.',
description='Renames fields.')
group_rename = parser_rename.add_argument_group('parsing arguments')
group_rename.add_argument('-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='List of fields to rename.')
group_rename.add_argument('-k',
nargs='+',
action='store',
dest='names',
required=True,
help='List of new names for each field.')
parser_rename.set_defaults(func=renameDbFile)
# Subparser to select records
parser_select = subparsers.add_parser(
'select',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Selects specific records.',
description='Selects specific records.')
group_select = parser_select.add_argument_group('parsing arguments')
group_select.add_argument(
'-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to check for selection criteria.')
group_select.add_argument(
'-u',
nargs='+',
action='store',
dest='values',
required=True,
help='''The values defining with records to select. A value
may appear in any of the fields specified with -f.'''
)
group_select.add_argument(
'--logic',
action='store',
dest='logic',
choices=('any', 'all'),
default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).'''
)
group_select.add_argument(
'--regex',
action='store_true',
dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_select.set_defaults(func=selectDbFile)
# Subparser to sort file by records
parser_sort = subparsers.add_parser(
'sort',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Sorts records by field values.',
description='Sorts records by field values.')
group_sort = parser_sort.add_argument_group('parsing arguments')
group_sort.add_argument(
'-f',
action='store',
dest='field',
type=str,
required=True,
help='The annotation field by which to sort records.')
group_sort.add_argument(
'--num',
action='store_true',
dest='numeric',
default=False,
help='''Specify to define the sort column as numeric rather
than textual.''')
group_sort.add_argument(
'--descend',
action='store_true',
dest='descend',
help='''If specified, sort records in descending, rather
than ascending, order by values in the target field.'''
)
parser_sort.set_defaults(func=sortDbFile)
# Subparser to update records
parser_update = subparsers.add_parser(
'update',
parents=[default_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Updates field and value pairs.',
description='Updates field and value pairs.')
group_update = parser_update.add_argument_group('parsing arguments')
group_update.add_argument('-f',
action='store',
dest='field',
required=True,
help='The name of the field to update.')
group_update.add_argument('-u',
nargs='+',
action='store',
dest='values',
required=True,
help='The values that will be replaced.')
group_update.add_argument(
'-t',
nargs='+',
action='store',
dest='updates',
required=True,
help='''The new value to assign to each selected row.''')
parser_update.set_defaults(func=updateDbFile)
# Subparser to merge files
parser_merge = subparsers.add_parser('merge',
parents=[multi_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Merges files.',
description='Merges files.')
group_merge = parser_merge.add_argument_group('parsing arguments')
group_merge.add_argument(
'-o',
action='store',
dest='out_file',
default=None,
help=
'''Explicit output file name. Note, this argument cannot be used with
the --failed, --outdir or --outname arguments.'''
)
group_merge.add_argument(
'--drop',
action='store_true',
dest='drop',
help='''If specified, drop fields that do not exist in all input files.
Otherwise, include all columns in all files and fill missing data
with empty strings.''')
parser_merge.set_defaults(func=mergeDbFiles)
# Subparser to partition files by annotation values
parser_split = subparsers.add_parser(
'split',
parents=[multi_parent],
formatter_class=CommonHelpFormatter,
add_help=False,
help='Splits database files by field values.',
description='Splits database files by field values')
group_split = parser_split.add_argument_group('parsing arguments')
group_split.add_argument(
'-f',
action='store',
dest='field',
type=str,
required=True,
help='Annotation field by which to split database files.')
group_split.add_argument(
'--num',
action='store',
dest='num_split',
type=float,
default=None,
help='''Specify to define the field as numeric and group
records by whether they are less than or at least
(greater than or equal to) the specified value.'''
)
parser_split.set_defaults(func=splitDbFile)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent(
'''
output files:
airr
AIRR formatted database files.
changeo
Change-O formatted database files.
sequences
FASTA formatted sequences output from the subcommands fasta and clip.
genbank
feature tables and fasta files containing MiAIRR compliant input for tbl2asn.
required fields:
sequence_id, sequence, sequence_alignment, junction, v_call, d_call, j_call,
v_germline_start, v_germline_end, v_sequence_start, v_sequence_end,
d_sequence_start, d_sequence_end, j_sequence_start, j_sequence_end
optional fields:
germline_alignment, c_call, clone_id
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__, epilog=fields,
formatter_class=CommonHelpFormatter, add_help=False)
group_help = parser.add_argument_group('help')
group_help.add_argument('--version', action='version',
version='%(prog)s:' + ' %s %s' %(__version__, __date__))
group_help.add_argument('-h', '--help', action='help', help='show this help message and exit')
subparsers = parser.add_subparsers(title='subcommands', dest='command', metavar='',
help='Database operation')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Define parent parsers
default_parent = getCommonArgParser(failed=False, log=False, format=False)
format_parent = getCommonArgParser(failed=False, log=False)
# Subparser to convert changeo to AIRR files
parser_airr = subparsers.add_parser('airr', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Converts input to an AIRR TSV file.',
description='Converts input to an AIRR TSV file.')
parser_airr.set_defaults(func=convertToAIRR)
# Subparser to convert AIRR to changeo files
parser_changeo = subparsers.add_parser('changeo', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Converts input into a Change-O TSV file.',
description='Converts input into a Change-O TSV file.')
parser_changeo.set_defaults(func=convertToChangeo)
# Subparser to insert IMGT-gaps
# desc_gap = dedent('''
# Inserts IMGT numbering spacers into the observed sequence
# (SEQUENCE_IMGT, sequence_alignment) and rebuilds the germline sequence
# (GERMLINE_IMGT, germline_alignment) if present. Also adjusts the values
# in the V germline coordinate fields (V_GERM_START_IMGT, V_GERM_LENGTH_IMGT;
# v_germline_end, v_germline_start), which are required.
# ''')
# parser_gap = subparsers.add_parser('gap', parents=[format_parent],
# formatter_class=CommonHelpFormatter, add_help=False,
# help='Inserts IMGT numbering spacers into the V region.',
# description=desc_gap)
# group_gap = parser_gap.add_argument_group('conversion arguments')
# group_gap.add_argument('-r', nargs='+', action='store', dest='references', required=False,
# help='''List of folders and/or fasta files containing
# IMGT-gapped germline sequences corresponding to the
# set of germlines used for the alignment.''')
# parser_gap.set_defaults(func=insertGaps)
# Subparser to convert database entries to sequence file
parser_fasta = subparsers.add_parser('fasta', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Creates a fasta file from database records.',
description='Creates a fasta file from database records.')
group_fasta = parser_fasta.add_argument_group('conversion arguments')
group_fasta.add_argument('--if', action='store', dest='id_field',
default=default_id_field,
help='The name of the field containing identifiers')
group_fasta.add_argument('--sf', action='store', dest='seq_field',
default=default_seq_field,
help='The name of the field containing sequences')
group_fasta.add_argument('--mf', nargs='+', action='store', dest='meta_fields',
help='List of annotation fields to add to the sequence description')
parser_fasta.set_defaults(func=convertToFasta)
# Subparser to convert database entries to clip-fasta file
parser_baseln = subparsers.add_parser('baseline', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
description='Creates a BASELINe fasta file from database records.',
help='''Creates a specially formatted fasta file
from database records for input into the BASELINe
website. The format groups clonally related sequences
sequentially, with the germline sequence preceding
each clone and denoted by headers starting with ">>".''')
group_baseln = parser_baseln.add_argument_group('conversion arguments')
group_baseln.add_argument('--if', action='store', dest='id_field',
default=default_id_field,
help='The name of the field containing identifiers')
group_baseln.add_argument('--sf', action='store', dest='seq_field',
default=default_seq_field,
help='The name of the field containing reads')
group_baseln.add_argument('--gf', action='store', dest='germ_field',
default=default_germ_field,
help='The name of the field containing germline sequences')
group_baseln.add_argument('--cf', action='store', dest='cluster_field', default=None,
help='The name of the field containing containing sorted clone IDs')
group_baseln.add_argument('--mf', nargs='+', action='store', dest='meta_fields',
help='List of annotation fields to add to the sequence description')
parser_baseln.set_defaults(func=convertToBaseline)
# Subparser to convert database entries to a GenBank fasta and feature table file
parser_gb = subparsers.add_parser('genbank', parents=[format_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Creates files for GenBank/TLS submissions.',
description='Creates files for GenBank/TLS submissions.')
