allParameters.template

################################################################################
################################################################################

# This is an IGGPIPE TEMPLATE FILE giving an example of how to define each
# IGGPIPE parameter.  DO NOT EDIT THIS FILE.  COPY THIS FILE to a new file name
# that suggests the analysis you are doing, such as name that uses the single
# letters to be defined herein to represent each genome.  For example, if you
# are doing an analysis of tomato and S. pennellii genomes and you plan to use
# the letters H and P to represent those two genomes, you might copy it to a
# new file name as follows:
#       cp allParameters.template allParameters.HP

# After copying this file to your own file name, EDIT YOUR NEW FILE and set the
# parameters to the values required for your analysis.  Read through the first
# part of the file carefully to see what needs to be changed.  Parameters that
# usually don't need to be changed have been placed at the end of this file, and
# a comment block marks the place where those parameters begin.  Your focus will
# be on setting parameters in the beginning part of this file.

# Paths, directories, filenames, and program parameters required for running
# the IGGPIPE pipeline are defined here, including paths to input files that
# are used, and some of the output files that are generated.  (Paths to programs
# used by IGGPIPE are defined in file allPathParameters.ours, which is set up
# one time only during IGGPIPE installation.)

# This file has been filled in with actual values as EXAMPLES.  These examples
# are for analyzing tomato (H) ITAG2.4 and S. pennellii (P) V2.0 genomes.
# As you edit your new file, CHANGE these values to appropriate ones for your
# analysis.

# You use this parameter file to run the IGGPIPE pipeline by specifying this
# parameter file's name in a 'make' command using the PARAMS command line
# argument.  See the RUN user guide for instructions on running the pipeline.

# Many paths and filenames defined here are located in or under the pipeline
# install directory, and the definitions often specify a pathname or filename
# relative to it.  If a filename doesn't start with "/", it is relative to the
# install directory.

# All definitions in this file are 'make' variable assignments.  A variable is
# replaced by its value when you write $(VARIABLE_NAME).  Some variables are
# defined here and then used in $() constructs in subsequent definitions of
# other variables.  You can add as many of your own variables as you want to
# this file to help you define directory and file names.

# All system environment variables are automatically predefined as make variables
# by 'make' itself, so you can use $(ENVIRONMENT_VARIABLE_NAME) to access the
# value of an environment variable.

#@@ Each parameter has a BOLD COMMENT STARTING WITH "#@@" saying whether that
#@@ parameter should be changed, seldom needs changed, already has a reasonable
#@@ value, etc.  This will guide you as to what needs to be changed.

################################################################################
################################################################################


################################################################################
# Value of "k" to use, i.e. the length of a k-mer in base-pairs.  Too small a
# value will result in too few common unique k-mers.  The computation time and
# memory requirements increase dramatically as this is increased.  A value of
# K=14 has worked well for the tomato genome without using too much memory.  A
# significantly larger genome might require use of K=15.  Use an upper-case
# letter K here.
################################################################################

#@@ CHANGE THIS TO THE VALUE OF K THAT YOU WANT.  A VALUE OF 14 OFTEN WORKS WELL.
K := 14


################################################################################
# Number of genomes to be analyzed.  Must be 2 or more.  If more than two, other
# definitions in this file that are based on genomes will need to be expanded to
# include one definition per genome.
################################################################################

#@@ CHANGE THIS TO YOUR NUMBER OF GENOMES TO BE ANALYZED.
N_GENOMES := 2


# Genome numbers, starting at 1, separated from each other by a space.  If
# N_GENOMES is more than 2, add additional numbers to this.  Believe it or not,
# it seems to be very difficult to generate this sequence automatically in 'make',
# as, despite all its macros, it has no concept of arithmetic and counting.
#@@ CHANGE THIS TO 1 2 3 (etc. up to N_GENOMES)
GENOME_NUMBERS := 1 2


################################################################################
# Letters to assign to genomes.  Choose one UPPER CASE letter to represent each
# genome.  The first genome, referred to as genome 1, is the REFERENCE GENOME.
# The reference genome can be chosen at random if there is not one genome that
# is the obvious one.  It would be best to choose one with few sequence IDs, so
# if one genome has chromosome IDs (i.e. pseudomolecules) and the other(s) have
# scaffolds, choose the one with chromosomes as the reference.
#
# Genome 1 data columns will appear first in output files, genome 2 data columns
# second, and so on.
#
# You must define exactly N_GENOMES definitions, with a different UPPER CASE
# letter for each one.
################################################################################

# In this example, we use two genomes, the Heinz tomato genome (letter H) and
# the Solanum pennellii genome (letter P).  The tomato genome is the reference
# genome.
#@@ CHANGE THESE (AND ADD MORE IF NECESSARY) TO ASSIGN LETTERS TO YOUR GENOMES.
GENOME_1 := H
GENOME_2 := P


# Combine the above letters together with one space between each letter.
# For example, if GENOME_1 is "X", GENOME_2 is "Y", and GENOME_3 is "Z", then
# GENOME_LETTERS will be "X Y Z".
#@@ DO NOT CHANGE THIS.
GENOME_LETTERS := $(foreach X,$(GENOME_NUMBERS),$(GENOME_$(X)))


