#!/bin/bash -l
##################################################################################
#Andy Rampersaud, 02.23.16
#This script is called by FASTQC.sh
##################################################################################
# Specify which shell to use
#$ -S /bin/bash
# Run on the current working directory
#$ -cwd

# Join standard output and error to a single file  
#$ -j n
# change to y if you want a single qlog file 
##################################################################################
#Initialize variables from FASTQC.sh
##################################################################################
#checking the command line arg
#-ne : "is not equal to"
if [ $# -ne 6 ] ; then
      echo "Need 6 arguments for the qsub command:"
      echo "qsub -N ${Job_Name}'_'${Sample_ID} -P waxmanlab -l h_rt=${TIME_LIMIT} FASTQC.qsub ${Sample_ID} ${Dataset_DIR} ${Sample_Labels_DIR} ${BU_User} ${VM_DIR_FASTQC} ${OUTPUT_DIR}"
      exit 0
fi
#process the command line arguments
Sample_ID=$1
Dataset_DIR=$2
Sample_Labels_DIR=$3
BU_User=$4
VM_DIR_FASTQC=$5
OUTPUT_DIR=$6

#Print variables (make sure they appear correctly):
echo "-----------------------"
echo "Start of variable list:"
echo "-----------------------"
echo "Sample_ID:"
echo ${Sample_ID}
echo "Dataset_DIR:"
echo ${Dataset_DIR}
echo "Sample_Labels_DIR:"
echo ${Sample_Labels_DIR}
echo "BU_User:"
echo ${BU_User}
echo "VM_DIR_FASTQC:"
echo ${VM_DIR_FASTQC}
echo "OUTPUT_DIR:"
echo ${OUTPUT_DIR}
echo "-----------------------"
echo "End of variable list"
echo "-----------------------"

# Now let's keep track of some information just in case anything goes wrong
echo "=========================================================="
#Use to calculate job time:
#Start_Time in seconds
Start_Time=$(date +"%s")
echo "Starting on : $(date)"
echo "Running on node : $(hostname)"
echo "Current directory : $(pwd)"
echo "Current job ID : $JOB_ID"
echo "Current job name : $JOB_NAME"
echo "Task index number : $SGE_TASK_ID"
echo "Parameter for multiple cores : $NSLOTS"
echo "=========================================================="

# Go to local scratch directory
echo
echo 'Change dir to scratch directory'
echo
cd ${TMPDIR}
echo
echo 'Print scratch directory location:'
echo
echo $TMPDIR
#--------------------------------------
echo
echo 'Loading required modules...'
echo
#Make sure the shebang line = #!/bin/bash -l
#Need the -l option to load modules
#Search for latest program installed:
#module avail -t 2>&1 | grep -i fastqc
#fastqc/0.10.1
#fastqc/0.11.2
#Load module:
module load fastqc/0.11.2
#module help FASTX-Toolkit/0.0.13.2
#---------------------------------------------------------------------------------
#----------- Module Specific Help for 'FASTX-Toolkit/0.0.13.2' ---------------------------
#FASTX-Toolkit 0.0.13.2: Commandline tools for short-read FASTA/FASTQ file preprocessing
#FASTX-Toolkit is a collection of command line tools for Short-Reads FASTA/FASTQ files preprocessing.
#For more information on FASTX-Toolkit, please see http://hannonlab.cshl.edu/fastx_toolkit/
#---------------------------------------------------------------------------------

#-----------------------------------------------------
# copy user input data files to scratch
#Copy over the *R1*.fastq.gz file(s):
cp ${Dataset_DIR}/${Sample_ID}/fastq/*R1*.fastq.gz .
#Copy over the *R2*.fastq.gz file(s):
cp ${Dataset_DIR}/${Sample_ID}/fastq/*R2*.fastq.gz .
#-----------------------------------------------------

#Create FASTQC output folder to store files:
FASTQC_DIR=${Sample_ID}'_FASTQC'
###############################
if [ ! -d $FASTQC_DIR ]; then
mkdir $FASTQC_DIR
fi
###############################

echo
echo 'List files in scratch directory:'
echo
ls -alh

echo
echo 'Starting to run my commands'
echo

echo
echo 'Unzip files:'
echo

time gzip -d *.gz

echo
echo 'Finished unzipping'
echo


echo
echo 'Print first 20 lines of FASTQ file:'
echo

head -20 *.fastq

echo
echo 'Starting FASTQC command'
echo

#--------------------------------------------------------------------------------
#fastqc --help

