Options Available

Here we attempt to list all available FALCON options, with defaults where applicable.

input_fofn = REQUIRED
# (string) filename for the file-of-filenames
# Each line is fasta filename.
# Any relative paths are relative to the location of the input_fofn.

genome_size = REQUIRED
# (integer) estimated number of base-pairs in haplotype

seed_coverage = 30
# (integer) requested coverage for auto-calculated cutoff

length_cutoff = 1
# (integer) minimum length of seed-reads used for pre-assembly stage
# If '-1', then auto-calculate the cutoff based on genome_size and seed_coverage.

length_cutoff_pr = 50
# (integer) minimum length of seed-reads used after pre-assembly, for the "overlap" stage

target = assembly
# (string) "assembly" or "preads"
# If "preads", then pre-assembly stage is skipped and input is assumed to be preads.

job_type = local
# (string) grid submission system, or "local"
# case-insensitive
# Supported types include: "sge", "lsf", "pbs", "torque", "slurm", "local"

# maximum concurrency -- different for different stages
default_conconcurrent_jobs = 8

pa_concurrent_jobs = %(default_concurrent_jobs)
cns_concurrent_jobs = %(default_concurrent_jobs) 
ovlp_concurrent_jobs = %(default_concurrent_jobs)

# Grid job distribution options
# No matter what the job_type, we call these "sge_option_*".
# These are ignored for the "local" job_type.
# These are REQUIRED for all other job_types.
# Typical values:
sge_option_cns =  -q default -pe smp 4
sge_option_da =  -q default -pe smp 4
sge_option_fc =  -q default -pe smp 4
sge_option_la =  -q default -pe smp 4
sge_option_pda =  -q default -pe smp 4
sge_option_pla =  -q default -pe smp 4

# sub-tool options
# For specific sub-tool options, try `--help`, search for docs here, or see
#    https://dazzlerblog.wordpress.com/command-guides/

pa_DBdust_option = ...
# Passed to `DBdust`. Used only if `dust = true`.

pa_DBsplit_option = -x250 -s500 -a
# Passed to `DBsplit` during pre-assembly stage.

pa_HPCdaligner_option = -v -k16 -h35 -w7 -e.70 -l40 -s100 -M16
# Passed to `HPC.daligner` during pre-assembly stage.
# We will add `-H` based on "length_cutoff".

pa_dazcon_option = ...
# Passed to `dazcon`. Used only if `dazcon = true`.

falcon_sense_option = ...
# Passed to `fc_consensus`.
# Ignored if `dazcon = true`.

falcon_sense_skip_contained = false
# Causes '-s' to be passed to `LA4Falcon`. Rarely needed.

ovlp_DBsplit_option = -s50 -a
# Passed to `DBsplit` during overlap stage.

ovlp_HPCdaligner_option = -v -k15 -h60 -w6 -e.95 -l40 -s100 -M16
# Passed to `HPC.daligner` during overlap stage.

overlap_filtering_setting = ...
# Passed to `fc_ovlp_filter` during assembly stage.

fc_ovlp_to_graph_option = ...
# Passed to `fc_ovlp_to_graph`.


# Others

skip_checks = false
# (boolean string)
# If "true", then skip `LAcheck` during LAmerge/LAsort.
# (Actually, `LAcheck` is run, but failures are ignored.)
# When *daligner* bugs are finally fixed, this will be unnecessary.

dust = false
# (boolean string)
# If true, then run `DBdust` before pre-assembly.

dazcon = false
# (boolean string)
# If true, then use `dazcon` (from pbdagcon repo).

stop_all_jobs_on_failure = false
# (boolean string) DEPRECATED
# This was used for the old pypeFLOW refresh-loop, used by `run0.py`.
# (This is *not* the option to let jobs currently in SGE (etc) to keep running, which is still TODO.)

use_tmpdir = false
# (boolean string) whether to run each job in TMPDIR and copy results back to nfs
# If "true", use TMPDIR. (Actually, `tempfile.tmpdir`. See standard Python docs: https://docs.python.org/2/library/tempfile.html )
# If the value looks like a path, then it is used instead of TMPDIR.