# Combine the above letters together with no spaces into a single string.
# For example, if GENOME_1 is "X", GENOME_2 is "Y", and GENOME_3 is "Z", then
# GENOME_LETTERS_SQUISHED will be "XYZ".
#@@ DO NOT CHANGE THIS.
GENOME_LETTERS_SQUISHED := $(shell echo "$(GENOME_LETTERS)" | sed "s/ //g")


################################################################################
# Path of main output directory where output files will be placed.
################################################################################

# It is useful to include the genome letters and the value of k in the name, so
# that a different run with different genomes or k will produce output in a
# different folder.  For example, with genome letters "X" and "Y" and with K set
# to "14", the output directory name would be "outXY14".  This directory will be
# created when the pipeline is run if it doesn't already exist.
#@@ THIS DOES NOT NEED TO BE CHANGED UNLESS YOU PREFER A DIFFERENT OUTPUT
#@@ DIRECTORY, BUT IF NOT CHANGED, TAKE NOTE OF THE DIRECTORY NAME.
DIR_IGGPIPE_OUT := out$(GENOME_LETTERS_SQUISHED)$(K)


################################################################################
# Paths of FASTA files containing the genomes to be analyzed, and for output
# files that are generated from the FASTA files.
################################################################################

# Path to parent folder of all genome data.
#@@ YOU ONLY NEED TO DEFINE THIS IF YOU USE IT IN OTHER ASSIGNMENTS BELOW.
#@@ OTHERWISE, DELETE THIS.
# (This example assumes that an environment variable named "BRADYLAB" has been
# defined, that gives the path to a high-level directory.)
DIR_GENOME_DATA := $(BRADYLAB)/Genomes


# Directories containing the FASTA files for the N_GENOMES genomes.
#@@ YOU ONLY NEED TO DEFINE THIS IF YOU USE IT IN OTHER ASSIGNMENTS BELOW.
#@@ OTHERWISE, DELETE THIS.
# (This example uses the DIR_GENOME_DATA variable above to define the directories
# containing files for the two genomes to be run through the IGGPIPE pipeline.)
DIR_GENOME_DATA_1 := $(DIR_GENOME_DATA)/Soly/ITAG2.4_release
DIR_GENOME_DATA_2 := $(DIR_GENOME_DATA)/Sope/V2.0genome


# Paths of the N_GENOMES FASTA files containing the genome sequences being
# analyzed.  Each variable name must be the string "PATH_GENOME_FASTA_" followed
# by the genome number.
#@@ SET THESE TO YOUR GENOME FASTA FILE PATHS.
# The ITAG2.4_genomic.fasta genome is the latest tomato genome release from solGenomics.net.
# The Spenn.fasta genome is the recent S. pennellii genome release from solGenomics.net.
PATH_GENOME_FASTA_1 := $(DIR_GENOME_DATA_1)/ITAG2.4_genomic.fasta
PATH_GENOME_FASTA_2 := $(DIR_GENOME_DATA_2)/Spenn.fasta


################################################################################
# Pipeline command timing.
################################################################################

# Set TIME_CMDS to YES if you wish to time each pipeline command, NO if not.
# When set to YES, each pipeline command will be executed with the shell command
# '(time <command>) 2>&1'.  The 'time' program executes <command> and times it,
# and when it finishes, it prints out the amount of time it used (on stderr,
# which is redirected to stdout with 2>&1), in this format:
#   real    0m0.002s
#   user    0m0.000s
#   sys     0m0.001s
# These values indicate the amount of time required to execute the command.  For
# details on their interpretation, see 'man time'.
#@@ CHANGE THIS TO "NO" IF YOU DON'T WANT TO SEE COMMAND TIMING INFO IN THE OUTPUT.
TIME_CMDS := YES


################################################################################
# Parameters affecting the IGG marker algorithm and likely to be changed by the
# user.
#
# All parameters here should be carefully reviewed and set by the user.
################################################################################

# Minimum acceptable length of an LCR in base-pairs.  This is normally equal
# to the minimum acceptable amplicon size AMIN (defined below), although it
# could be larger.  Smaller values make more LCRs and increase computation time.
#@@ YOU PROBABLY WANT TO SET THIS EQUAL TO YOUR MINIMUM ACCEPTABLE AMPLICON LENGTH.
LMIN := 250


# Maximum distance in bp between two adjacent k-mers in an LCR.  If two adjacent
# k-mers are farther apart than this in any genome, the k-mers serve to split the
# LCR into two LCRs at that point.  This value limits the maximum length of one
# indel within an Indel Group or LCR.  This is normally set equal to the maximum
# acceptable amplicon size AMAX (defined below), although it could be larger.
#@@ YOU PROBABLY WANT TO SET THIS EQUAL TO YOUR MAXIMUM ACCEPTABLE AMPLICON
#@@ LENGTH.
DMAX := 800


# Minimum IGG marker amplicon size in any genome.
#@@ SET THIS EQUAL TO YOUR MINIMUM ACCEPTABLE AMPLICON LENGTH.
AMIN := 250


# Maximum IGG marker amplicon size in any genome.  The amplicon size will always
# be less than DMAX also.  This also limits the maximum Indel Group size.
#@@ SET THIS EQUAL TO YOUR MAXIMUM ACCEPTABLE AMPLICON LENGTH.
AMAX := 800


