parameters_docker.tsv

############################################################################################
###############################   P.E.M.A. 's PARAMETERS   #####################################
############################################################################################
#
#
# In this file there are all the parameters that NEED TO BE ASSIGNED every time you need PEMA to run!
# That does not mean that these parameters that we have her,  are the only  parameters of the tools PEMA uses!
# As you already may know, the combinations are infinite! 
# Hence, we encourage you the most to study the manual of each tool and make them as good as possible for your SPECIFIC experiment.
# In each and every variable that you see quotes ( '' ) you have to write inside those the option you choose
# The rest, you need to complete them with a number and never add quotes.
# We chose to have a set of parameters for some tools (mainly for Trimmomatic) as 'by default'. That is because in some cases, plenty of time is required 
# in order to have a correct set of those. In the link next to each tool, you can find further information about its parameters. 
# YOU NEED TO BE REALLY CAREFUL WHEN YOU FILL THIS FILE !!
#  From each variable you have to leave EXACTLY FOUR (4) BLANKS and then fill the parameter as you wish. 
#
## just to test that the parameters are assigned right in our main script:
#
sources	my_parameters_work_just_fine!
#
## give in your each uniq experiment a NAME, so a single output file will be created for each of them 
outputFile	<put_here_the_name_of_your_output_file>
#
#############################################################
######################   blastqc    #########################
#############################################################
#
## no parameters here! 
#
#
#############################################################
##################### trimmomatic   #########################		//	http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/TrimmomaticManual_V0.32.pdf
#############################################################
#
## Performs an adaptive quality trim, balancing the benefits 
## of retaining longer reads against the costs of retaining 
## bases with errors.
## can be either 'Yes' or 'No'
maxInfo	Y
#
#
############ for MAXINFO ####################
## Specifies the read length which is likely to allow the
## location of the read within the target sequence to be determined
targetLength	200
#
#
## this value, which should be set between 0 and 1, specifies the 
## balance between preserving as much read length as possible vs. 
## removal of incorrect bases. A low value of this parameter (<0.2) 
## favours longer reads, while a high value (>0.8) favours read correctness.
strictness	0.3
#
#
############ for ILLUMINACLIP ##################
## specifies the path to a fasta file containing all the adapters, PCR sequences etc. 
## The naming of the various sequences within this file determines how they are used.
adapters	TruSeq2-PE.fa
#
##specifies the maximum mismatch count which will still allow a full match 
## to be performed
seedMismatches	1
#
#
## specifies how accurate the match between the two 'adapter ligated' reads 
## must be for PE palindrome read alignment.
palindromeClipThreshold	30
#
#
## specifies how accurate the match between any adapter etc. sequence must be against a read.
simpleClipThreshold	10
#
#
############ for LEADING  ##########################
## Remove low quality bases from the beginning. As long as a base has a value 
## below this threshold the base is removed and the next base will be investigated.
## quality: Specifies the minimum quality required to keep a base.
leading	3
#
#
############ for TRAILING  #############################
## Remove low quality bases from the end. As long as a base has a value below this 
## threshold the base is removed and the next base (which as trimmomatic is starting 
## from the 3‟ prime end would be base preceding the just removed base) will be investigated.
trailing	3
#
#
############  for MINLEN  ################################
## This module removes reads that fall below the specified minimal length. If required, it should 
## normally be after all other processing steps. Reads removed by this step will be counted and
## included in the „dropped reads‟ count presented in the trimmomatic summary
minlen	100
#
#
#
###############################################################
#################   BayesHammer   #############################
###############################################################
#
## no parameters here!
#
#
################################################################
####################    SPAdes       ########################### ######
################################################################ 
#
## PANDAseq has more than one merging algorithms. Here, we set the algorithm used for assembly
## The most common of them are: 
## pear --> uses the formula described in the PEAR paper (Zhang 2013), optionally with the probability of a random base (q) provide
## simple_bayesian --> uses the formula described in the original paper (Masella 2012), optionally with an error estimation (ε) provided.