#            FastQC - A high throughput sequence QC analysis tool

#SYNOPSIS

#	fastqc seqfile1 seqfile2 .. seqfileN

#    fastqc [-o output dir] [--(no)extract] [-f fastq|bam|sam] 
#           [-c contaminant file] seqfile1 .. seqfileN

#DESCRIPTION

#    FastQC reads a set of sequence files and produces from each one a quality
#    control report consisting of a number of different modules, each one of 
#    which will help to identify a different potential type of problem in your
#    data.
#    
#    If no files to process are specified on the command line then the program
#    will start as an interactive graphical application.  If files are provided
#    on the command line then the program will run with no user interaction
#    required.  In this mode it is suitable for inclusion into a standardised
#    analysis pipeline.
#    
#    The options for the program as as follows:
#    
#    -h --help       Print this help file and exit
#    
#    -v --version    Print the version of the program and exit
#    
#    -o --outdir     Create all output files in the specified output directory.
#                    Please note that this directory must exist as the program
#                    will not create it.  If this option is not set then the 
#                    output file for each sequence file is created in the same
#                    directory as the sequence file which was processed.
#                    
#    --casava        Files come from raw casava output. Files in the same sample
#                    group (differing only by the group number) will be analysed
#                    as a set rather than individually. Sequences with the filter
#                    flag set in the header will be excluded from the analysis.
#                    Files must have the same names given to them by casava
#                    (including being gzipped and ending with .gz) otherwise they
#                    won't be grouped together correctly.
#                    
#    --nofilter      If running with --casava then don't remove read flagged by
#                    casava as poor quality when performing the QC analysis.
#                   
#    --extract       If set then the zipped output file will be uncompressed in
#                    the same directory after it has been created.  By default
#                    this option will be set if fastqc is run in non-interactive
#                    mode.
#                    
#    -j --java       Provides the full path to the java binary you want to use to
#                    launch fastqc. If not supplied then java is assumed to be in
#                    your path.
#                   
#    --noextract     Do not uncompress the output file after creating it.  You
#                    should set this option if you do not wish to uncompress
#                    the output when running in non-interactive mode.
#                    
#    --nogroup       Disable grouping of bases for reads >50bp. All reports will
#                    show data for every base in the read.  WARNING: Using this
#                    option will cause fastqc to crash and burn if you use it on
#                    really long reads, and your plots may end up a ridiculous size.
#                    You have been warned!
#                    
#    -f --format     Bypasses the normal sequence file format detection and
#                    forces the program to use the specified format.  Valid
#                    formats are bam,sam,bam_mapped,sam_mapped and fastq
#                    
#    -t --threads    Specifies the number of files which can be processed
#                    simultaneously.  Each thread will be allocated 250MB of
#                    memory so you shouldn't run more threads than your
#                    available memory will cope with, and not more than
#                    6 threads on a 32 bit machine
#                  
#    -c              Specifies a non-default file which contains the list of
#    --contaminants  contaminants to screen overrepresented sequences against.
#                    The file must contain sets of named contaminants in the
#                    form name[tab]sequence.  Lines prefixed with a hash will
#                    be ignored.

#    -a              Specifies a non-default file which contains the list of
#    --adapters      adapter sequences which will be explicity searched against
#                    the library. The file must contain sets of named adapters
#                    in the form name[tab]sequence.  Lines prefixed with a hash
#                    will be ignored.
#                    
#    -l              Specifies a non-default file which contains a set of criteria
#    --limits        which will be used to determine the warn/error limits for the
#                    various modules.  This file can also be used to selectively 
#                    remove some modules from the output all together.  The format
#                    needs to mirror the default limits.txt file found in the
#                    Configuration folder.
#                    
#   -k --kmers       Specifies the length of Kmer to look for in the Kmer content
#                    module. Specified Kmer length must be between 2 and 10. Default
#                    length is 7 if not specified.
#                    
#   -q --quiet       Supress all progress messages on stdout and only report errors.
#   
#   -d --dir         Selects a directory to be used for temporary files written when
#                    generating report images. Defaults to system temp directory if
#                    not specified.
#                    
#BUGS

#    Any bugs in fastqc should be reported either to simon.andrews@babraham.ac.uk
#    or in www.bioinformatics.babraham.ac.uk/bugzilla/
#--------------------------------------------------------------------------------
#Run the command for each fastq file:
FASTQ_LIST=*.fastq
for FASTQ_FILE in ${FASTQ_LIST}
do
echo
echo "Processing "${FASTQ_FILE}
echo
echo 'Printing command:'
echo "fastqc --outdir ${FASTQ_FILE}"
echo
#Run command:
fastqc --outdir $FASTQC_DIR ${FASTQ_FILE}
done
#--------------------------------------------------------------------------------
echo
echo 'Finished FASTQC command'
echo

echo
echo 'Copy output to storage dir'
echo
cp -r $FASTQC_DIR $OUTPUT_DIR

echo
echo "List files in scratch"
echo
ls -alh

echo "=========================================================="
echo "Finished on : $(date)"
#Use to calculate job time:
#End_Time in seconds
End_Time=$(date +"%s")
diff=$(($End_Time-$Start_Time))
echo "$(($diff / 3600)) hours, $((($diff / 60) % 60)) minutes and $(($diff % 60)) seconds elapsed."
echo "=========================================================="