def __init__(self,
root_dir,
fasta_filenames,
fastq_filenames,
ref_fasta,
out_pickle,
ice_opts,
sge_opts,
cpus,
tmp_dir=None):
"""
fasta_filenames --- a list of splitted nfl fasta files.
ref_fasta --- (unpolished) consensus isoforms
out_pickle --- a pickle file with all nfl fasta reads
root_dir --- ICE root output directory
tmp_dir --- if not None, write temporary clusters, dazz, las
files to the given temporaray directory
sge_opts --- params for SGE environment, including
use_sge : use SGE or not
max_sge_jobs: maximum number of sub-jobs submitted
unique_id : unique qsub job id, important that this
DOES NOT CONFLICT!
"""
self.prog_name = "IceAllPartials"
IceFiles.__init__(self,
prog_name=self.prog_name,
root_dir=root_dir,
tmp_dir=tmp_dir)
self.fasta_filenames, self.ref_fasta = \
self._validate_inputs(fasta_filenames=fasta_filenames,
ref_fasta=ref_fasta)
if fastq_filenames is not None:
for fq in fastq_filenames:
assert op.exists(fq)
self.fastq_filenames = fastq_filenames # note: could be None
self.out_pickle = out_pickle
self.ice_opts = ice_opts
self.sge_opts = sge_opts
self.cpus = cpus # this is the number of CPUs to use per SGE job or per local job
self.add_log("Making dir for mapping noFL reads: " + self.nfl_dir)
mkdir(self.nfl_dir)
self.add_log("input fasta files are: " +
", ".join(self.fasta_filenames))
self.add_log("temp pickle files are: " +
", ".join(self.pickle_filenames))
self.add_log("out pickle file is: " + self.out_pickle)
self.add_log("temp directory is: " + str(self.tmp_dir))
def __init__(self, root_dir, nfl_fa, bas_fofn, ccs_fofn,
ice_opts, sge_opts, ipq_opts, fasta_fofn=None,
tmp_dir=None):
"""
root_dir --- IceFiles.root_dir, usually data/clusterOutDir
nfl_fa --- non-full-length reads in fasta, e.g., isoseq_nfl.fasta
bas_fofn --- e.g. input.fofn of bas|bax.h5 files
ccs_fofn --- e.g. ccs.fofn of ccs files.
ipq_opts --- IceQuiverHQLQOptions
qv_trim_5: ignore QV of n bases in the 5' end
qv_trim_3: ignore QV of n bases in the 3' end
hq_quiver_min_accuracy: minimum allowed quiver accuracy
to mark an isoform as high quality
hq_isoforms_fa|fq: polished, hiqh quality consensus
isoforms in fasta|q
lq_isoforms_fa|fq: polished, low quality consensus
isoforms in fasta|q
"""
IceFiles.__init__(self, prog_name="IcePolish", root_dir=root_dir,
bas_fofn=bas_fofn, ccs_fofn=ccs_fofn,
fasta_fofn=fasta_fofn, tmp_dir=tmp_dir)
self.nfl_fa = realpath(nfl_fa)
self.ice_opts = ice_opts
self.sge_opts = sge_opts
self.ipq_opts = ipq_opts
self.add_log("ece_penalty: {0}, ece_min_len: {1}".format(self.ice_opts.ece_penalty, self.ice_opts.ece_min_len))
self.icep = None # IceAllPartials.
self.iceq = None # IceQuiver
self.icepq = None # IceQuiverPostprocess
self._nfl_splitted_fas = None
self.validate_inputs()
def __init__(self,
root_dir,
fasta_filenames,
ref_fasta,
out_pickle,
sge_opts,
ccs_fofn=None,
tmp_dir=None):
"""
fasta_filenames --- a list of splitted nfl fasta files.
ref_fasta --- (unpolished) consensus isoforms
out_pickle --- a pickle file with all nfl fasta reads
ccs_fofn --- should be reads_of_insert.fofn or None
root_dir --- ICE root output directory
tmp_dir --- if not None, write temporary clusters, dazz, las
files to the given temporaray directory
sge_opts --- params for SGE environment, including
use_sge : use SGE or not
max_sge_jobs: maximum number of sub-jobs submitted
unique_id : unique qsub job id, important that this
DOES NOT CONFLICT!
blasr_nproc: blasr -nproc param, number of threads per cpu.
"""
self.prog_name = "IceAllPartials"
IceFiles.__init__(self,
prog_name=self.prog_name,
root_dir=root_dir,
tmp_dir=tmp_dir)
self.fasta_filenames, self.ref_fasta, self.ccs_fofn, = \
self._validate_inputs(fasta_filenames=fasta_filenames,
ref_fasta=ref_fasta,
ccs_fofn=ccs_fofn)
self.out_pickle = out_pickle
self.sge_opts = sge_opts
self.add_log("Making dir for mapping noFL reads: " + self.nfl_dir)
mkdir(self.nfl_dir)
self.add_log("input fasta files are: " +
", ".join(self.fasta_filenames))
self.add_log("temp pickle files are: " +
", ".join(self.pickle_filenames))
self.add_log("out pickle file is: " + self.out_pickle)
self.add_log("temp directory is: " + str(self.tmp_dir))
def __init__(self, root_dir, fasta_filenames, fastq_filenames, ref_fasta,
out_pickle, ice_opts, sge_opts, cpus, tmp_dir=None):
"""
fasta_filenames --- a list of splitted nfl fasta files.
ref_fasta --- (unpolished) consensus isoforms
out_pickle --- a pickle file with all nfl fasta reads
root_dir --- ICE root output directory
tmp_dir --- if not None, write temporary clusters, dazz, las
files to the given temporaray directory
sge_opts --- params for SGE environment, including
use_sge : use SGE or not
max_sge_jobs: maximum number of sub-jobs submitted
unique_id : unique qsub job id, important that this
DOES NOT CONFLICT!
