def run(start=1, end='', gap_open=11, gap_extend=1, local_=False, global_=False, semiglobal=False,
protein=False, translate=False, inter=False, table=False, mutations=False, strict=False,
pep1=False, pep3=False, limit=1, verbose=False, target=None, query=None):
"""
Performs an alignment between the query and target.
"""
# Alignments over this size will take a long time!
MAX_LEN = 100000
# Set the verbosity of the process.
utils.set_verbosity(logger, level=int(verbose))
# Reset counter (needed for consistency during testing).
jsonrec.reset_sequence_names()
# This method requires two inputs.
if not (query and target):
utils.error(f"Please specify a TARGET and a QUERY")
if global_:
mode = const.GLOBAL_ALIGN
elif local_:
mode = const.LOCAL_ALIGN
elif semiglobal:
mode = const.SEMIGLOBAL_ALIGN
else:
mode = const.GLOBAL_ALIGN
# A parameter for each record.
common = dict(
protein=protein, translate=translate, mutations=mutations, pep1=pep1, pep3=pep3,
table=table, strict=strict, start=start, end=end, gap_open=gap_open, gap_extend=gap_extend,
mode=mode
)
# Create parameters to represent each data.
param_t = objects.Param(acc=target, **common)
param_q = objects.Param(acc=query, **common)
# Fill JSON data for parameters.
param_t.json = fetch.get_json(param_t.acc, inter=inter, strict=True)[:limit]
param_q.json = fetch.get_json(param_q.acc, inter=inter, strict=True)[:limit]
# Each data object may contain several records.
#
# For more than one record we iterate in pairs
#
for rec1, rec2 in zip(param_q.json, param_t.json):
qrecs = fastarec.get_fasta(rec1, param=param_q)
trecs = fastarec.get_fasta(rec2, param=param_t)
for qseq, tseq in zip(qrecs, trecs):
if (len(qseq) > MAX_LEN):
utils.error(f"query is longer than maximum: {len(qseq):,} > {MAX_LEN:,}")
if (len(tseq) > MAX_LEN):
utils.error(f"target sequence is longer than maximum: {len(tseq):,} > {MAX_LEN:,}")
biopython_align(qseq=qseq, tseq=tseq, param=param_q)
def run(start=1,
end='',
mode=LOCAL_ALIGN,
gap_open=11,
gap_extend=1,
protein=False,
translate=False,
inter=False,
verbose=False,
query='',
target=''):
"""
Handles an alignment request.
"""
# Set the verbosity of the process.
utils.set_verbosity(logger, level=int(verbose))
# Ensure counter is reset.
jsonrec.reset_counter()
# Requires two inputs.
if not (query and target):
utils.error(f"Please specify both a QUERY and a TARGET")
param1 = objects.Param(name=query,
protein=protein,
translate=translate,
start=start,
end=end,
gap_open=gap_open,
gap_extend=gap_extend,
mode=mode)
param2 = objects.Param(name=target,
protein=protein,
translate=translate,
start=start,
end=end,
gap_open=gap_open,
gap_extend=gap_extend,
mode=mode)
# Get the JSON data.
param1.json = storage.get_json(param1.name, inter=inter, strict=True)
param2.json = storage.get_json(param2.name, inter=inter, strict=True)
for rec1 in param1.json:
for rec2 in param2.json:
qrecs = fastarec.get_fasta(rec1, param=param1)
trecs = fastarec.get_fasta(rec2, param=param2)
for qseq in qrecs:
for tseq in trecs:
parasail_align(qseq=qseq, tseq=tseq, param=param1)
def make_param(acc):
"""
Creates a parameter for each accession.
"""
# Set the verbosity
utils.set_verbosity(logger, level=int(verbose))
# A simple wrapper class to carry all parameters around.
p = objects.Param(start=start,
end=end,
seqid=seqid,
protein=protein,
revcomp=revcomp,
acc=acc,
translate=translate,
reverse=reverse,
uid=id_,
gff=gff,
complement=complement,
name=name,
inter=inter,
features=features,
fasta=fasta,
type=type,
gene=gene,
regexp=match,
transcribe=transcribe)
# Fill the json data for the parameter if not an update
p.json = fetch.get_json(p.acc, seqid=seqid, inter=inter)
return p
def run(update=False,
rename='',
seqid='',
protein=False,
verbose=False,
*data):
"""
Fetches and manages data in storage.
"""
# Set the verbosity
utils.set_verbosity(logger, level=int(verbose))
# Reset counter (needed for consistency during testing).
jsonrec.reset_counter()
# A simple wrapper class to represent input parameters.
param = objects.Param(seqid=seqid,
rename=rename,
start=1,
protein=protein,
update=update)
# Fetch the data.
fetch_data(data, param=param)
# Renaming after fetching.
if rename:
rename_data(data, param=param, newname=rename)
def make_param(name):
"""
Creates a parameter for each accession.
