arq5x

library(ggplot2)
library(gridExtra)
cov <- read.table("/Users/arq5x/Documents/Projects/HallLab/TCGA-1KG/ForKeystone/tcga_and_1kg_span_cov.txt",header=TRUE)
span <- qplot(sample, span_cov, data=cov, fill=factor(type_num), geom="bar", 
             binwidth=1, 
             xlab="Sample", 
             ylab="Spanning coverage") +
        opts(axis.ticks = theme_blank(), 
             axis.text.x = theme_blank(), 
             axis.title.x = theme_text(size = 18, face = "bold"), 

arq5x

export BATCH1="1094PC0005 1094PC0009 1094PC0012 1094PC0013 "
export BATCH2="1094PC0016 1094PC0017 1094PC0018 1094PC0019 \
               1094PC0020 1094PC0021 1094PC0022 1094PC0023 1094PC0025 "
export BATCH3="1478PC0001B 1478PC0002 1478PC0003 1478PC0004 \
               1478PC0005 1478PC0006B 1478PC0007B 1478PC0008B \
               1478PC0009B 1478PC0010 1478PC0011 1478PC0012 \
               1478PC0013B 1478PC0014B 1478PC0015B 1478PC0016 \
               1478PC0017B 1478PC0018 1478PC0019 1478PC0020 \
               1478PC0021 1478PC0022B 1478PC0023B 1478PC0024B"
export BATCH4="1719PC0001 1719PC0002 1719PC0003 1719PC0004 \

arq5x

############################################################
# Pair the alignments.
# Keep proper, on-target (i.e. +/- 500 bp of a probe) pairs.
# Require mapping quality >= 20
############################################################
export DIR=/home/arq5x/cphg-home/projects/t1d/t1d-exome-suna/
export STEPNAME=t1d-ex-bwa-par
export GENOME=/home/arq5x/cphg-home/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa

arq5x

export GENOME=hg19
export SNPBUILD=131
curl -s http://hgdownload.cse.ucsc.edu/goldenPath/$GENOME/database/snp$SNPBUILD.txt.gz | \
        zcat | \
        cut -f 2,3,4,5,6,7,10,16 > dbsnp.$SNPBUILD.$GENOME.bed

head dbsnp.$SNPBUILD.$GENOME.bed
chr1	10433	10433	rs56289060	0	+	-/C	near-gene-5
chr1	10491	10492	rs55998931	0	+	C/T	near-gene-5
chr1	10518	10519	rs62636508	0	+	C/G	near-gene-5

arq5x

# Step 1: Get transcripts from UCSC refGene (hg19) into a BED file.
# Notes:
#      the awk statement reorders the "raw" columns into BED12 format
#      bed12ToBed6 converts the BED12 into discrete BED6 entries for each exon
#           - the -n option is new and in the bedtools repository
$ curl -s http://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/refGene.txt.gz | \
      zcat | \
      awk '{OFS="\t"; print $3,$5,$6,$2,$9,$4,$7,$8,"0",$9,$10,$11}' | \
      bed12ToBed6 -n \
      > refGene.bed

arq5x

# Staring FASTQ files
export FQ1=1.fq
export FQ2=2.fq

# The names of the random subsets
export FQ1SUBSET=1.rand.fq
export FQ2SUBSET=2.rand.fq

# How many random pairs do we want?
export N=100

arq5x

###################################################################
# Assume we have a file of BED exons for every gene and transcript. 
# The exons are listed in genomic order for each gene/transcipt
###################################################################
$ head -n 5 exons.bed 
chr1	1337462	1337636	MRPL20	exon1	-
chr1	1340996	1341266	MRPL20	exon2	-
chr1	1341188	1341266	MRPL20	exon3	-
chr1	1342288	1342399	MRPL20	exon4	-
chr1	1342510	1342597	MRPL20	exon5	-

arq5x

void MultiCovBam::CollectCoverage()
{
    BamMultiReader reader;

    if ( !reader.Open(_bam_files) )
    {
        cerr << "Could not open input BAM files." << endl; return;
    }
    else
    {

arq5x

############################################################
# Index the position-sorted BAM files.
############################################################
export SAMPLES="T10AA T10AB T10D T10H"
export TUMHOME=/home/arq5x/cphg-home/projects/navin-tumor-heterogeneity/
export STEPNAME="bam-index"
for sample in `echo $SAMPLES`
do
export QSUB="qsub -q cphg -W group_list=CPHG -V -l select=1:mem=2000m:ncpus=1 -N $STEPNAME -m bea -M [email protected]"
      echo "cd $TUMHOME; samtools index bam/$sample.*.bam" | $QSUB

arq5x

########################################
# 1. Counting the discrete occurrences 
#    of a value in each column of a 
#    matrix. Store the count for each 
#    column in a new vector whose size
#    is the number of columns in the 
#    matrix. 
########################################
# make a 3x3 matrix with columns
# having 0, 1, and 2 zeros