# For a given IGG marker, when the smallest amplicon size is AMIN, this is the
# minimum ADDITIONAL bp's of size required for the next larger amplicon.  If
# there are only two genomes or if NDAMIN is 2 (defined below), then if one
# genome's amplicon size is AMIN, the other's must be at least AMIN+ADMIN.
# For the purpose of finding Indel Groups only, this is the minimum Indel
# Group size that will ever be found.
#@@ SET THIS EQUAL TO YOUR MINIMUM ACCEPTABLE DIFFERENCE IN AMPLICON LENGTHS WHEN
#@@ ONE AMPLICON'S LENGTH IS EQUAL TO AMIN AND ANOTHER IS AMIN+ADMIN.
ADMIN := 100


# For a given IGG marker, when the largest amplicon size is AMAX, this is the
# minimum FEWER bp's of size required for the next smaller amplicon.  If there
# are only two genomes or if NDAMIN is 2 (defined below), then if one genome's
# amplicon size is AMAX, the other's must be no more than AMAX-ADMAX.
#
# Interpolation is linear between ADMIN and ADMAX.  The amplicon sizes for
# each genome are sorted smallest first, then the interpolated ADMIN/ADMAX
# value is applied to each amplicon except the last, and if fewer than NDAMIN
# genomes meet the test, the marker is discarded.
#
# The idea behind ADMIN/ADMAX is to require amplicons to be different enough in
# size that they can be easily distinguished on a gel, but that required size
# difference may scale up as the amplicon sizes grow.
#
# For the purpose of finding Indel Groups only, this should be set equal to ADMIN.
#@@ SET THIS EQUAL TO YOUR MAXIMUM ACCEPTABLE DIFFERENCE IN AMPLICON LENGTHS WHEN
#@@ ONE AMPLICON'S LENGTH IS EQUAL TO AMAX AND ANOTHER IS AMAX-ADMAX.
ADMAX := 200


# Minimum number of distinct amplicon sizes for each marker.  Set this to the
# number of genomes if you want distinct amplicon sizes for each genome.  Set
# it to a smaller value (>= 2) if fewer distinct sizes are acceptable.  For
# two genomes, this is always set to 2.  If for example there were 3 genomes
# and you set this to 3, all amplicons of a marker must be a different size,
# but if you set this to 2, as long as two genomes have different amplicon
# sizes, the marker is accepted (i.e. two genomes might have the same or
# similar-sized amplicons, but the third genome would have a different size).
#@@ SET THIS EQUAL TO N_GENOMES IF YOU WANT ALL GENOMES TO PRODUCE DIFFERENT
#@@ AMPLICON LENGTHS.  OTHERWISE, SET IT TO THE MINIMUM NUMBER OF ACCEPTABLE
#@@ DIFFERENT AMPLICON LENGTHS.
NDAMIN := 2


# Two files of Indel Groups are produced, one of overlapping Indel Groups and
# another of non-overlapping Indel Groups.  Likewise, two files of IGG markers
# are produced, one of overlapping markers and another of non-overlapping.
# You may be interested in one or the other, overlapping or non-overlapping,
# or perhaps both.
#
# To explain the meaning of "overlapping" in this context, consider two Indel
# Groups or markers that follow one after another, the first bounded by k-mers
# A and B, and the second bounded by k-mers C and D.  Suppose that both AB and
# CD satisfy the parameters above such as AMIN and AMAX.  Now, it is entirely
# possible that AD also satisfies those parameters.  If it does, it will be
# included in the overlapping Indel Group and IGG marker files along with AB
# and CD, even though its amplicon includes both the AB and the CD amplicon
# regions, i.e. there is redundancy in the Indel Groups and IGG markers within
# the overlapping files.
#
# The files of non-overlapping Indel Groups and IGG markers are created by
# removing some Indel Groups or IGG markers from the set of overlapping ones,
# so that after removal none of the Indel Groups or IGG markers overlap.
#
# Two different methods are provided for determining which Indel Groups and
# markers to remove, and the following parameter chooses the method.  It must
# be the value MIN or else MAX, meaning:
#   MIN: when a set of Indel Groups/markers overlaps, the SHORTEST Indel
#       Group/marker within the genome being tested is retained, and any Indel
#       Groups/markers that overlap it are removed.  (I.e. shortest amplicons).
#   MAX: when a set of Indel Groups/markers overlaps, the LONGEST Indel
#       Group/marker within the genome being tested is retained, and any Indel
#       Groups/markers that overlap it are removed.  (I.e. longest amplicons).
# That removal process is repeated until no more Indel Groups/markers overlap.
# It is repeated for each genome as it is possible two Indel Groups/markers
# might overlap in one genome but not another.
#
# Therefore you would set this to MIN if you want to bias towards getting
# shorter amplicons, and to MAX to bias towards longer ones.
#@@ CHANGE THIS TO YOUR CHOICE OF THE TWO
OVERLAP_REMOVAL := MAX


# Maximum deviation in base pairs from expected amplicon size of off-target
# amplicons discovered by e-PCR (electronic PCR) testing of the candidate
# markers.  Set this to a value where, if there is an off-target amplicon
# whose size is within this amount of the target amplicon size, then you want
# that marker to be marked bad and deleted.
#@@ SET THIS TO THE LARGEST AMPLICON SIZE POSSIBLE WITH YOUR PCR PARAMETERS SUCH
#@@ AS THE EXTENSION TIME AND POLYMERASE POLYMERIZATION RATE.
EPCR_MAX_DEV := 2500