# Genbank source information arguments
group_gb_src = parser_gb.add_argument_group('source information arguments')
group_gb_src.add_argument('--mol', action='store', dest='molecule', default=default_molecule,
help='''The source molecule type. Usually one of "mRNA" or "genomic DNA".''')
group_gb_src.add_argument('--product', action='store', dest='product', default=default_product,
help='''The product name, such as "immunoglobulin heavy chain".''')
group_gb_src.add_argument('--db', action='store', dest='db_xref', default=None,
help='''Name of the reference database used for alignment.
Usually "IMGT/GENE-DB".''')
group_gb_src.add_argument('--inf', action='store', dest='inference', default=None,
help='''Name and version of the inference tool used for reference alignment in the
form tool:version.''')
# Genbank sample information arguments
group_gb_sam = parser_gb.add_argument_group('sample information arguments')
group_gb_sam.add_argument('--organism', action='store', dest='organism', default=None,
help='The scientific name of the organism.')
group_gb_sam.add_argument('--sex', action='store', dest='sex', default=None,
help='''If specified, adds the given sex annotation
to the fasta headers.''')
group_gb_sam.add_argument('--isolate', action='store', dest='isolate', default=None,
help='''If specified, adds the given isolate annotation
(sample label) to the fasta headers.''')
group_gb_sam.add_argument('--tissue', action='store', dest='tissue', default=None,
help='''If specified, adds the given tissue-type annotation
to the fasta headers.''')
group_gb_sam.add_argument('--cell-type', action='store', dest='cell_type', default=None,
help='''If specified, adds the given cell-type annotation
to the fasta headers.''')
group_gb_sam.add_argument('-y', action='store', dest='yaml_config', default=None,
help='''A yaml file specifying sample features (BioSample attributes)
in the form \'variable: value\'. If specified, any features provided in the
yaml file will override those provided at the commandline. Note,
this config file applies to sample features only and
cannot be used for required source features such as
the --product or --mol argument.''')
# General genbank conversion arguments
group_gb_cvt = parser_gb.add_argument_group('conversion arguments')
group_gb_cvt.add_argument('--label', action='store', dest='label', default=None,
help='''If specified, add a field name to the sequence identifier.
Sequence identifiers will be output in the form <label>=<id>.''')
group_gb_cvt.add_argument('--cf', action='store', dest='c_field', default=None,
help='''Field containing the C region call. If unspecified, the C region gene
call will be excluded from the feature table.''')
group_gb_cvt.add_argument('--nf', action='store', dest='count_field', default=None,
help='''If specified, use the provided column to add the AIRR_READ_COUNT
note to the feature table.''')
group_gb_cvt.add_argument('--if', action='store', dest='index_field', default=None,
help='''If specified, use the provided column to add the AIRR_CELL_INDEX
note to the feature table.''')
group_gb_cvt.add_argument('--allow-stop', action='store_true', dest='allow_stop',
help='''If specified, retain records in the output with stop codons in the junction region.
In such records the CDS will be removed and replaced with a similar misc_feature in
the feature table.''')
group_gb_cvt.add_argument('--asis-id', action='store_true', dest='asis_id',
help='''If specified, use the existing sequence identifier for the output identifier.
By default, only the row number will be used as the identifier to avoid
the 50 character limit.''')
group_gb_cvt.add_argument('--asis-calls', action='store_true', dest='asis_calls',
help='''Specify to prevent alleles from being parsed using the IMGT nomenclature.
Note, this requires the gene assignments to be exact matches to valid
records in the references database specified by the --db argument.''')
group_gb_cvt.add_argument('--allele-delim', action='store', dest='allele_delim', default=default_allele_delim,
help='''The delimiter to use for splitting the gene name from the allele number.
Note, this only applies when specifying --asis-calls. By default,
this argument will be ignored and allele numbers extracted under the
expectation of IMGT nomenclature consistency.''')
group_gb_cvt.add_argument('--asn', action='store_true', dest='build_asn',
help='''If specified, run tbl2asn to generate the .sqn submission file after making
the .fsa and .tbl files.''')
group_gb_cvt.add_argument('--sbt', action='store', dest='asn_template', default=None,
help='''If provided along with --asn, use the specified file for the template file
argument to tbl2asn.''')
group_gb_cvt.add_argument('--exec', action='store', dest='tbl2asn_exec', default=default_tbl2asn_exec,
help='The name or location of the tbl2asn executable.')
parser_gb.set_defaults(func=convertToGenbank)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent('''
output files:
sequences
FASTA formatted sequences output from the subcommands fasta and clip.
<field>-<value>
database files partitioned by annotation <field> and <value>.
parse-<command>
output of the database modification functions where <command> is one of
the subcommands add, index, drop, delete, rename, select, sort or update.
required fields:
SEQUENCE_ID
optional fields:
JUNCTION, SEQUENCE_IMGT, SEQUENCE_VDJ, GERMLINE_IMGT, GERMLINE_VDJ,
GERMLINE_IMGT_D_MASK, GERMLINE_VDJ_D_MASK,
GERMLINE_IMGT_V_REGION, GERMLINE_VDJ_V_REGION
output fields:
None
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__,
epilog=fields,
formatter_class=CommonHelpFormatter)
parser.add_argument('--version',
action='version',
version='%(prog)s:' + ' %s-%s' %
(__version__, __date__))
subparsers = parser.add_subparsers(title='subcommands',
dest='command',
metavar='',
help='Database operation')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Define parent parser
parser_parent = getCommonArgParser(seq_in=False,
seq_out=False,
db_in=True,
failed=False,
log=False)
# Subparser to convert database entries to sequence file
parser_seq = subparsers.add_parser(
'fasta',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Creates a fasta file from database records.',
description='Creates a fasta file from database records.')
parser_seq.add_argument(
'--if',
action='store',
dest='id_field',
default=default_id_field,
help='The name of the field containing identifiers')
parser_seq.add_argument('--sf',
action='store',
dest='seq_field',
default=default_seq_field,
help='The name of the field containing sequences')
parser_seq.add_argument(
'--mf',
nargs='+',
action='store',
dest='meta_fields',
help='List of annotation fields to add to the sequence description')
parser_seq.set_defaults(func=convertDbFasta)
# Subparser to convert database entries to clip-fasta file
parser_baseln = subparsers.add_parser(
'baseline',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
description='Creates a BASELINe fasta file from database records.',
help='''Creates a specially formatted fasta file
from database records for input into the BASELINe
website. The format groups clonally related sequences
sequentially, with the germline sequence preceding
each clone and denoted by headers starting with ">>".'''
