parameters.drw

################################################################################
#        ___           ___           ___     
#       /\  \         /\__\         /\  \    
#      /::\  \       /::|  |       /::\  \   
#     /:/\:\  \     /:|:|  |      /:/\:\  \  
#    /:/  \:\  \   /:/|:|__|__   /::\~\:\  \ 
#   /:/__/ \:\__\ /:/ |::::\__\ /:/\:\ \:\__\
#   \:\  \ /:/  / \/__/~~/:/  / \/__\:\/:/  /
#    \:\  /:/  /        /:/  /       \::/  / 
#     \:\/:/  /        /:/  /        /:/  /  
#      \::/  /        /:/  /        /:/  /   
#       \/__/         \/__/         \/__/    
#   
################################################################################

# Type of input sequence data, has to be either 'DNA' or 'AA'
InputDataType := 'AA';

# Output folder
OutputFolder := 'Output';

# Folder where auxillary data (e.g. GeneOntology definitions, etc)
# will be stored. The folder must be writable by the user. If not set
# or commented, the default will be ~/.cache/oma/
# You can use environment variables (with getenv() function) or relative
# paths which are relative to the current directory where you start the run
# AuxDataPath := getenv('HOME').'/.cache/oma';

# if you want to recompute everything from scratch every time the script
# is run, set the following parameter to false.
ReuseCachedResults := true;

# number of pairwise protein alignments done in one unit. The larger this 
# number, the longer each unit runs, and the fewer files get produced. This 
# allows to adjust the frequency of milestone steps (e.g. in case of computer 
# crash)
AlignBatchSize := 1e6;

# alignments which have a score lower than MinScore will not be considered.
# The scores are in Gonnet PAM matrices units.
MinScore := 181;

# Length tolerance ratio.  If the length of the effective alignment is less 
# than LengthTol*min(length(s1),length(s2)) then the alignment is not 
# considered.
LengthTol := 0.61;

# During the stable pair formation, if a pair has a distance provable higher 
# than another pair (i.e. StablePairTol standard deviations away) then it is 
# discarded.
StablePairTol := 1.81;

# During the stable pair formation, if the within species evolutionary distance 
# difference is more than InparalogTol standard deviations closer than the 
# distance to the other species, a pair is still considered inparalog even 
# if they don't fullfil the StablePairTol criterion
InparalogTol := 3.00;

# The ParalogTol is used to identify clear paralogous pairs, which can be 
# used in further analysis. If set to a value larger than StablePairTol,
# homologous matches for which the difference in their evolutionary distance
# is larger than ParalogTol * std(distance), where std(distance) is the 
# standard deviation of the distance difference between the closest ortholog
# and the more distant homolog, will be stored. 
# WARNING: This is an experimental feature only! No performance analysis nor
# in-depth debugging has been done on this feature. USE AT OWN RISK!
# computing and storing the paralogs can be disabled by setting this
# parameter to a negative value.
ParalogTol := -2.5*StablePairTol;

# For the verification of stable pairs, there is also a tolerance parameter 
# (for details, see Dessimoz et al, Nucl Acids Res 2006)
VerifiedPairTol := 1.53;

# SkipVerification is a flag to disable the Verification step entirely.
# This can be useful for dataset where little differential gene loss is
# expected and where the verification step takes a long time otherwise.
# Uncomment to activate.
# SkipVerification := true;

# Any sequence which is less than MinSeqLen amino acids long in regular 
# genomes is not considered.
MinSeqLen := 50;

# Whether or not OMA should keep only one splicing variant per gene, i.e. 
# the one with the most homologous matches in all other species.
# Annotation of splicing variants needs to be provided in a text file 
# DB/<genome>.splice 
UseOnlyOneSplicingVariant := true;

# use experimental code (single processor only) to compute homologous
# clusters instead of full All-against-all. 
UseExperimentalHomologousClusters := false;

# OMA groups are cliques on the pairwise ortholog graph. By specifying 
# a QuasiCliquesCutoff of less than 1, OMA groups that do not share any
# species and N/(n*m) >= QuasiCliquesCutoff where N is the number of 
# orthologous relations between the two OMA groups of sizes n and m, 
# will be merged. The merged groups will be written to seperate output
# files.
QuasiCliquesCutoff := 1.0:


##############################################################
# Output parameters
##############################################################
# Enables/disables the generation of stable identifiers for OMA groups (and 
# Hierarchical Groups if their computation enabled). The identifier consists 
# of a prefix to determine the type of the group ('OMA' or 'HOG'), and a 
# subsequence of the amino acid sequence uniquely present in this group. The 
# computation of these ids might require a substantial amount of time. The ids 
# are stored in the OrthoXML files only.
StableIdsForGroups := false;

# Enable/disable guessing of the id types while generating the orthoxml
# file. In this context we refer to ID type guessing as the task to 
# gussing whether an ID should be stored in the geneId, protId or 
# transcriptId tag. If the flag is set to false, the whole fasta header 
# is used and stored as is in the protId tag.
GuessIdType := false;