#@@#############################################################################
#@@#############################################################################
#@@#############################################################################
#@@ Nothing below this point has to be changed.  Unless you are studying the
#@@ parameters in detail, skip the remaining sections.
#@@
#@@ The following section collects together the parameters which are next most
#@@ likely to be changed, if you do need to change parameters.
#@@#############################################################################
#@@#############################################################################
#@@#############################################################################

################################################################################
# Parameters affecting the IGG marker algorithm but less likely to be changed by
# the user.
################################################################################

# Minimum number of sequential k-mers required to call a locally conserved
# region (LCR).  The larger this number, the less likely that LCRs will be
# called that are not actually conserved regions, and the fewer the number
# of LCRs that will be called.  Numbers too large will limit the number of
# markers created.  Smaller values make more LCRs and increase computation
# time.  Since e-PCR testing will validate all candidate markers, there is
# no reason not to set this to its minimum of 2 if you are only making
# markers.  If you want LCRs for another purpose such as a reliable Indel
# Group list or for doing whole genome alignment, a larger value such as 4
# is advised.
# This should be at least two more than twice MINFLANK (defined below),
# since that is the minimum number of k-mers in an LCR that could result
# in an Indel Group call.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
KMIN := 2


# Minimum distance in bp between two adjacent k-mers in an LCR.  If two k-mers are
# closer than this, the second one of the close pair is discarded.  This prevents
# a series of back-to-back k-mers in a conserved region from satisfying the KMIN
# setting or MINFLANK setting.  A value in the range of k would be reasonable.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
DMIN := 10


# Minimum number of k-mers to the left of the left-side Indel Group k-mer and to
# the right of the right-side Indel Group k-mer.  May be 0 for none.  The Indel
# Group k-mers are the two common unique k-mers, one on each end of an Indel
# Group, at which primers are designed.  An Indel Group can require only those
# two k-mers, if MINFLANK is 0.  The number of k-mers that must be present in
# the LCR to create a candidate marker is at least 2+2*MINFLANK.  By setting
# this to a value larger than 0, you might decrease the odds that a single
# random common unique k-mer on the LCR could trigger creation of an IGG marker,
# but since e-PCR testing of candidate primers will reject bad random markers,
# there is no reason not to leave this set to 0.  For the purpose of finding
# Indel Groups only, you may want to use a larger value than 0.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
MINFLANK := 0


# Number of base pairs of additional sequence to retrieve on each side of each
# of the two anchor k-mers of an IGG marker, for the purpose of designing
# primers.  Primer parameters such as minimum and maximum size, and all other
# parameters, are set in a parameter file used by primer3 to design the primer.
# The value 2*EXTENSION_LEN + k is the maximum possible primer length.  Set
# EXTENSION_LEN large enough that you create multiple sites at which primers
# could possibly be found.  The maximum allowed setting for this is 50.  If
# this is >= minimum primer length, then it is possible a primer will be made
# in the extension region and not including ANY of the unique k-mer bases.
# This might make the primer less likely to be unique, but the e-PCR testing
# of the primers will catch those situations and reject those primers.  A
# value of 20 with k=14 provides 54 base-pairs of sequence in which to design
# a primer.  Note that N's are placed at positions where genomes differ in the
# extended regions on either side of the k-mer, so that primer3 will not design
# a primer on that position.  This means many candidate markers will fail to get
# a primer designed and so will be rejected.  All bases of the k-mer are of
# course identical across all genomes.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
EXTENSION_LEN := 20


# Size, in base pairs, of a "hash word" in the e-PCR program.  This parameter has
# two different effects, unrelated unfortunately.  First, it determines the size
# of the data structure used for searching sequence data for primers, and in this
# context, a larger value uses more memory but can speed up the e-PCR operation,
# while a smaller value uses less memory but can cause inefficient use of hash
# tables, resulting in slow operation.  Second, it sets the number of base pairs
# starting at the 3' end of each primer, which must match EXACTLY with no gaps.
# In this context, a larger value means fewer off-target hits will be identified
# and removed as ambiguous markers, while a smaller value means more off-target
# hits will be identified and more markers will be removed as being ambiguous.
# Base pairs beyond this number in the primer are subject to the next two
# parameters, EPCR_MAX_MISMATCH and EPCR_MAX_GAPS.  The e-PCR program uses a
# default of 7 for this.  It probably shouldn't be made smaller than that, and
# probably should be made larger.  Larger values will result in more markers.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
EPCR_WORD_SIZE := 8


# Maximum number of off-target primer mismatches, in base pairs, within the
# primer outside of the EPCR_WORD_SIZE base pairs at the 3' end, during e-PCR
# (electronic PCR) testing of the candidate markers.  Set this to a size where,
# if there is an off-target approximate primer match with this many or fewer
# mismatched bases, then you want that marker to be marked bad and deleted.
# Larger values increase computation time and reduce number of markers obtained.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
EPCR_MAX_MISMATCH := 3