)
parser_baseln.add_argument(
'--if',
action='store',
dest='id_field',
default=default_id_field,
help='The name of the field containing identifiers')
parser_baseln.add_argument('--sf',
action='store',
dest='seq_field',
default=default_seq_field,
help='The name of the field containing reads')
parser_baseln.add_argument(
'--gf',
action='store',
dest='germ_field',
default=default_germ_field,
help='The name of the field containing germline sequences')
parser_baseln.add_argument(
'--cf',
action='store',
dest='cluster_field',
default=None,
help='The name of the field containing containing sorted clone IDs')
parser_baseln.add_argument(
'--mf',
nargs='+',
action='store',
dest='meta_fields',
help='List of annotation fields to add to the sequence description')
parser_baseln.set_defaults(func=convertDbBaseline)
# Subparser to partition files by annotation values
parser_split = subparsers.add_parser(
'split',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Splits database files by field values.',
description='Splits database files by field values')
parser_split.add_argument(
'-f',
action='store',
dest='field',
type=str,
required=True,
help='Annotation field by which to split database files.')
parser_split.add_argument(
'--num',
action='store',
dest='num_split',
type=float,
default=None,
help='''Specify to define the field as numeric and group
records by whether they are less than or at least
(greater than or equal to) the specified value.'''
)
parser_split.set_defaults(func=splitDbFile)
# Subparser to add records
parser_add = subparsers.add_parser(
'add',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Adds field and value pairs.',
description='Adds field and value pairs.')
parser_add.add_argument('-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to add.')
parser_add.add_argument(
'-u',
nargs='+',
action='store',
dest='values',
required=True,
help='The value to assign to all rows for each field.')
parser_add.set_defaults(func=addDbFile)
# Subparser to delete records
parser_delete = subparsers.add_parser(
'delete',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Deletes specific records.',
description='Deletes specific records.')
parser_delete.add_argument(
'-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to check for deletion criteria.')
parser_delete.add_argument(
'-u',
nargs='+',
action='store',
dest='values',
default=['', 'NA'],
help='''The values defining which records to delete. A value
may appear in any of the fields specified with -f.'''
)
parser_delete.add_argument(
'--logic',
action='store',
dest='logic',
choices=('any', 'all'),
default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).'''
)
parser_delete.add_argument(
'--regex',
action='store_true',
dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_delete.set_defaults(func=deleteDbFile)
# Subparser to drop fields
parser_drop = subparsers.add_parser('drop',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Deletes entire fields.',
description='Deletes entire fields.')
parser_drop.add_argument(
'-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to delete from the database.')
parser_drop.set_defaults(func=dropDbFile)
# Subparser to index fields
parser_index = subparsers.add_parser(
'index',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Adds a numeric index field.',
description='Adds a numeric index field.')
parser_index.add_argument(
'-f',
action='store',
dest='field',
default=default_index_field,
help='The name of the index field to add to the database.')
parser_index.set_defaults(func=indexDbFile)
# Subparser to rename fields
parser_rename = subparsers.add_parser('rename',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Renames fields.',
description='Renames fields.')
parser_rename.add_argument('-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='List of fields to rename.')
parser_rename.add_argument('-k',
nargs='+',
action='store',
dest='names',
required=True,
help='List of new names for each field.')
parser_rename.set_defaults(func=renameDbFile)
# Subparser to select records
parser_select = subparsers.add_parser(
'select',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Selects specific records.',
description='Selects specific records.')
parser_select.add_argument(
'-f',
nargs='+',
action='store',
dest='fields',
required=True,
help='The name of the fields to check for selection criteria.')
parser_select.add_argument(
'-u',
nargs='+',
action='store',
dest='values',
required=True,
help='''The values defining with records to select. A value
may appear in any of the fields specified with -f.'''
)
parser_select.add_argument(
'--logic',
action='store',
dest='logic',
choices=('any', 'all'),
default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).'''
)
parser_select.add_argument(
'--regex',
action='store_true',
dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_select.set_defaults(func=selectDbFile)
# Subparser to sort file by records
parser_sort = subparsers.add_parser(
'sort',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Sorts records by field values.',
description='Sorts records by field values.')
parser_sort.add_argument(
'-f',
action='store',
dest='field',
type=str,
required=True,
help='The annotation field by which to sort records.')
parser_sort.add_argument(
'--num',
action='store_true',
dest='numeric',
default=False,
help='''Specify to define the sort column as numeric rather
than textual.''')
parser_sort.add_argument(
'--descend',
action='store_true',
dest='descend',
help='''If specified, sort records in descending, rather
than ascending, order by values in the target field.'''
)
parser_sort.set_defaults(func=sortDbFile)
# Subparser to update records
parser_update = subparsers.add_parser(
'update',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Updates field and value pairs.',
description='Updates field and value pairs.')
parser_update.add_argument('-f',
action='store',
dest='field',
required=True,
help='The name of the field to update.')
parser_update.add_argument('-u',
nargs='+',
action='store',
dest='values',
required=True,
help='The values that will be replaced.')
parser_update.add_argument(
'-t',
nargs='+',
action='store',
dest='updates',
required=True,
help='''The new value to assign to each selected row.''')
parser_update.set_defaults(func=updateDbFile)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
fields = dedent(
'''
output files:
db-pass
database of parsed alignment records.
db-fail
database with records failing alignment.
output fields:
SEQUENCE_ID, SEQUENCE_INPUT, FUNCTIONAL, IN_FRAME, STOP, MUTATED_INVARIANT,
INDELS, V_CALL, D_CALL, J_CALL, SEQUENCE_VDJ and/or SEQUENCE_IMGT,
V_SEQ_START, V_SEQ_LENGTH, V_GERM_START_VDJ and/or V_GERM_START_IMGT,
V_GERM_LENGTH_VDJ and/or V_GERM_LENGTH_IMGT, N1_LENGTH,
D_SEQ_START, D_SEQ_LENGTH, D_GERM_START, D_GERM_LENGTH, N2_LENGTH,
J_SEQ_START, J_SEQ_LENGTH, J_GERM_START, J_GERM_LENGTH,
JUNCTION_LENGTH, JUNCTION, V_SCORE, V_IDENTITY, V_EVALUE, V_BTOP,
J_SCORE, J_IDENTITY, J_EVALUE, J_BTOP, FWR1_IMGT, FWR2_IMGT, FWR3_IMGT,
FWR4_IMGT, CDR1_IMGT, CDR2_IMGT, CDR3_IMGT
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__, epilog=fields,
formatter_class=CommonHelpFormatter)
parser.add_argument('--version', action='version',
version='%(prog)s:' + ' %s-%s' %(__version__, __date__))
subparsers = parser.add_subparsers(title='subcommands', dest='command',
help='Aligner used', metavar='')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Parent parser
parser_parent = getCommonArgParser(seq_in=False, seq_out=False, log=False)
# IgBlast Aligner
parser_igblast = subparsers.add_parser('igblast', help='Process IgBlast output',
parents=[parser_parent],
formatter_class=CommonHelpFormatter)
parser_igblast.set_defaults(func=parseIgBlast)
parser_igblast.add_argument('-i', nargs='+', action='store', dest='aligner_files',
required=True,
help='''IgBLAST output files in format 7 with query sequence
(IgBLAST argument \'-outfmt "7 std qseq sseq btop"\').''')
parser_igblast.add_argument('-r', nargs='+', action='store', dest='repo', required=True,
help='''List of folders and/or fasta files containing
IMGT-gapped germline sequences corresponding to the
set of germlines used in the IgBLAST alignment.''')
parser_igblast.add_argument('-s', action='store', nargs='+', dest='seq_files',
required=True,
help='List of input FASTA files containing sequences')
parser_igblast.add_argument('--noparse', action='store_true', dest='no_parse',
help='''Specify if input IDs should not be parsed to add
new columns to database.''')
parser_igblast.add_argument('--scores', action='store_true', dest='score_fields',
help='''Specify if alignment score metrics should be
included in the output. Adds the V_SCORE, V_IDENTITY,
V_EVALUE, V_BTOP, J_SCORE, J_IDENTITY,
J_BTOP, and J_EVALUE columns.''')
parser_igblast.add_argument('--regions', action='store_true', dest='region_fields',
help='''Specify if IMGT framework and CDR regions should be
included in the output. Adds the FWR1_IMGT, FWR2_IMGT,
FWR3_IMGT, FWR4_IMGT, CDR1_IMGT, CDR2_IMGT, and
CDR3_IMGT columns.''')
