########################################################################
#
# RNA-seq sequencing project specific information
#
#######################################################################

RUN_STAR=y
RUN_FEATURECOUNTS=y
RUN_SNPCALL=y
RUN_RSEM=y
RUN_SALMON=n
RUN_KALLISTO=n

# !!!!!!
# Species: human, mouse, rat and etc
SAMPLE_SPECIES=mouse

# !!!!!!
# Directory for FASTQ files. This parameter MUST be changed
# every time when you analyze a new project/dataset
FASTQ_DIR=/camhpc/ngs/projects/GEO/Stefka/TST10345_TST11079

# !!!!!!
# stranded or nonstranded. #0: nonstranded;  1: forward strandness;  2: reverse strandness
# For Illumina true mRNA-seq, this parameter is usually set to 2
STRAND=0

# !!!!!!
# If you don't have an annotation, please comment the next line
# If you do, please make sure coulmn #1 and #2 correponding to
# Sample_ID and Subject_ID, respectively.
SAMPLE_ANNOTATION=sample.annotation.txt

# Suffix for fastq:  fq.gz or fastq.gz or fastq  or fq
FASTQ_SUFFIX=fastq.gz

# Select the algorithm for quantification:  RSEM, KALLISTO, SALMON_ALN, SALMON
# You can set this papareter to ALL if you want to run all algorithms. 
# SALMON_ALN is generally recommeded. KALLISTO and RSEM also work great.
#
#ISOFORM_ALGORITHM=SALMON_ALN
#ISOFORM_ALGORITHM=ALL
ISOFORM_ALGORITHM=RSEM
#ISOFORM_ALGORITHM=KALLISTO
#ISOFORM_ALGORITHM=SALMON

# sequencing type: pair or single
SEQUENCE_TYPE=pair

# sequencing depth #regular: 40-80M; #deep: >80M, or encounter issues with STAR run due to BAM sorting
SEQUENCE_DEPTH=regular

#log directory
LOGDIR=/camhpc/ngs/projects/TST10345_TST11079/analysis/log
mkdir -p $LOGDIR



#######################################################################
#
##Software specific parameters
##Usually, you DON'T need to modify them unless you understand the
##impacts of these parameters
#
#######################################################################
STAR_PARAMETER="--alignSJDBoverhangMin 1 --outFilterMismatchNoverLmax 0.05 --alignIntronMax 1000000"
FEATURECOUNTS_OVERLAP="--minOverlap 25"
VARSCAN_PARAMETER="--min-coverage 20 --min-reads2 4"

RSEM_PARAMETER="--seed 12345 --quiet --time  --no-bam-output --bam"
SALMON_ALN_PARAMETER=" --incompatPrior 0 "
SALMON_PARAMETER=" --incompatPrior 0  --validateMappings "
KALLISTO_PARAMETER=" "



# change 100 to 150 for read length > 100
STAR_INDEX=/camhpc/ngs/genomes/mouse/gencode.vM16/STAR_100
RSEM_INDEX=/camhpc/ngs/genomes/mouse/gencode.vM16/rsem/rsem

GENOME_FASTA=/camhpc/ngs/genomes/mouse/gencode.vM16/fasta/GRCm38.primary.genome.fa
TRANSCRIPT_FASTA=/camhpc/ngs/genomes/mouse/gencode.vM16/fasta/gencode.vM16.transcripts.polish.fa
GTF_FILE=/camhpc/ngs/genomes/mouse/gencode.vM16/annotation/gencode.vM16.gtf
GENE_ANNOTATION=/camhpc/ngs/genomes/mouse/gencode.vM16/annotation/gencode.vM16.gene.annot
TRANSCRIPT_ANNOTATION=/camhpc/ngs/genomes/mouse/gencode.vM16/annotation/gencode.vM16.transcripts.annot
# HLA region for the most SNPs, it is orgnism specific
CHR_REGION=chr17:1-94987271

# tools
module purge
module load STAR/2.5.2a
module load rsem/1.2.26
module load subread/1.5.0-p1
module load bowtie/1.2.2
module load samtools/1.9
module load R/3.5.1
module load pandoc/2.1.1
module load varscan/2.4.2
VARSCAN_JAR=/camhpc/pkg/varscan/2.4.2/centos6/varscan.jar

export QuickIsoSeq=/camhpc/ngs/tools/pipelines/QuickIsoSeq
export SCRIPTPATH=/camhpc/ngs/tools/pipelines/QuickIsoSeq/QuickIsoSeq_html
export PATH=$QuickIsoSeq:$SCRIPTPATH:$PATH