# Avoid producing some of the output files. This can reduce computing time
# and especially avoids the generation of many files in large analysis. By 
# default all the output files are generated. Uncomment certain lines to 
# avoid the production of the corresponding output.
#WriteOutput_PairwiseOrthologs := false;
#WriteOutput_OrthologousPairs_orthoxml := false;  #this file requires lots of time.
#WriteOutput_OrthologousGroupsFasta := false;
#WriteOutput_HOGFasta := false;
#WriteOutput_Paralogs := false; 
#WriteOutput_PhyleticProfileHOG := false;
#WriteOutput_PhyleticProfileOG := false;


##############################################################
# Hierarchical Orthologous Groups (HOGs)
##############################################################
# Infer the Hierarchical Orthologous Groups (HOGs)? 
# In OMA standalone prior to 2.0 you can activate the inference of HOGs 
# through the Top-Down algorithm by setting 'DoHierarchicalGroup' to 'true'. 
# Since 2.0, you should set it to 'top-down' or 'bottom-up'. The 'top-down' 
# is the original approach, where as 'bottom-up' is the much more scaleable 
# algorithm introduced in version 2.0.0 for the first time. You can disable
# the HOG computation by setting it to 'false'.
DoHierarchicalGroups := 'bottom-up';

# The hierarchical groups need a hierarchy of the involved species in from of 
# a tree. This tree can either be estimated from the OMA Groups by setting the 
# SpeciesTree variable to 'estimate', or a (partially resolved) tree can be 
# given in Newick format. The estimation step needs again additional computing 
# time.
SpeciesTree := 'estimate';
#SpeciesTree := '((mouse,mouse2),human,dog);';

# Out-group species. If the species tree should be estimated, you should provide
# a set of out-group species to properly root the species tree. The set of
# out-group species must form a monophyletic clade that branches off from the
# root.
# If you do not want to specify an out-group set, you can set the parameter to
# 'none', in which case OmaStandalone will use a mid-point rooting. However,
# this root is most likely wrong and inferred hierarchical orthologous groups 
# (HOGs) will be strongly affected from this. Therefore this setting is 
# strongly discouraged
OutgroupSpecies := [];
# OutgroupSpecies := ['dog'];  # example with one out-group species
# OutgroupSpecies := ['DROME', 'DROSA'];  # example with more than one species
# OutgroupSpecies := 'none';  # use midpoint rooting (strongly discouraged)


# The cutoff in GETHOGs bottom-up algorithm to make an edge trusted in the 
# orthology graph among HOGs. This parameter applies only to the bottom-up 
# approach. Use 'ReachabilityCutoff' for the top-down approach. 
MinEdgeCompletenessFraction := 0.65;


# The cutoff of 'average reachability within two steps' defines up to what 
# point a cluster is split into sub-clusters. This parameter applies only to the
# top-down approach. For the bottom-up approach, use the parameter 
# 'MinEdgeCompletenessFraction' instead.
ReachabilityCutoff := 0.65;

# Define maximum amount of time (in sec) spent by the program for breaking
# every connected component of the orthology graph at its weakest link on a
# given taxonomic level. If set to a negative value, no timelimit is enforced.
# This variable applies only to the top-down approach.
MaxTimePerLevel := 1200;  # 20min



##############################################################
# Function Prediction
##############################################################
# Compute predictions using Orthologous groups?
# You can either set it to 'true', which will enable the computation or 
# disable it by setting it to 'false'. Writing the output takes a long time. 
DoGroupFunctionPrediction := true;

# Fraction of group members that need to be assigned with a certain
# GO annotation in order to transfer it. The lower the value is the 
# more liberally functions are propagated.
GroupFunctionCutoff := 0.5;

# Specify how to limit function propagation on clades. Parameter can be
# one of (i) default (ii) none or (iii) <file-path>.
# default infers species tree and limits propagation at predefined clade 
# levels. 'none' disables the limits entirely and the last option allows to 
# point to a tsv file with the following format: <SPECIES NAME>\t<CLADE>,
# that provides a mapping from genome name to a clade. Only annotations that 
# are supported within the same clade are transferred to a genome.
CladeDefinition := 'default';


###############################################################################
# ESPRIT -- Detection of split genes
###############################################################################
# Use Esprit?
# You can either set this to 'true', which will enable esprit and shut down the
# parts of OMA that are not directly needed for esprit, or set it to 'false' to
# make no use of esprit at all.
UseEsprit := false;

# NOTE: Genomes in which split genes are to be found should be called 
#       "{unique name}.contig.fa". All other genomes are considered
#       reference genomes.


# ESPRIT PARAMETERS 

# Confidence level variable for contigs  (this is the parameter "tol" 
# described in the paper)
DistConfLevel := 2;

# Min proportion of genomes with which contigs form many:1 BestMatches to 
# consider that we might be dealing with fragments of the same gene (this is 
# the parameter "MinRefGenomes" described in the paper, normalized by the 
# total number of reference genomes)
MinProbContig := 0.4;

# Maximum overlap between fragmnents of same gene from different contigs
MaxContigOverlap := 5;

# Any sequence which is less than MinSeqLen amino acids long in contigs is not 
# considered.
MinSeqLenContig := 20;

# Minimum score for BestMatch in scaffold recognition
MinBestScore := 250;