# IMGT aligner
parser_imgt = subparsers.add_parser('imgt', help='Process IMGT/HighV-Quest output',
parents=[parser_parent],
formatter_class=CommonHelpFormatter)
imgt_arg_group = parser_imgt.add_mutually_exclusive_group(required=True)
imgt_arg_group.add_argument('-i', nargs='+', action='store', dest='aligner_files',
help='''Either zipped IMGT output files (.zip) or a folder
containing unzipped IMGT output files (which must
include 1_Summary, 2_IMGT-gapped, 3_Nt-sequences,
and 6_Junction).''')
parser_imgt.add_argument('-s', nargs='*', action='store', dest='seq_files',
required=False,
help='List of input FASTA files containing sequences')
parser_imgt.add_argument('--noparse', action='store_true', dest='no_parse',
help='''Specify if input IDs should not be parsed to add new
columns to database.''')
parser_imgt.add_argument('--scores', action='store_true', dest='score_fields',
help='''Specify if alignment score metrics should be
included in the output. Adds the V_SCORE, V_IDENTITY,
J_SCORE and J_IDENTITY. Note, this will also add
the columns V_EVALUE, V_BTOP, J_EVALUE and J_BTOP,
but they will be empty for IMGT output.''')
parser_imgt.add_argument('--regions', action='store_true', dest='region_fields',
help='''Specify if IMGT framework and CDR regions should be
included in the output. Adds the FWR1_IMGT, FWR2_IMGT,
FWR3_IMGT, FWR4_IMGT, CDR1_IMGT, CDR2_IMGT, and
CDR3_IMGT columns.''')
parser_imgt.set_defaults(func=parseIMGT)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent('''
output files:
germ-pass
database with assigned germline sequences.
germ-fail
database with records failing germline assignment.
required fields:
SEQUENCE_ID, SEQUENCE_VDJ or SEQUENCE_IMGT,
V_CALL or V_CALL_GENOTYPED, D_CALL, J_CALL,
V_SEQ_START, V_SEQ_LENGTH, V_GERM_START_IMGT, V_GERM_LENGTH_IMGT,
D_SEQ_START, D_SEQ_LENGTH, D_GERM_START, D_GERM_LENGTH,
J_SEQ_START, J_SEQ_LENGTH, J_GERM_START, J_GERM_LENGTH,
NP1_LENGTH, NP2_LENGTH
optional fields:
N1_LENGTH, N2_LENGTH, P3V_LENGTH, P5D_LENGTH, P3D_LENGTH, P5J_LENGTH,
CLONE
output fields:
GERMLINE_VDJ, GERMLINE_VDJ_D_MASK, GERMLINE_VDJ_V_REGION,
GERMLINE_IMGT, GERMLINE_IMGT_D_MASK, GERMLINE_IMGT_V_REGION,
GERMLINE_V_CALL, GERMLINE_D_CALL, GERMLINE_J_CALL,
GERMLINE_REGIONS
''')
# Parent parser
parser_parent = getCommonArgParser(seq_in=False,
seq_out=False,
db_in=True,
annotation=False)
# Define argument parser
parser = ArgumentParser(description=__doc__,
epilog=fields,
parents=[parser_parent],
formatter_class=CommonHelpFormatter)
parser.add_argument('--version',
action='version',
version='%(prog)s:' + ' %s-%s' %
(__version__, __date__))
parser.add_argument(
'-r',
nargs='+',
action='store',
dest='repo',
required=True,
help='''List of folders and/or fasta files (with .fasta, .fna or .fa
extension) with germline sequences.''')
parser.add_argument(
'-g',
action='store',
dest='germ_types',
default=default_germ_types,
nargs='+',
choices=('full', 'dmask', 'vonly', 'regions'),
help='''Specify type(s) of germlines to include full germline,
germline with D-region masked, or germline for V region only.'''
)
parser.add_argument(
'--cloned',
action='store_true',
dest='cloned',
help=
'''Specify to create only one germline per clone. Assumes input file is
sorted by clone column, and will not yield correct results if the data
is unsorted. Note, if allele calls are ambiguous within a clonal group,
this will place the germline call used for the entire clone within the
GERMLINE_V_CALL, GERMLINE_D_CALL and GERMLINE_J_CALL fields.'''
)
parser.add_argument('--vf',
action='store',
dest='v_field',
default=default_v_field,
help='Specify field to use for germline V call')
parser.add_argument('--sf',
action='store',
dest='seq_field',
default=default_seq_field,
help='Specify field to use for sequence')
return parser
def getArgParser():
"""
Defines the ArgumentParser.
Returns:
argparse.ArgumentParser
"""
fields = dedent(
'''
output files:
db-pass
database of alignment records with functionality information,
V and J calls, and a junction region.
db-fail
database with records that fail due to no functionality information
(did not pass IMGT), no V call, no J call, or no junction region.
universal output fields:
SEQUENCE_ID, SEQUENCE_INPUT, SEQUENCE_VDJ, SEQUENCE_IMGT,
FUNCTIONAL, IN_FRAME, STOP, MUTATED_INVARIANT, INDELS,
V_CALL, D_CALL, J_CALL,
V_SEQ_START, V_SEQ_LENGTH,
D_SEQ_START, D_SEQ_LENGTH, D_GERM_START, D_GERM_LENGTH,
J_SEQ_START, J_SEQ_LENGTH, J_GERM_START, J_GERM_LENGTH,
JUNCTION_LENGTH, JUNCTION, NP1_LENGTH, NP2_LENGTH,
FWR1_IMGT, FWR2_IMGT, FWR3_IMGT, FWR4_IMGT,
CDR1_IMGT, CDR2_IMGT, CDR3_IMGT
imgt specific output fields:
V_GERM_START_IMGT, V_GERM_LENGTH_IMGT,
N1_LENGTH, N2_LENGTH, P3V_LENGTH, P5D_LENGTH, P3D_LENGTH, P5J_LENGTH,
D_FRAME, V_SCORE, V_IDENTITY, J_SCORE, J_IDENTITY,
igblast specific output fields:
V_GERM_START_VDJ, V_GERM_LENGTH_VDJ,
V_EVALUE, V_SCORE, V_IDENTITY, V_BTOP,
J_EVALUE, J_SCORE, J_IDENTITY, J_BTOP.