# Maximum number of off-target primer match gaps, in base pairs, within the
# primer outside of the EPCR_WORD_SIZE base pairs at the 3' end, during e-PCR
# (electronic PCR) testing of the candidate markers.  Set this to a size where,
# if there is an off-target approximate primer match with this many or fewer
# gaps in the mismatch, then you want that marker to be marked bad and deleted.
# Larger values increase computation time and reduce number of markers obtained.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
EPCR_MAX_GAPS := 1


# Prefix to use for the marker IDs.  Markers are numbered sequentially, and an ID
# column in the marker output file consists of the following prefix, followed by
# the sequential number of each marker.  This prefix lets you assign different
# IDs during different runs of IGGPIPE using different genomes or other parameters.
#@@ THIS IS A REASONABLE VALUE FOR THIS PARAMETER.
ID_PREFIX := IGG_$(GENOME_LETTERS_SQUISHED)$(K)_


# For plotting number and density of final markers, this parameter sets the
# minimum value in the marker NDA column (which ranges from NDAMIN to the number
# of genomes) of the markers to be plotted.  For example, if you are making both
# 2-way and 3-way markers (3 genomes with NDAMIN=2) and want to plot only the
# 3-way markers count/density, set this to 3.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PLOT_NDAMIN := $(NDAMIN)


# For plotting number and density of final markers, this parameter sets the
# alpha intensity with which black lines are drawn on chromosomes at marker
# positions.  This must be greater than 0 and no more than 1.  At 1, a single
# line is black.  As the value moves towards 0, and single line is lighter and
# lighter gray, and multiple lines must be plotted on top of each other to
# achieve black pixels.  For example, 0.25 would need 4 markers to get to black.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PLOT_ALPHA := 0.25


################################################################################
# Parameters used if the 'make IndelsSNPs' command is run to find Indels and
# SNPs between the genomes.
################################################################################

# Path of input file for aligning LCRs or IndelGroups or Markers and locating the
# Indels and SNPs in the alignment.  Used only if 'make IndelsSNPs' command is run.
# This path can be any of three different files, shown here commented out: the LCBs
# file (for capturing Indels and SNPs even in regions that do not have an amplicon
# size difference), the non-overlapping IndelGroups file (for capturing Indels and
# SNPs only in regions with the specified amplicon size difference, including
# regions that may be rejected as markers), or the non-overlapping markers file
# (for capturing Indels and SNPs only in regions where candidate markers have
# been found).
# The output files containing the Indel AND SNP positions are the same name as the
# input file with the .suffix replaced with the suffix ".indels.tsv" and ".snps.tsv".
# Copy and uncomment the ONE you want to use to find Indels and SNPs if you intend
# to run 'make IndelsSNPs'.  Note: these names refer to symbols defined later, so
# they use "=" instead of ":=".
#@@ THESE DO NOT NEED TO BE CHANGED.
#PATH_INDELS_SNPS_INPUT_FILE = $(PATH_LCB_FILE)
#PATH_INDELS_SNPS_INPUT_FILE = $(PATH_NONOVERLAPPING_INDEL_GROUPS_FILE)
#PATH_INDELS_SNPS_INPUT_FILE = $(PATH_NONOVERLAPPING_MARKERS_FILE)
# In this example we use the markers file.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PATH_INDELS_SNPS_INPUT_FILE = $(PATH_NONOVERLAPPING_MARKERS_FILE)


# For finding Indels and SNPs with 'make IndelsSNPs', these parameters set the
# maximum number of Indels and SNPs per Kbp of reference genome sequence that
# may exist in an alignment and still examine the alignment for Indels and SNPs.
# If more than this number of Indels or SNPs is found, that alignment is ignored.
# Set these to reject alignments that have an anomalously high number of Indels
# or SNPs, which might indicate a false positive LCR, Indel Group, or marker and
# an alignment of essentially random sequence.  When random sequences ARE aligned,
# they have minimum Indel and SNP counts of around 10 and 30 per Kbp, respectively.
#@@ THIS DOES NOT NEED TO BE CHANGED.
MAX_INDELS_PER_KBP := 10
MAX_SNPS_PER_KBP := 30


# For finding Indels and SNPs with 'make IndelsSNPs', this parameter can be set
# TRUE to scramble the sequences of each genome except the reference genome, in
# order to measure the statistics on the number of Indels and SNPs found in random
# sequence (which is displayed at the end when 'make IndelsSNPs' is run).  If this
# is set TRUE, then set the above two parameters to 500 and 1000 respectively.
#@@ THIS DOES NOT NEED TO BE CHANGED.
SCRAMBLE_SEQUENCE := FALSE


################################################################################
# Output directory of main output files.
################################################################################

# Path to the directory where the LCR, Indel Group, and marker output files will
# be placed.
#@@ THIS DOES NOT NEED TO BE CHANGED.
DIR_MAIN_OUTPUT := $(DIR_IGGPIPE_OUT)


################################################################################
# Paths of k-mer data output files.
################################################################################

# Directory in which to place k-mer data output files.  This directory will be
# created if it doesn't exist.
#@@ THIS DOES NOT NEED TO BE CHANGED.
DIR_KMERS := $(DIR_IGGPIPE_OUT)/Kmers