"""
self.prog_name = "IceAllPartials"
IceFiles.__init__(self, prog_name=self.prog_name, root_dir=root_dir, tmp_dir=tmp_dir)
self.fasta_filenames, self.ref_fasta = \
self._validate_inputs(fasta_filenames=fasta_filenames,
ref_fasta=ref_fasta)
if fastq_filenames is not None:
for fq in fastq_filenames:
assert op.exists(fq)
self.fastq_filenames = fastq_filenames # note: could be None
self.out_pickle = out_pickle
self.ice_opts = ice_opts
self.sge_opts = sge_opts
self.cpus = cpus # this is the number of CPUs to use per SGE job or per local job
self.add_log("Making dir for mapping noFL reads: " + self.nfl_dir)
mkdir(self.nfl_dir)
self.add_log("input fasta files are: " +
", ".join(self.fasta_filenames))
self.add_log("temp pickle files are: " +
", ".join(self.pickle_filenames))
self.add_log("out pickle file is: " + self.out_pickle)
self.add_log("temp directory is: " + str(self.tmp_dir))
def __init__(self,
root_dir,
nfl_fa,
bas_fofn,
ccs_fofn,
ice_opts,
sge_opts,
ipq_opts,
fasta_fofn=None,
tmp_dir=None):
"""
root_dir --- IceFiles.root_dir, usually data/clusterOutDir
nfl_fa --- non-full-length reads in fasta, e.g., isoseq_nfl.fasta
bas_fofn --- e.g. input.fofn of bas|bax.h5 files
ccs_fofn --- e.g. ccs.fofn of ccs files.
ipq_opts --- IceQuiverHQLQOptions
qv_trim_5: ignore QV of n bases in the 5' end
qv_trim_3: ignore QV of n bases in the 3' end
hq_quiver_min_accuracy: minimum allowed quiver accuracy
to mark an isoform as high quality
hq_isoforms_fa|fq: polished, hiqh quality consensus
isoforms in fasta|q
lq_isoforms_fa|fq: polished, low quality consensus
isoforms in fasta|q
"""
IceFiles.__init__(self,
prog_name="IcePolish",
root_dir=root_dir,
bas_fofn=bas_fofn,
ccs_fofn=ccs_fofn,
fasta_fofn=fasta_fofn,
tmp_dir=tmp_dir)
self.nfl_fa = realpath(nfl_fa)
self.ice_opts = ice_opts
self.sge_opts = sge_opts
self.ipq_opts = ipq_opts
self.add_log("ece_penalty: {0}, ece_min_len: {1}".format(
self.ice_opts.ece_penalty, self.ice_opts.ece_min_len))
self.icep = None # IceAllPartials.
self.iceq = None # IceQuiver
self.icepq = None # IceQuiverPostprocess
self._nfl_splitted_fas = None
self.validate_inputs()
def __init__(self, root_dir, fasta_filenames, ref_fasta,
out_pickle, sge_opts, ccs_fofn=None, tmp_dir=None):
"""
fasta_filenames --- a list of splitted nfl fasta files.
ref_fasta --- (unpolished) consensus isoforms
out_pickle --- a pickle file with all nfl fasta reads
ccs_fofn --- should be reads_of_insert.fofn or None
root_dir --- ICE root output directory
tmp_dir --- if not None, write temporary clusters, dazz, las
files to the given temporaray directory
sge_opts --- params for SGE environment, including
use_sge : use SGE or not
max_sge_jobs: maximum number of sub-jobs submitted
unique_id : unique qsub job id, important that this
DOES NOT CONFLICT!
blasr_nproc: blasr -nproc param, number of threads per cpu.
"""
self.prog_name = "IceAllPartials"
IceFiles.__init__(self, prog_name=self.prog_name, root_dir=root_dir, tmp_dir=tmp_dir)
self.fasta_filenames, self.ref_fasta, self.ccs_fofn, = \
self._validate_inputs(fasta_filenames=fasta_filenames,
ref_fasta=ref_fasta,
ccs_fofn=ccs_fofn)
self.out_pickle = out_pickle
self.sge_opts = sge_opts
self.add_log("Making dir for mapping noFL reads: " + self.nfl_dir)
mkdir(self.nfl_dir)
self.add_log("input fasta files are: " +
", ".join(self.fasta_filenames))
self.add_log("temp pickle files are: " +
", ".join(self.pickle_filenames))
self.add_log("out pickle file is: " + self.out_pickle)
self.add_log("temp directory is: " + str(self.tmp_dir))