CDR3_IGBLAST_NT, CDR3_IGBLAST_AA
ihmm specific output fields:
V_GERM_START_VDJ, V_GERM_LENGTH_VDJ,
HMM_SCORE
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__, epilog=fields,
formatter_class=CommonHelpFormatter)
parser.add_argument('--version', action='version',
version='%(prog)s:' + ' %s-%s' %(__version__, __date__))
subparsers = parser.add_subparsers(title='subcommands', dest='command',
help='Aligner used', metavar='')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Parent parser
parser_parent = getCommonArgParser(seq_in=False, seq_out=False, log=False)
# IgBlast Aligner
parser_igblast = subparsers.add_parser('igblast', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Process IgBLAST output.',
description='Process IgBLAST output.')
parser_igblast.add_argument('-i', nargs='+', action='store', dest='aligner_outputs',
required=True,
help='''IgBLAST output files in format 7 with query sequence
(IgBLAST argument \'-outfmt "7 std qseq sseq btop"\').''')
parser_igblast.add_argument('-r', nargs='+', action='store', dest='repo', required=True,
help='''List of folders and/or fasta files containing
IMGT-gapped germline sequences corresponding to the
set of germlines used in the IgBLAST alignment.''')
parser_igblast.add_argument('-s', action='store', nargs='+', dest='seq_files',
required=True,
help='''List of input FASTA files (with .fasta, .fna or .fa
extension), containing sequences.''')
parser_igblast.add_argument('--noparse', action='store_true', dest='no_parse',
help='''Specify to prevent input sequence headers from being parsed
to add new columns to database. Parsing of sequence headers requires
headers to be in the pRESTO annotation format, so this should be specified
when sequence headers are incompatible with the pRESTO annotation scheme.
Note, unrecognized header formats will default to this behavior.''')
parser_igblast.add_argument('--partial', action='store_true', dest='partial',
help='''If specified, include incomplete V(D)J alignments in
the pass file instead of the fail file.''')
parser_igblast.add_argument('--scores', action='store_true', dest='parse_scores',
help='''Specify if alignment score metrics should be
included in the output. Adds the V_SCORE, V_IDENTITY,
V_EVALUE, V_BTOP, J_SCORE, J_IDENTITY,
J_BTOP, and J_EVALUE columns.''')
parser_igblast.add_argument('--regions', action='store_true', dest='parse_regions',
help='''Specify if IMGT FWR and CDRs should be
included in the output. Adds the FWR1_IMGT, FWR2_IMGT,
FWR3_IMGT, FWR4_IMGT, CDR1_IMGT, CDR2_IMGT, and
CDR3_IMGT columns.''')
parser_igblast.add_argument('--cdr3', action='store_true',
dest='parse_igblast_cdr3',
help='''Specify if the CDR3 sequences generated by IgBLAST
should be included in the output. Adds the columns
CDR3_IGBLAST_NT and CDR3_IGBLAST_AA. Requires IgBLAST
version 1.5 or greater.''')
parser_igblast.set_defaults(func=parseIgBLAST)
# IMGT aligner
parser_imgt = subparsers.add_parser('imgt', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='''Process IMGT/HighV-Quest output
(does not work with V-QUEST).''',
description='''Process IMGT/HighV-Quest output
(does not work with V-QUEST).''')
parser_imgt.add_argument('-i', nargs='+', action='store', dest='aligner_outputs',
help='''Either zipped IMGT output files (.zip or .txz) or a
folder containing unzipped IMGT output files (which must
include 1_Summary, 2_IMGT-gapped, 3_Nt-sequences,
and 6_Junction).''')
parser_imgt.add_argument('-s', nargs='*', action='store', dest='seq_files',
required=False,
help='''List of input FASTA files (with .fasta, .fna or .fa
extension) containing sequences.''')
parser_imgt.add_argument('--noparse', action='store_true', dest='no_parse',
help='''Specify to prevent input sequence headers from being parsed
to add new columns to database. Parsing of sequence headers requires
headers to be in the pRESTO annotation format, so this should be specified
when sequence headers are incompatible with the pRESTO annotation scheme.
Note, unrecognized header formats will default to this behavior.''')
parser_imgt.add_argument('--partial', action='store_true', dest='partial',
help='''If specified, include incomplete V(D)J alignments in
the pass file instead of the fail file.''')
parser_imgt.add_argument('--scores', action='store_true', dest='parse_scores',
help='''Specify if alignment score metrics should be
included in the output. Adds the V_SCORE, V_IDENTITY,
J_SCORE and J_IDENTITY.''')
parser_imgt.add_argument('--regions', action='store_true', dest='parse_regions',
help='''Specify if IMGT FWRs and CDRs should be
included in the output. Adds the FWR1_IMGT, FWR2_IMGT,
FWR3_IMGT, FWR4_IMGT, CDR1_IMGT, CDR2_IMGT, and
CDR3_IMGT columns.''')
parser_imgt.add_argument('--junction', action='store_true', dest='parse_junction',
help='''Specify if detailed junction fields should be
included in the output. Adds the columns
N1_LENGTH, N2_LENGTH, P3V_LENGTH, P5D_LENGTH, P3D_LENGTH,
P5J_LENGTH, D_FRAME.''')
parser_imgt.set_defaults(func=parseIMGT)
# iHMMuneAlign Aligner
parser_ihmm = subparsers.add_parser('ihmm', parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='Process iHMMune-Align output.',
description='Process iHMMune-Align output.')
parser_ihmm.add_argument('-i', nargs='+', action='store', dest='aligner_outputs',
required=True,
help='''iHMMune-Align output file.''')
parser_ihmm.add_argument('-r', nargs='+', action='store', dest='repo', required=True,
help='''List of folders and/or FASTA files containing
IMGT-gapped germline sequences corresponding to the
set of germlines used in the IgBLAST alignment.''')
parser_ihmm.add_argument('-s', action='store', nargs='+', dest='seq_files',
required=True,
help='''List of input FASTA files (with .fasta, .fna or .fa
extension) containing sequences.''')
parser_ihmm.add_argument('--noparse', action='store_true', dest='no_parse',
help='''Specify to prevent input sequence headers from being parsed
to add new columns to database. Parsing of sequence headers requires
headers to be in the pRESTO annotation format, so this should be specified
when sequence headers are incompatible with the pRESTO annotation scheme.
Note, unrecognized header formats will default to this behavior.''')
parser_ihmm.add_argument('--partial', action='store_true', dest='partial',
help='''If specified, include incomplete V(D)J alignments in
the pass file instead of the fail file.''')
parser_ihmm.add_argument('--scores', action='store_true', dest='parse_scores',
help='''Specify if alignment score metrics should be
included in the output. Adds the path score of the
iHMMune-Align hidden Markov model to HMM_SCORE.''')
parser_ihmm.add_argument('--regions', action='store_true', dest='parse_regions',
help='''Specify if IMGT FWRs and CDRs should be
included in the output. Adds the FWR1_IMGT, FWR2_IMGT,
FWR3_IMGT, FWR4_IMGT, CDR1_IMGT, CDR2_IMGT, and
CDR3_IMGT columns.''')
parser_ihmm.set_defaults(func=parseIHMM)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent(
'''
output files:
germ-pass
database with assigned germline sequences.
germ-fail
database with records failing germline assignment.
required fields:
sequence_id, sequence_alignment, v_call, d_call, j_call,
v_sequence_start, v_sequence_end, v_germline_start, v_germline_end,
d_sequence_start, d_sequence_end, d_germline_start, d_germline_end,
j_sequence_start, j_sequence_end, j_germline_start, j_germline_end,
np1_length, np2_length
optional fields:
n1_length, n2_length, p3v_length, p5d_length, p3d_length, p5j_length,
clone_id
output fields:
germline_v_call, germline_d_call, germline_j_call,
germline_alignment, germline_alignment_d_mask,
germline_alignment_v_region, germline_regions,
''')
# Define argument parser
parser = ArgumentParser(description=__doc__, epilog=fields,
parents=[getCommonArgParser(format=True)],
formatter_class=CommonHelpFormatter, add_help=False)
# Germlines arguments
group = parser.add_argument_group('germline construction arguments')
group.add_argument('-r', nargs='+', action='store', dest='references', required=True,
help='''List of folders and/or fasta files (with .fasta, .fna or .fa
extension) with germline sequences. When using the default
Change-O sequence and coordinate fields, these reference sequences
must contain IMGT-numbering spacers (gaps) in the V segment.
