#
# NcDNAlign example config file
#

# Project directory
C_P_DIR = "/XXX/YYY/ZZZ/project"
# Source directory
C_SOURCE_DIR = "/XXX/YYY/ZZZ/project/src"
# Alignment dir
C_ALN_DIR = "/XXX/YYY/ZZZ/project/dialign2-2"
# your blast executing command / binary
C_BLAST_CMD = "blastall -p blastn -r 5 -q -4 -G 10 -E 6 "
# eValue
C_CUTOFF_EVALUE = "1e-3";
# path to your clustalw binary
C_ALN_CMD = "dialign2-2 -n "
# min number of sequences in an alignment
C_MIN_SEQ = "3"
# minimal alignment length, sequences >= this value are kept
C_MIN_ALN_LENGTH = "40"
C_FLANKING = "30"
# Keys from 'http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#7.3' that are neglected
#C_GBK_KEYS = "CDS;repeat_region;repeat_unit;LTR;satellite;sig_peptide;transit_peptide;mat_peptide"
C_GBK_KEYS = " "
# ensure alignment quality, cutoff value, only trimmed sequences with qtGaps/length < C_GAP_SCORE make it into an alignment, the smaller the better
C_GAP_SCORE = "0.3"
# who is the target, same name like the name of the first organism
C_TARGET_NAME = "hsa"

# ------------------------------------------------------
# 1. Organism = Human
# ------------------------------------------------------
# name
ORG_NAME = "hsa"
# name of the file containing the ncregions in fasta format
ORG_NCREGIONS_FASTA = "hsa.cut.fa"

# ------------------------------------------------------
# 2. Organism = Mouse
# ------------------------------------------------------
# name 
ORG_NAME = "mmu"
# name of the file containing the ncregions in fasta format
ORG_NCREGIONS_FASTA = "mmu.cut.fa"

# ------------------------------------------------------
# 3. Organism = Rat
# ------------------------------------------------------
# name 
ORG_NAME = "rno"
# name of the file containing the ncregions in fasta format
ORG_NCREGIONS_FASTA = "rno.cut.fa"

# 4. Cow
ORG_NAME = "cow"
ORG_NCREGIONS_FASTA = "cow.cut.fa"

# 5. Zebrafish
ORG_NAME = "dre"
ORG_NCREGIONS_FASTA = "dre.cut.fa"

# 6. Chicken
ORG_NAME = "gga"
ORG_NCREGIONS_FASTA = "gga.cut.fa"