# Prefix, including directory, of output files that will be generated containing
# k-mer information.  These files are created for each genome:
# 1. a list of unique k-mers in the genome:
#       <this prefix><genome_number>.kmers
# 2. a text file of k-mer statistics:
#       <this prefix><genome_number>.stats
# 3. a list of SORTED unique k-mers in the genome:
#       <this prefix><genome_number>.sorted
# 4. A list of positions of common unique k-mers in the genome:
#       <this prefix><genome_number>.isect
# 5. A list of common unique k-mers of these genome and preceding genomes
#       <this prefix><genome_number>.merge
#@@ THIS DOES NOT NEED TO BE CHANGED.
PFX_KMERS_DATA_FILE := $(DIR_KMERS)/Kmers_


# Path of the k-mer text file containing the common unique k-mers with genomic
# positions in each genome, sorted by reference genome position.  This file will
# be created.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PATH_COMMON_UNIQUE_KMERS := $(DIR_KMERS)/common.unique.kmers


################################################################################
# Paths of primer data files.
################################################################################

# Path of primer3 settings file.  You must create this file by copying file
# primer3settings.default.txt, which is a modified version of the settings file
# named primer3web_v4_0_0_default_settings.txt that is part of the primer3
# V2.3.6 distribution.  The changes made to that file were:
#   1. Changed the descriptive string P3_FILE_ID
#   2. Added PRIMER_THERMODYNAMIC_PARAMETERS_PATH to point to primer3_config
#       subfolder in installed primer3 distribution.
#   3. Changed PRIMER_EXPLAIN_FLAG from 1 to 0.
#   4. Changed PRIMER_PRODUCT_SIZE_RANGE to twice PRIMER_MIN_SIZE followed by
#       "-300", e.g. 36-300
#   5. Changed PRIMER_NUM_RETURN from 5 to 1.
#   6. Changed PRIMER_GC_CLAMP from 0 to 1.
# COPY primer3settings.default.txt to the file name given here, then EDIT it to
# set PRIMER_THERMODYNAMIC_PARAMETERS_PATH to the path of the primer3_config
# directory that was included in the primer3 distribution.  You can change any
# other primer design parameters you want, including the above (except leave
# PRIMER_NUM_RETURN at 1; only one primer pair per marker is retained).  Refer
# to the primer3 manual for an explanation of all the parameters.  Refer to
# IGGPIPE install instructions for more details.

# This is normally in the IGGPIPE installation directory.
#@@ THIS DOES NOT NEED TO BE CHANGED BUT THE FILE MUST BE COPIED AND EDITED.
PATH_PRIMER3_SETTINGS := primer3settings.txt


# Directory in which to place these files.  This directory will be created if it
# doesn't exist.
#@@ THIS DOES NOT NEED TO BE CHANGED.
DIR_PRIMER_DATA := $(DIR_IGGPIPE_OUT)/Primers


# Path of data file to be created containing sequence data for use by primer3
# when designing primers.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PATH_PRIMER3_IN := $(DIR_PRIMER_DATA)/Primer3In.txt


# Path of data file to be created by primer3 containing primer design results.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PATH_PRIMER3_OUT := $(DIR_PRIMER_DATA)/Primer3Out.txt


################################################################################
# Filename prefixes of main output files.
################################################################################

# Filename prefix of LCR data file and bad K-mer data file.
#@@ THESE DO NOT NEED TO BE CHANGED.
PFX_LCR_FILE := LCRs
PFX_BAD_KMERS_FILE := BadKmers


# Filename prefixes of Indel Groups data files.
#@@ THESE DO NOT NEED TO BE CHANGED.
PFX_OVERLAPPING_INDEL_GROUPS_FILE := IndelGroupsOverlapping
PFX_NONOVERLAPPING_INDEL_GROUPS_FILE := IndelGroupsNonoverlapping


# Filename prefix of IGG marker file, for markers prior to e-PCR verification.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PFX_NONVALIDATED_MARKER_FILE := NonvalidatedMarkers


# Filename prefix of e-PCR bad marker file.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PFX_BAD_MARKER_ERROR_FILE := MarkerErrors


# Filename prefixes of "good" IGG marker files, with bad (by e-PCR) markers removed.
#@@ THESE DO NOT NEED TO BE CHANGED.
PFX_OVERLAPPING_MARKERS_FILE := MarkersOverlapping
PFX_NONOVERLAPPING_MARKERS_FILE := MarkersNonoverlapping


# Filename prefixes of IGG marker count and density plot files.
#@@ THESE DO NOT NEED TO BE CHANGED.
PFX_MARKER_COUNTS_FILE := MarkerCounts
PFX_MARKER_DENSITY_FILE := MarkerDensity


# Filename prefix of LCB data file.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PFX_LCB_FILE := LCBs


################################################################################
# Filename suffixes of main output files.
################################################################################