Alternative numbering schemes, or no numbering, may work for alternative
sequence and coordinate definitions that define a valid alignment, but
a warning will be issued.''')
group.add_argument('-g', action='store', dest='germ_types', default=default_germ_types,
nargs='+', choices=('full', 'dmask', 'vonly', 'regions'),
help='''Specify type(s) of germlines to include full germline,
germline with D segment masked, or germline for V segment only.''')
group.add_argument('--cloned', action='store_true', dest='cloned',
help='''Specify to create only one germline per clone. Note, if allele
calls are ambiguous within a clonal group, this will place the
germline call used for the entire clone within the
germline_v_call, germline_d_call and germline_j_call fields.''')
group.add_argument('--sf', action='store', dest='seq_field', default=None,
help='''Field containing the aligned sequence.
Defaults to sequence_alignment (airr) or SEQUENCE_IMGT (changeo).''')
group.add_argument('--vf', action='store', dest='v_field', default=None,
help='''Field containing the germline V segment call.
Defaults to v_call (airr) or V_CALL (changeo).''')
group.add_argument('--df', action='store', dest='d_field', default=None,
help='''Field containing the germline D segment call.
Defaults to d_call (airr) or D_CALL (changeo).''')
group.add_argument('--jf', action='store', dest='j_field', default=None,
help='''Field containing the germline J segment call.
Defaults to j_call (airr) or J_CALL (changeo).''')
group.add_argument('--cf', action='store', dest='clone_field', default=None,
help='''Field containing clone identifiers.
Ignored if --cloned is not also specified.
Defaults to clone_id (airr) or CLONE (changeo).''')
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output fields
fields = dedent('''
output files:
clone-pass
database with assigned clonal group numbers.
clone-fail
database with records failing clonal grouping.
required fields:
SEQUENCE_ID, V_CALL or V_CALL_GENOTYPED, D_CALL, J_CALL, JUNCTION
<field>
sequence field specified by the --sf parameter
output fields:
CLONE
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__,
epilog=fields,
formatter_class=CommonHelpFormatter)
parser.add_argument('--version',
action='version',
version='%(prog)s:' + ' %s-%s' %
(__version__, __date__))
subparsers = parser.add_subparsers(title='subcommands',
dest='command',
metavar='',
help='Cloning method')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Parent parser
parser_parent = getCommonArgParser(seq_in=False,
seq_out=False,
db_in=True,
multiproc=True)
# Distance cloning method
parser_bygroup = subparsers.add_parser(
'bygroup',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='''Defines clones as having same V assignment,
J assignment, and junction length with
specified substitution distance model.''',
description='''Defines clones as having same V assignment,
J assignment, and junction length with
specified substitution distance model.'''
)
parser_bygroup.add_argument(
'-f',
nargs='+',
action='store',
dest='fields',
default=None,
help='Additional fields to use for grouping clones (non VDJ)')
parser_bygroup.add_argument(
'--mode',
action='store',
dest='mode',
choices=('allele', 'gene'),
default=default_index_mode,
help='''Specifies whether to use the V(D)J allele or gene for
initial grouping.''')
parser_bygroup.add_argument(
'--act',
action='store',
dest='action',
choices=('first', 'set'),
default=default_index_action,
help='''Specifies how to handle multiple V(D)J assignments
for initial grouping.''')
parser_bygroup.add_argument(
'--model',
action='store',
dest='model',
choices=choices_bygroup_model,
default=default_bygroup_model,
help=
'''Specifies which substitution model to use for calculating distance
between sequences. The "ham" model is nucleotide Hamming distance and
"aa" is amino acid Hamming distance. The "hh_s1f" and "hh_s5f" models are
human specific single nucleotide and 5-mer content models, respectively,
from Yaari et al, 2013. The "mk_rs1nf" and "mk_rs5nf" models are
mouse specific single nucleotide and 5-mer content models, respectively,
from Cui et al, 2016. The "m1n_compat" and "hs1f_compat" models are
deprecated models provided backwards compatibility with the "m1n" and
"hs1f" models in Change-O v0.3.3 and SHazaM v0.1.4. Both
5-mer models should be considered experimental.'''
)
parser_bygroup.add_argument(
'--dist',
action='store',
dest='distance',
type=float,
default=default_distance,
help='The distance threshold for clonal grouping')
parser_bygroup.add_argument(
'--norm',
action='store',
dest='norm',
choices=('len', 'mut', 'none'),
default=default_norm,
help='''Specifies how to normalize distances. One of none
(do not normalize), len (normalize by length),
or mut (normalize by number of mutations between sequences).'''
)
parser_bygroup.add_argument(
'--sym',
action='store',
dest='sym',
choices=('avg', 'min'),
default=default_sym,
help='''Specifies how to combine asymmetric distances. One of avg
(average of A->B and B->A) or min (minimum of A->B and B->A).'''
)
parser_bygroup.add_argument(
'--link',
action='store',
dest='linkage',
choices=('single', 'average', 'complete'),
default=default_linkage,
help='''Type of linkage to use for hierarchical clustering.''')
parser_bygroup.add_argument(
'--maxmiss',
action='store',
dest='max_missing',
type=int,
default=default_max_missing,
help='''The maximum number of non-ACGT characters (gaps or Ns) to
permit in the junction sequence before excluding the record
from clonal assignment. Warning, under single linkage
non-informative positions can create artifactual links
between unrelated sequences. Use with caution.'''
)
parser_bygroup.add_argument(
'--sf',
action='store',
dest='seq_field',
default=default_seq_field,
help='''The name of the field to be used to calculate
distance between records''')
parser_bygroup.set_defaults(feed_func=feedQueue)
parser_bygroup.set_defaults(work_func=processQueue)
parser_bygroup.set_defaults(collect_func=collectQueue)
parser_bygroup.set_defaults(group_func=indexJunctions)
parser_bygroup.set_defaults(clone_func=distanceClones)
# Chen2010
parser_chen = subparsers.add_parser(
'chen2010',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='''Defines clones by method specified in Chen, 2010.''',
description='''Defines clones by method specified in Chen, 2010.''')
parser_chen.set_defaults(feed_func=feedQueueClust)
parser_chen.set_defaults(work_func=processQueueClust)
parser_chen.set_defaults(collect_func=collectQueueClust)
parser_chen.set_defaults(cluster_func=hierClust)
# Ademokun2011
parser_ade = subparsers.add_parser(
'ademokun2011',
parents=[parser_parent],
formatter_class=CommonHelpFormatter,
help='''Defines clones by method specified in Ademokun, 2011.''',
description='''Defines clones by method specified in Ademokun, 2011.'''
)
parser_ade.set_defaults(feed_func=feedQueueClust)
parser_ade.set_defaults(work_func=processQueueClust)
parser_ade.set_defaults(collect_func=collectQueueClust)
parser_ade.set_defaults(cluster_func=hierClust)
return parser
def getArgParser():
"""
Defines the ArgumentParser.
