#---- MaSuRCA sample config file
#---- process with runSRCA.pl command tool

#------------- DATA SECTION ----------------------------------------------

# DATA is specified as type {PE,JUMP,OTHER}= two_letter_prefix mean stdev fastq(.gz)_fwd_reads fastq(.gz)_rev_reads
# NOTE that PE reads are always assumed to be  innies, i.e. --->  <---, and JUMP are assumed to be outties <---    --->; if there are any jump libraries that are innies, such as longjump, specify them as JUMP and specify NEGATIVE mean
# rev reads are optional for PE libraries and mandatory for JUMP libraries
# any OTHER sequence data (454, Sanger, Ion torrent, etc) must be first converted into Celera Assembler compatible .frg files (see http://wgs-assembler.sourceforge.com)

DATA

PE= pe 180 20  /FULL_PATH/frag_1.fastq  /FULL_PATH/frag_2.fastq

JUMP= sh 3600 200  /FULL_PATH/shortjump_1.fastq  /FULL_PATH/shortjump_2.fastq

# OTHER=/FULL_PATH/file.frg

END


#------------- PARAMETERS SECTION ----------------------------------------

PARAMETERS

# set this to 1 for Illumina-only assemblies and to 0 if you have 2x or more long (Sanger, 454) reads
# default if not specified: 1
#USE_LINKING_MATES=1

# k-mer size for deBruijn graph 
# values between 25 and 101 are supported
# auto will compute the optimal size based on the read data and GC content
# default if not specified: auto
#GRAPH_KMER_SIZE=auto

# this parameter is useful if you have too many jumping library mates.
# Typically set it to 60 for bacteria and something large (300) for mammals
# default if not specified: 60
#LIMIT_JUMP_COVERAGE = 60

#these are the additional parameters to Celera Assembler.  do not worry about performance, number or processors or batch sizes -- these are computed automatically. for mammals do not set cgwErrorRate above 0.15!!!
CA_PARAMETERS= cgwErrorRate=0.25 merylMemory=8192 ovlMemory=4GB 

# minimum count k-mers used in error correction 1 means all k-mers are used.  one can increase to 2 if coverage >100
# default if not specified: 1
#KMER_COUNT_THRESHOLD = 1

# number of cpus to use
# default if not specified: 1
#NUM_THREADS= 1

#this is mandatory jellyfish hash size
# default if not specified: 100000000
#JF_SIZE=100000000

# this specifies if we do (1) or do not (0) want to trim long runs of homopolymers (e.g. GGGGGGGG) from 3' read ends, use it for high GC genomes
# default if not specified: 0
#DO_HOMOPOLYMER_TRIM=0

# default if not specified: 0
#EXTEND_JUMP_READS=0

# close gaps in scaffolds 
# default if not specified: 1
#CLOSE_GAPS=1

# default if not specified: 1
#USE_LINKING_MATES=1


END
