# example configuration file

# DATA is specified as type {PE,JUMP,OTHER,PACBIO} and 5 fields:
# 1)two_letter_prefix 2)mean 3)stdev 4)fastq(.gz)_fwd_reads
# 5)fastq(.gz)_rev_reads. The 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. Reverse 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= p0 180 20 /data/ngs/projects/hithesh/SO_7717/ILLUMINA_RAWDATA/SO_7717_145_R1.fastq.gz /data/ngs/projects/hithesh/SO_7717/ILLUMINA_RAWDATA/SO_7717_145_R2.fastq.gz
#PE= p1 180 20 /data/ngs/projects/hithesh/SO_7718_FIG_WASP/Illumina_SR_Raw_Reads/SO-7718-Fig-Wasp-SI_R1_001.fastq.gz /data/ngs/projects/hithesh/SO_7718_FIG_WASP/Illumina_SR_Raw_Reads/SO-7718-Fig-Wasp-SI_R2_001.fastq.gz
#JUMP= sh 3600 200 /data/ngs/projects/hithesh/SO_7718_FIG_WASP/Illumina_MP_Raw_Reads/SO-7718-Fig-Wasp-MP-5kb_R1_001.fastq.gz /data/ngs/projects/hithesh/SO_7718_FIG_WASP/Illumina_MP_Raw_Reads/SO-7718-Fig-Wasp-MP-5kb_R2_001.fastq.gz 
#pacbio reads must be in a single fasta file! make sure you provide absolute path
#PACBIO=/FULL_PATH/pacbio.fa
NANOPORE=/data/ngs/projects/hithesh/SO_7717/ANALYSIS/PRE-PROCESSING/Nano/SO_7717_145_BC08/GT_SO_7718_145_BC08.fasta
#OTHER=/data/ngs/projects/hithesh/SO_7956_7733/Ion_Torrent/FRG_Output.frg
END

PARAMETERS
#this is k-mer size for deBruijn graph values between 25 and 127 are supported, auto will compute the optimal size based on the read data and GC content
GRAPH_KMER_SIZE = auto
#set this to 1 for all Illumina-only assemblies
#set this to 1 if you have less than 20x long reads (454, Sanger, Pacbio) and less than 50x CLONE coverage by Illumina, Sanger or 454 mate pairs
#otherwise keep at 0
USE_LINKING_MATES = 0
#this parameter is useful if you have too many Illumina jumping library mates. Typically set it to 60 for bacteria and 300 for the other organisms
LIMIT_JUMP_COVERAGE = 300
#these are the additional parameters to Celera Assembler.  do not worry about performance, number or processors or batch sizes -- these are computed automatically.
#set cgwErrorRate=0.25 for bacteria and 0.1<=cgwErrorRate<=0.15 for other organisms.
CA_PARAMETERS = cgwErrorRate=0.15
#minimum count k-mers used in error correction 1 means all k-mers are used.  one can increase to 2 if Illumina coverage >100
KMER_COUNT_THRESHOLD = 1
#auto-detected number of cpus to use
NUM_THREADS = 30
#this is mandatory jellyfish hash size -- a safe value is estimated_genome_size*estimated_coverage
JF_SIZE = 902951142
#set this to 1 to use SOAPdenovo contigging/scaffolding module.  Assembly will be worse but will run faster. Useful for very large (>5Gbp) genomes
SOAP_ASSEMBLY=0
END