Returns:
argparse.ArgumentParser
"""
fields = dedent(
'''
output files:
db-pass
database of alignment records with functionality information,
V and J calls, and a junction region.
db-fail
database with records that fail due to no productivity information,
no gene V assignment, no J assignment, or no junction region.
universal output fields:
sequence_id, sequence, sequence_alignment, germline_alignment,
rev_comp, productive, stop_codon, vj_in_frame, locus,
v_call, d_call, j_call, junction, junction_length, junction_aa,
v_sequence_start, v_sequence_end, v_germline_start, v_germline_end,
d_sequence_start, d_sequence_end, d_germline_start, d_germline_end,
j_sequence_start, j_sequence_end, j_germline_start, j_germline_end,
np1_length, np2_length, fwr1, fwr2, fwr3, fwr4, cdr1, cdr2, cdr3
imgt specific output fields:
n1_length, n2_length, p3v_length, p5d_length, p3d_length, p5j_length,
d_frame, v_score, v_identity, d_score, d_identity, j_score, j_identity
igblast specific output fields:
v_score, v_identity, v_support, v_cigar,
d_score, d_identity, d_support, d_cigar,
j_score, j_identity, j_support, j_cigar
ihmm specific output fields:
vdj_score
10X specific output fields:
cell_id, c_call, consensus_count, umi_count,
v_call_10x, d_call_10x, j_call_10x,
junction_10x, junction_10x_aa
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__, epilog=fields,
formatter_class=CommonHelpFormatter, add_help=False)
group_help = parser.add_argument_group('help')
group_help.add_argument('--version', action='version',
version='%(prog)s:' + ' %s %s' %(__version__, __date__))
group_help.add_argument('-h', '--help', action='help', help='show this help message and exit')
subparsers = parser.add_subparsers(title='subcommands', dest='command',
help='Aligner used', metavar='')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Parent parser
parser_parent = getCommonArgParser(db_in=False)
# igblastn output parser
parser_igblast = subparsers.add_parser('igblast', parents=[parser_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Process igblastn output.',
description='Process igblastn output.')
group_igblast = parser_igblast.add_argument_group('aligner parsing arguments')
group_igblast.add_argument('-i', nargs='+', action='store', dest='aligner_files',
required=True,
help='''IgBLAST output files in format 7 with query sequence
(igblastn argument \'-outfmt "7 std qseq sseq btop"\').''')
group_igblast.add_argument('-r', nargs='+', action='store', dest='repo', required=True,
help='''List of folders and/or fasta files containing
the same germline set used in the IgBLAST alignment. These
reference sequences must contain IMGT-numbering spacers (gaps)
in the V segment.''')
group_igblast.add_argument('-s', action='store', nargs='+', dest='seq_files',
required=True,
help='''List of input FASTA files (with .fasta, .fna or .fa
extension), containing sequences.''')
group_igblast.add_argument('--10x', action='store', nargs='+', dest='cellranger_file',
help='''Table file containing 10X annotations (with .csv or .tsv
extension).''')
group_igblast.add_argument('--asis-id', action='store_true', dest='asis_id',
help='''Specify to prevent input sequence headers from being parsed
to add new columns to database. Parsing of sequence headers requires
headers to be in the pRESTO annotation format, so this should be specified
when sequence headers are incompatible with the pRESTO annotation scheme.
Note, unrecognized header formats will default to this behavior.''')
group_igblast.add_argument('--asis-calls', action='store_true', dest='asis_calls',
help='''Specify to prevent gene calls from being parsed into standard allele names
in both the IgBLAST output and reference database. Note, this requires
the sequence identifiers in the reference sequence set and the IgBLAST
database to be exact string matches.''')
group_igblast.add_argument('--partial', action='store_true', dest='partial',
help='''If specified, include incomplete V(D)J alignments in
the pass file instead of the fail file. An incomplete alignment
is defined as a record for which a valid IMGT-gapped sequence
cannot be built or that is missing a V gene assignment,
J gene assignment, junction region, or productivity call.''')
group_igblast.add_argument('--extended', action='store_true', dest='extended',
help='''Specify to include additional aligner specific fields in the output.
Adds <vdj>_score, <vdj>_identity, <vdj>_support, <vdj>_cigar,
fwr1, fwr2, fwr3, fwr4, cdr1, cdr2 and cdr3.''')
group_igblast.add_argument('--regions', action='store', dest='regions',
choices=('default', 'rhesus-igl'), default='default',
help='''IMGT CDR and FWR boundary definition to use.''')
parser_igblast.set_defaults(func=parseIgBLAST, amino_acid=False)
# igblastp output parser
parser_igblast_aa = subparsers.add_parser('igblast-aa', parents=[parser_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Process igblastp output.',
description='Process igblastp output.')
group_igblast_aa = parser_igblast_aa.add_argument_group('aligner parsing arguments')
group_igblast_aa.add_argument('-i', nargs='+', action='store', dest='aligner_files',
required=True,
help='''IgBLAST output files in format 7 with query sequence
(igblastp argument \'-outfmt "7 std qseq sseq btop"\').''')
group_igblast_aa.add_argument('-r', nargs='+', action='store', dest='repo', required=True,
help='''List of folders and/or fasta files containing
the same germline set used in the IgBLAST alignment. These
reference sequences must contain IMGT-numbering spacers (gaps)
in the V segment.''')
group_igblast_aa.add_argument('-s', action='store', nargs='+', dest='seq_files', required=True,
help='''List of input FASTA files (with .fasta, .fna or .fa
extension), containing sequences.''')
group_igblast_aa.add_argument('--10x', action='store', nargs='+', dest='cellranger_file',
help='''Table file containing 10X annotations (with .csv or .tsv extension).''')
group_igblast_aa.add_argument('--asis-id', action='store_true', dest='asis_id',
help='''Specify to prevent input sequence headers from being parsed
to add new columns to database. Parsing of sequence headers requires
headers to be in the pRESTO annotation format, so this should be specified
when sequence headers are incompatible with the pRESTO annotation scheme.
Note, unrecognized header formats will default to this behavior.''')
group_igblast_aa.add_argument('--asis-calls', action='store_true', dest='asis_calls',
help='''Specify to prevent gene calls from being parsed into standard allele names
in both the IgBLAST output and reference database. Note, this requires
the sequence identifiers in the reference sequence set and the IgBLAST
database to be exact string matches.''')
group_igblast_aa.add_argument('--extended', action='store_true', dest='extended',
help='''Specify to include additional aligner specific fields in the output.
Adds v_score, v_identity, v_support, v_cigar, fwr1, fwr2, fwr3, cdr1 and cdr2.''')
group_igblast_aa.add_argument('--regions', action='store', dest='regions',
choices=('default', 'rhesus-igl'), default='default',
help='''IMGT CDR and FWR boundary definition to use.''')
parser_igblast_aa.set_defaults(func=parseIgBLAST, partial=True, amino_acid=True)
# IMGT aligner
parser_imgt = subparsers.add_parser('imgt', parents=[parser_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='''Process IMGT/HighV-Quest output
(does not work with V-QUEST).''',
description='''Process IMGT/HighV-Quest output
(does not work with V-QUEST).''')
group_imgt = parser_imgt.add_argument_group('aligner parsing arguments')
group_imgt.add_argument('-i', nargs='+', action='store', dest='aligner_files',
help='''Either zipped IMGT output files (.zip or .txz) or a
folder containing unzipped IMGT output files (which must
include 1_Summary, 2_IMGT-gapped, 3_Nt-sequences,
and 6_Junction).''')
group_imgt.add_argument('-s', nargs='*', action='store', dest='seq_files', required=False,
help='''List of FASTA files (with .fasta, .fna or .fa
extension) that were submitted to IMGT/HighV-QUEST.
If unspecified, sequence identifiers truncated by IMGT/HighV-QUEST
will not be corrected.''')
group_imgt.add_argument('-r', nargs='+', action='store', dest='repo', required=False,
help='''List of folders and/or fasta files containing
the germline sequence set used by IMGT/HighV-QUEST.