# Filename suffixes for the main output files are defined here.  These suffixes
# grow longer and longer as you move down the page here, each containing the
# previous one and adding to it.  These are long because they include as part
# of the filename all of the parameter values used to make the file.  These
# prefixes form UNWIELDY file names that are not really necessary, but are
# useful if you try different parameter values and want to keep track of the
# different output files.  However, if you only plan to experiment with a
# limited number of parameter values, you could simplify these prefixes to
# only include those parameter values as part of the prefix.  Or, you can
# make the prefixes be very simple or even empty, if you want simple file
# names and will delete or archive existing files when you make parameter
# changes.
# An advantage of putting parameter values that change into the file name is
# that, when you make a parameter change, 'make' will rebuild only the files
# it needs to, and the ones whose name remains the same because they were built
# at an earlier step whose parameters remain unchanged are not rebuilt, saving
# build time.
#@@ FOR EXAMPLE, YOU MIGHT WANT ALL PREFIXES TO BE SIMPLY _$(DMIN)_$(DMAX)
#@@ OR, A MORE COMPLEX EXAMPLE THAT INCLUDES THE e-PCR PARAMETERS IN FINAL OUTPUT FILES:
#@@ Set SFX_ constants to _$(DMIN)_$(DMAX) except leave SFX_GOOD_MARKER_FILE as-is.


# Suffix to use for the files created when LCRs are called.
# (This includes in the filename the parameter values used to find LCRs)
#@@ THIS DOES NOT NEED TO BE CHANGED.
SFX_LCR_FILE := _K$(K)k$(KMIN)L$(LMIN)D$(DMIN)_$(DMAX)


# Suffix to use for the file that holds Indel Group positions.
# (This includes all of SFX_LCR_FILE and the parameter values used to find markers)
#@@ THIS DOES NOT NEED TO BE CHANGED.
SFX_INDEL_GROUPS_FILE := $(SFX_LCR_FILE)A$(AMIN)_$(AMAX)d$(ADMIN)_$(ADMAX)N$(NDAMIN)F$(MINFLANK)


# Suffix to use for the file that holds DNA sequence around k-mers.
# (This includes all of SFX_INDEL_GROUPS_FILE and the parameter value used to extract DNA sequences)
#@@ THIS DOES NOT NEED TO BE CHANGED.
SFX_DNA_SEQS_FILE := $(SFX_INDEL_GROUPS_FILE)X$(EXTENSION_LEN)


# Suffix of IGG marker file, for markers prior to e-PCR verification.
# (This includes all of SFX_DNA_SEQS_FILE and it should include the parameters
# used when making primers, but those are in the primer parameters file.  We
# should use a separate primer parameters filename for each run, and include
# that filename within this filename, but we don't, we assume the same primer
# parameter file always.  If it changes, user had better clean the directories
# before doing a make.)
#@@ THIS DOES NOT NEED TO BE CHANGED.
SFX_NONVALIDATED_MARKER_FILE := $(SFX_DNA_SEQS_FILE)


# Suffix to use for the files that hold candidate IGG marker primers, both
# before and after e-PCR testing,  and marker density plots.
# (This includes all of SFX_NONVALIDATED_MARKER_FILE and the parameter values used for e-PCR)
#@@ THIS DOES NOT NEED TO BE CHANGED.
SFX_GOOD_MARKER_FILE := $(SFX_NONVALIDATED_MARKER_FILE)V$(EPCR_MAX_DEV)W$(EPCR_WORD_SIZE)M$(EPCR_MAX_MISMATCH)G$(EPCR_MAX_GAPS)


# Suffix to use for the files created when LCBs are created.
# (No parameters are needed for conversion of LCRs to LCBs, so just the suffix here.)
#@@ THIS DOES NOT NEED TO BE CHANGED.
SFX_LCB_FILE := $(SFX_LCR_FILE)


################################################################################
# Full pathnames of main output files.  These pathnames are formed by joining
# DIR_MAIN_OUTPUT/PFX_*/SFX_*, where all of these variables were defined
# immediately above.  Do not change the names here.  To change the names,
# change the prefixes and/or suffixes.
################################################################################

# Directory in which to place miscellaneous output files that are generated
# directly from the FASTA files.  This directory will be created if it doesn't
# exist.
#@@ THIS DOES NOT NEED TO BE CHANGED.
DIR_GENOME_OUT_DATA := $(DIR_IGGPIPE_OUT)/GenomeData


# Prefix, including directory, of output files that will be generated from the
# FASTA files.  These files are created for each genome:
# 1. A list of genome FASTA file sequence IDs and their lengths:
#       <this prefix><genome_number>.idlens
# 2. A list of sequence contig information: for each contig, the sequence ID,
#   start position, contig sequence number, and contig length:
#       <this prefix><genome_number>.contigs
#@@ THIS DOES NOT NEED TO BE CHANGED.
PFX_GENOME_DATA_FILE := $(DIR_GENOME_OUT_DATA)/Genome_


# Paths of LCR data file and bad K-mer data file.
#@@ DO NOT CHANGE THESE.
PATH_LCR_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_LCR_FILE)$(SFX_LCR_FILE).tsv
PATH_BAD_KMERS_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_BAD_KMERS_FILE)$(SFX_LCR_FILE).tsv


# Paths of Indel Groups data files.
#@@ DO NOT CHANGE THESE.
PATH_OVERLAPPING_INDEL_GROUPS_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_OVERLAPPING_INDEL_GROUPS_FILE)$(SFX_INDEL_GROUPS_FILE).tsv
PATH_NONOVERLAPPING_INDEL_GROUPS_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_NONOVERLAPPING_INDEL_GROUPS_FILE)$(SFX_INDEL_GROUPS_FILE).tsv