"""
# Set the verbosity
utils.set_verbosity(logger, level=int(verbose))
# A very common error to pass a fragment as
if name.startswith("-"):
msg = f"Invalid accession number: {name}"
utils.error(msg)
# A simple wrapper class to carry all parameters around.
p = objects.Param(start=start, end=end, seqid=seqid, protein=protein, revcomp=revcomp,
update=update, name=name, gff=gff, translate=translate, reverse=reverse, complement=complement,
fasta=fasta, type=type, gene=gene, regexp=match, transcribe=transcribe)
# Fill the json data for the parameter.
p.json = storage.get_json(p.name, seqid=seqid, inter=inter)
return p
def run(start=1,
end='',
gap_open=11,
gap_extend=1,
local_=False,
global_=False,
semiglobal=False,
protein=False,
translate=False,
inter=False,
verbose=False,
query=None,
target=None):
"""
Performs an alignment between the query and target.
"""
# Set the verbosity of the process.
utils.set_verbosity(logger, level=int(verbose))
# Ensure counter is reset.
jsonrec.reset_counter()
# Requires two inputs.
if not (query and target):
utils.error(f"Please specify both a QUERY and a TARGET")
if global_:
mode = const.GLOBAL_ALIGN
elif local_:
mode = const.LOCAL_ALIGN
elif semiglobal:
mode = const.SEMIGLOBAL_ALIGN
else:
mode = const.SEMIGLOBAL_ALIGN
param1 = objects.Param(acc=query,
protein=protein,
translate=translate,
start=start,
end=end,
gap_open=gap_open,
gap_extend=gap_extend,
mode=mode)
param2 = objects.Param(acc=target,
protein=protein,
translate=translate,
start=start,
end=end,
gap_open=gap_open,
gap_extend=gap_extend,
mode=mode)
# Get the JSON data.
param1.json = storage.get_json(param1.acc, inter=inter, strict=True)
param2.json = storage.get_json(param2.acc, inter=inter, strict=True)
for rec1 in param1.json:
for rec2 in param2.json:
qrecs = fastarec.get_fasta(rec1, param=param1)
trecs = fastarec.get_fasta(rec2, param=param2)
for qseq in qrecs:
for tseq in trecs:
parasail_align(qseq=qseq, tseq=tseq, param=param1)
def run(start=1,
end='',
gap_open=11,
gap_extend=1,
local_=False,
global_=False,
semiglobal=False,
protein=False,
translate=False,
inter=False,
table=False,
strict=False,
pep1=False,
pep3=False,
verbose=False,
target=None,
query=None):
"""
Performs an alignment between the query and target.
"""
# Alignments over this size will take a long time!
MAX_LEN = 100000
# Set the verbosity of the process.
utils.set_verbosity(logger, level=int(verbose))
# Reset counter (needed for consistency during testing).
jsonrec.reset_counter()
# This method requires two inputs.
if not (query and target):
utils.error(f"Please specify both a QUERY and a TARGET")
if global_:
mode = const.GLOBAL_ALIGN
elif local_:
mode = const.LOCAL_ALIGN
elif semiglobal:
mode = const.SEMIGLOBAL_ALIGN
else:
mode = const.GLOBAL_ALIGN
# A parameter for each record.
param1 = objects.Param(acc=query,
protein=protein,
translate=translate,
pep1=pep1,
pep3=pep3,
start=start,
end=end,
gap_open=gap_open,
gap_extend=gap_extend,
mode=mode)
param2 = objects.Param(acc=target,
protein=protein,
translate=translate,
start=start,
end=end,
gap_open=gap_open,
gap_extend=gap_extend,
mode=mode)
# Get the JSON data.
param1.json = storage.get_json(param1.acc, inter=inter, strict=True)
param2.json = storage.get_json(param2.acc, inter=inter, strict=True)
# Each data object may contain several records.
for rec1 in param1.json:
for rec2 in param2.json:
qrecs = fastarec.get_fasta(rec1, param=param1)
trecs = fastarec.get_fasta(rec2, param=param2)
for qseq in qrecs:
for tseq in trecs:
if (len(qseq) > MAX_LEN):
utils.error(
f"query is longer than maximum: {len(qseq):,} > {MAX_LEN:,}"
)
if (len(tseq) > MAX_LEN):
utils.error(
f"target sequence is longer than maximum: {len(tseq):,} > {MAX_LEN:,}"
)
biopython_align(qseq=qseq,
tseq=tseq,
param=param1,
table=table,
strict=strict)