These reference sequences must contain IMGT-numbering spacers (gaps)
in the V segment. If unspecified, the germline sequence reconstruction
will not be included in the output.''')
group_imgt.add_argument('--10x', action='store', nargs='+', dest='cellranger_file',
help='''Table file containing 10X annotations (with .csv or .tsv
extension).''')
group_imgt.add_argument('--asis-id', action='store_true', dest='asis_id',
help='''Specify to prevent input sequence headers from being parsed
to add new columns to database. Parsing of sequence headers requires
headers to be in the pRESTO annotation format, so this should be specified
when sequence headers are incompatible with the pRESTO annotation scheme.
Note, unrecognized header formats will default to this behavior.''')
group_imgt.add_argument('--partial', action='store_true', dest='partial',
help='''If specified, include incomplete V(D)J alignments in
the pass file instead of the fail file. An incomplete alignment
is defined as a record that is missing a V gene assignment,
J gene assignment, junction region, or productivity call.''')
group_imgt.add_argument('--extended', action='store_true', dest='extended',
help='''Specify to include additional aligner specific fields in the output.
Adds <vdj>_score, <vdj>_identity>, fwr1, fwr2, fwr3, fwr4,
cdr1, cdr2, cdr3, n1_length, n2_length, p3v_length, p5d_length,
p3d_length, p5j_length and d_frame.''')
parser_imgt.set_defaults(func=parseIMGT)
# iHMMuneAlign Aligner
parser_ihmm = subparsers.add_parser('ihmm', parents=[parser_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Process iHMMune-Align output.',
description='Process iHMMune-Align output.')
group_ihmm = parser_ihmm.add_argument_group('aligner parsing arguments')
group_ihmm.add_argument('-i', nargs='+', action='store', dest='aligner_files',
required=True,
help='''iHMMune-Align output file.''')
group_ihmm.add_argument('-r', nargs='+', action='store', dest='repo', required=True,
help='''List of folders and/or FASTA files containing
the set of germline sequences used by iHMMune-Align. These
reference sequences must contain IMGT-numbering spacers (gaps)
in the V segment.''')
group_ihmm.add_argument('-s', action='store', nargs='+', dest='seq_files',
required=True,
help='''List of input FASTA files (with .fasta, .fna or .fa
extension) containing sequences.''')
group_ihmm.add_argument('--10x', action='store', nargs='+', dest='cellranger_file',
help='''Table file containing 10X annotations (with .csv or .tsv
extension).''')
group_ihmm.add_argument('--asis-id', action='store_true', dest='asis_id',
help='''Specify to prevent input sequence headers from being parsed
to add new columns to database. Parsing of sequence headers requires
headers to be in the pRESTO annotation format, so this should be specified
when sequence headers are incompatible with the pRESTO annotation scheme.
Note, unrecognized header formats will default to this behavior.''')
group_ihmm.add_argument('--partial', action='store_true', dest='partial',
help='''If specified, include incomplete V(D)J alignments in
the pass file instead of the fail file. An incomplete alignment
is defined as a record for which a valid IMGT-gapped sequence
cannot be built or that is missing a V gene assignment,
J gene assignment, junction region, or productivity call.''')
group_ihmm.add_argument('--extended', action='store_true', dest='extended',
help='''Specify to include additional aligner specific fields in the output.
Adds the path score of the iHMMune-Align hidden Markov model as vdj_score;
adds fwr1, fwr2, fwr3, fwr4, cdr1, cdr2 and cdr3.''')
parser_ihmm.set_defaults(func=parseIHMM)
return parser
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output fields
fields = dedent('''
output files:
clone-pass
database with assigned clonal group numbers.
clone-fail
database with records failing clonal grouping.
required fields:
sequence_id, v_call, j_call, junction
output fields:
clone_id
''')
# Define argument parser
parser = ArgumentParser(
description=__doc__,
epilog=fields,
parents=[getCommonArgParser(format=True, multiproc=True)],
formatter_class=CommonHelpFormatter,
add_help=False)
# Distance cloning method
group = parser.add_argument_group('cloning arguments')
group.add_argument(
'--sf',
action='store',
dest='seq_field',
default=None,
help='''Field to be used to calculate distance between records.
Defaults to junction (airr) or JUNCTION (changeo).'''
)
group.add_argument('--vf',
action='store',
dest='v_field',
default=None,
help='''Field containing the germline V segment call.
Defaults to v_call (airr) or V_CALL (changeo).''')
group.add_argument('--jf',
action='store',
dest='j_field',
default=None,
help='''Field containing the germline J segment call.
Defaults to j_call (airr) or J_CALL (changeo).''')
group.add_argument(
'--gf',
nargs='+',
action='store',
dest='group_fields',
default=None,
help=
'Additional fields to use for grouping clones aside from V, J and junction length.'
)
group.add_argument(
'--mode',
action='store',
dest='mode',
choices=('allele', 'gene'),
default=default_index_mode,
help='''Specifies whether to use the V(D)J allele or gene for
initial grouping.''')
group.add_argument(
'--act',
action='store',
dest='action',
choices=('first', 'set'),
default=default_index_action,
help=
'''Specifies how to handle multiple V(D)J assignments for initial grouping.
The "first" action will use only the first gene listed.
The "set" action will use all gene assignments and construct a larger gene
grouping composed of any sequences sharing an assignment or linked to another
sequence by a common assignment (similar to single-linkage).'''
)
group.add_argument(
'--model',
action='store',
dest='model',
choices=choices_distance_model,
default=default_distance_model,
help=
'''Specifies which substitution model to use for calculating distance
between sequences. The "ham" model is nucleotide Hamming distance and
"aa" is amino acid Hamming distance. The "hh_s1f" and "hh_s5f" models are
human specific single nucleotide and 5-mer content models, respectively,
from Yaari et al, 2013. The "mk_rs1nf" and "mk_rs5nf" models are
mouse specific single nucleotide and 5-mer content models, respectively,
from Cui et al, 2016. The "m1n_compat" and "hs1f_compat" models are
deprecated models provided backwards compatibility with the "m1n" and
"hs1f" models in Change-O v0.3.3 and SHazaM v0.1.4. Both
5-mer models should be considered experimental.'''
)
group.add_argument('--dist',
action='store',
dest='distance',
type=float,
default=default_distance,
help='The distance threshold for clonal grouping')
group.add_argument(
'--norm',
action='store',
dest='norm',
choices=('len', 'mut', 'none'),
default=default_norm,
help='''Specifies how to normalize distances. One of none
(do not normalize), len (normalize by length),
or mut (normalize by number of mutations between sequences).'''
)
group.add_argument(
'--sym',
action='store',
dest='sym',
choices=('avg', 'min'),
default=default_sym,
help='''Specifies how to combine asymmetric distances. One of avg
(average of A->B and B->A) or min (minimum of A->B and B->A).'''
)
group.add_argument(
'--link',
action='store',
dest='linkage',
choices=('single', 'average', 'complete'),
default=default_linkage,
help='''Type of linkage to use for hierarchical clustering.''')
group.add_argument(
'--maxmiss',
action='store',
dest='max_missing',
type=int,
default=default_max_missing,
help='''The maximum number of non-ACGT characters (gaps or Ns) to
permit in the junction sequence before excluding the record
from clonal assignment. Note, under single linkage
non-informative positions can create artifactual links
between unrelated sequences. Use with caution.''')
parser.set_defaults(group_func=groupByGene)
parser.set_defaults(clone_func=distanceClones)
return parser