# Path prefix of file that holds DNA sequence around k-mers, excluding only the
# suffix, which consists of "_<genome number>.dnaseqs".
#@@ DO NOT CHANGE THIS.
PFX_DNA_SEQS_PATH := $(DIR_GENOME_OUT_DATA)/$(PFX_OVERLAPPING_INDEL_GROUPS_FILE)$(SFX_DNA_SEQS_FILE)


# Path of IGG marker file, for markers prior to e-PCR verification.
#@@ DO NOT CHANGE THIS.
PATH_NONVALIDATED_MARKER_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_NONVALIDATED_MARKER_FILE)$(SFX_NONVALIDATED_MARKER_FILE).tsv


# Path prefix of IGG marker e-PCR bad marker file as determined by e-PCR,
# excluding only the suffix, which consists of "_<genome number>.bad.tsv".
#@@ DO NOT CHANGE THIS.
PFX_BAD_MARKER_ERROR_PATH := $(DIR_MAIN_OUTPUT)/$(PFX_BAD_MARKER_ERROR_FILE)$(SFX_GOOD_MARKER_FILE)


# Paths of "good" IGG marker files, with bad (by e-PCR) markers removed.
#@@ DO NOT CHANGE THESE.
PATH_OVERLAPPING_MARKERS_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_OVERLAPPING_MARKERS_FILE)$(SFX_GOOD_MARKER_FILE).tsv
PATH_NONOVERLAPPING_MARKERS_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_NONOVERLAPPING_MARKERS_FILE)$(SFX_GOOD_MARKER_FILE).tsv


# Path prefixes of IGG marker counts and density plot files.  ".pdf" is appended
# to the counts file path, and "_<genome letter>.png" is appended to the density
# file path.
#@@ DO NOT CHANGE THESE.
PFX_MARKER_COUNTS_PATH := $(DIR_MAIN_OUTPUT)/$(PFX_MARKER_COUNTS_FILE)$(SFX_GOOD_MARKER_FILE)
PFX_MARKER_DENSITY_PATH := $(DIR_MAIN_OUTPUT)/$(PFX_MARKER_DENSITY_FILE)$(SFX_GOOD_MARKER_FILE)


# Path of LCB data file.
#@@ THIS DOES NOT NEED TO BE CHANGED.
PATH_LCB_FILE := $(DIR_MAIN_OUTPUT)/$(PFX_LCB_FILE)$(SFX_LCB_FILE).tsv


# Path of input file containing DNA sequences merged with LCBs or Indel Groups or
# Markers data, used only if 'make IndelsSNPs' command is run to find Indels and SNPs.
#@@ DO NOT CHANGE THIS.
# Replace the ".<suffix>" on PATH_INDELS_SNPS_INPUT_FILE with ".withseqs.<suffix>"
# to form the output file name.
PATH_INDELS_SNPS_SEQS_FILE := $(basename $(PATH_INDELS_SNPS_INPUT_FILE)).withseqs$(suffix $(PATH_INDELS_SNPS_INPUT_FILE))


# Path of Indels and SNPs output files, used only if 'make IndelsSNPs' command is
# run to find Indels and SNPs.
#@@ DO NOT CHANGE THESE.
# Replace the ".<suffix>" on PATH_INDELS_SNPS_INPUT_FILE with ".indels.<suffix>"
# and ".snps.<suffix>" to form the output file names.
PATH_INDELS_OUTPUT_FILE := $(basename $(PATH_INDELS_SNPS_INPUT_FILE)).indels$(suffix $(PATH_INDELS_SNPS_INPUT_FILE))
PATH_SNPS_OUTPUT_FILE := $(basename $(PATH_INDELS_SNPS_INPUT_FILE)).snps$(suffix $(PATH_INDELS_SNPS_INPUT_FILE))


# Path of Indels plot file, used only if 'make plotIndels' command is run to plot
# Indel data.
#@@ THIS DOES NOT NEED TO BE CHANGED.
# Replace the ".<suffix>" on PATH_INDELS_OUTPUT_FILE with ".<pdf>" to form the
# plot file name.
PATH_INDELS_PLOT_FILE := $(basename $(PATH_INDELS_OUTPUT_FILE)).pdf


################################################################################
# Paths of debugging settings.  Set these TRUE to turn on debug output from
# individual modules.
################################################################################

# Produce debug output when calling LCRs.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_FINDLCRS := FALSE


# Produce debug output when analyzing LCRs for Indel Groups.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_ANALYZELCRS := FALSE


# Produce debug output when getting DNA sequences at Indel Group k-mers.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_GETDNASEQS := FALSE


# Produce debug output when finding primers.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_FINDPRIMERS := FALSE


# Produce debug output when doing e-PCR testing of marker primer pairs.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_EPCRTESTING := FALSE


# Produce debug output when removing markers identified as bad by e-PCR.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_RMVBADMARKERS := FALSE


# Produce debug output when getting DNA sequences for locating Indels and SNPs.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_GET_DNA_SEQS_FOR_INDELS_SNPS := FALSE


# Produce debug output when extracting and aligning sequences and locating Indels and SNPs.
#@@ THIS DOES NOT NEED TO BE CHANGED.
INVESTIGATE_ALIGN_AND_GET_INDELS_SNPS := FALSE


################################################################################
# End of file.
################################################################################