## other options are stich, flash and more that you can fing in the above link
spadesAlgorithm	simple_bayesian
#
#
## in our command, we also have -a that strips the primers after assembly, rather than before. 
## and -B that allows input sequences to lack a barcode/tag. 
## if you wish to have even more option of SPAdes you should visit http://neufeldserver.uwaterloo.ca/%7Eapmasell/pandaseq_man1.html
##and then add them to the main script
#
#
################################################################
################  DEREPLICATE me ti voitheia ton OBITools !  ###################
#################################################################
#
#
## no parameters here!
#
#
#
################################################################################################
#//////////////////////////////////////////////////////////////////////////////////////////////
############################ GENE -  dependent parameters #####################################
#//////////////////////////////////////////////////////////////////////////////////////////////
###############################################################################################
#
## The marker gene you have is really important for both the clustering & chimera removal procedure and the
## taxonomy assignment. By default, the pipeline runs for 16S. Substitute with 'COI' if COI is your marker gene
## write down your gene after "_" character - do not erase it!! 
gene	gene_16S
#
## You might want to download the last version of SILVA database and handle it with the primers you have used
## in your experiment in order to get an even better assignment. You can find SILVA 132 already in PEMA/tools  
## Hence, by default getting_silva is FALSE. You have to turn it to TRUE in order to do so.
gettingSilva	FALSE
primerF	''
primerR	''
#
#
## if your marker gene is 16S, you can choose between 2 different approaches of taxonomy assignment (alignment & phylogenetic based)
## by  default, you get an alignment based taxonomy assignment - set as 'alignment' -  which is based on SILVA and CREST 
## however you can also get a phylogenetic based assignment, by putting 'phylogeny' in this parameter
taxonomyAssignmentMethod	alignment
#
#
## if your marker gene is  COI, you can choose between 2 different approaches of clustering. Depending on which of them you choose 
## you get either a robust output in a short time (SWARM)  or a non-robust output (CROP) that requires quite much more time. CROP is a bayesian   
## algorithm and that is why its output in non-robust. By default, SWARM algorithm runs for the clustering. You have to change in to 'CROP'
## if you want the CROP algorithm to do the clustering step
clusteringAlgo	algo_SWARM
#
#
#
#
# in case of SWARM, the user needs to speeecify the value of "d" parameter
# d is the number of missmatches
d	10
#
#######################################################################################################
#
## Would you like to get one taxonomy assignment using normal BLAST?!
## can be either 'Yes' or 'No'.
blast	N
blastPath	/home/haris/blocking_primers/programs/BLAST/ncbi-blast-2.7.1+/bin
blastDatabase	/mnt/big/blastdb/nt/nt/nt
#
#
#
#
#  If your marker gene is 16S and you wish to use Rhea in order to analyse your returned data
#  then you need to create a tree using these OTUs. If you do wish so, set 'preparingForRhea' as 'Yes'
#
forRhea	N
#
## If you need to make a tree for running Rhea, you will need RAxMl
## Hence please give us the path where RAxML is located on your cluster
raxmlPath	/usr/bin/raxmlHPC
pathForR	/usr/bin/Rscript
# In case you wish for Beta-diversity from Rhea, then you have to set a categorical variable.
# Hence, you have to set 'categoricalVariable' as 'Y' and then go to the Rhea script for Beta-diversity to set which variable you want as categorical
# We should mention here, that P.E.M.A has already created the tree Rhea needs from its first step. Hence, the user now can use Rhea scripts, even out of P.E.M.A
# as all needed files are made.
categoricalVariable	Y
#
#
## Give to PEMA the percentage of similarity over which you want to keep taxonomy as for sure taxa
percentageOfSimilarity	91
#
#
## Finally, do you want your raw data to be removed in another file and empty the "rawData" file and all the checkpoints of PEMA to be also in an extra folder
## Swich 'Yes' to 'No' if you wish so. Be very careful when you do that, as you need to remember that if you want to analyze another dataset through P.E.M.A
## you will have to remove the first one manually. 
emptyRawDataFile	Y
emptyCheckpoints	Y