mbk0asis

library(ggplot2)
library(ggpmisc)

p <- ggplot(df2,aes(log2(df2$high_mean),log2(df2$low_mean)), 
            xlab="log2(Setdb1_high)", ylab="log2(Setdb1_low)")

p + xlim(0,10) + ylim(0,10)+ theme_bw() + 
  geom_point(size=1,alpha=.3,col="black") +
  stat_density2d(aes(fill=..level..,alpha=..level..),geom='polygon',colour='grey50',bins=10, show.legend = F) + 
  scale_fill_continuous(low="yellow",high="red") +

mbk0asis

# gather "accepted_hits.bam" to one directory
$ find . -name "accepted_hits.bam" > bam_list
$ while read line; do cp $line  $(dirname $line).bam  ; done < bam_list


# rename bam files to shorten the names (e.g. SAMPLE.trim.cut.fq.gz.bam --> SAMPLE.bam)
$ rename 's/trim.cut.fq.gz.//g' *

mbk0asis

library(ggplot2)
All <- read.csv("~/00-NGS/RNAseq/bov/niceM/Sham_Corrected/TopHat_UMD3.1_NCBI/log10_log2_mean.csv")
colnames(All) = c("chr","MI","MN","FI","FN",
                  "log10_MN_MI","log10_FI_MI","log10_FN_MI",
                  "log2_MN_MI","log2_FI_MI","log2_FN_MI")
head(All)

# set chr in natural order
All$chr <- factor(All$chr, 
                  levels=c("1","2","3","4","5","6","7","8","9","10",

mbk0asis

chr         MI        MN        FI        FN log10_MN.MI log10_FI.MI log10_FN.MI log2_MN.MI log2_FI.MI  log2_FN.MI
1   4.274425  6.348213  5.055983  4.505403   0.1440066  0.06000955  0.01861402  0.4783797  0.1993474  0.06183444
1   0.000000  0.000000  0.000000  0.000000   0.0000000  0.00000000  0.00000000  0.0000000  0.0000000  0.00000000
1 147.443667 73.833702 99.568167 55.867500  -0.2974644 -0.16910114 -0.41669754 -0.9881555 -0.5617418 -1.38423925
1   5.123198  7.764905  3.524147  3.185655   0.1557689 -0.13144165 -0.16521490  0.5174530 -0.4366397 -0.54883201
1   1.217480  2.133620  1.641105  2.506605   0.1501866  0.07592596  0.19902714  0.4989091  0.2522206  0.66115384
1   8.494963  4.504353  7.199487  7.713527  -0.2367870 -0.06370663 -0.03729933 -0.7865893 -0.2116288 -0.12390568

mbk0asis

with(SCNT_TSA, plot(log2FoldChange,-log10(pval),pch=20,main="Volcano plot",
col=rgb(0.6,0.6,0.6, alpha = 0.1)))  

with(subset(SCNT_TSA, pval<.05 & abs(log2FoldChange)>1),
points(log2FoldChange,-log10(pval),pch=20,col=rgb(1,0.5,0, alpha = 0.4)))

abline(v=c(-1,1),col="blue",lwd=1,lty=5)
abline(v=c(0,0),col="grey40",lwd=1,lty=2)
abline(c(-log10(0.05),0),col="blue",lwd=1,lty=5)

mbk0asis

$ while read line; do echo $line | grep -o 'Any_Pattern' | wc -l; done < Input_File > Result_file

# Example
$ while read line; do echo $line | grep -o 'CG' | wc -l; done < Dlk1_mm10.txt > Dlk1_CpG_density

mbk0asis

library(cummeRbund)

# set working directory

setwd('/home/bio3/00-NGS/RNAseq/E-MTAB-3037_human_aging_fibroblasts/diffout')

# read cuffdiff results
cuff_data<-readCufflinks()   

# DEGs

mbk0asis

#############################################################################################
# Commands in GATK 4.0 drastically changed.

# to run 'MarkDuplicates', simply
$ /dir/to/gatk Markduplicates --INPUT test.bam --OUTPUT test.dedupped.bam [options]

# originally
$ picard-tools MarkDuplicates I=test.bam O=test.dedupped.bam [options]

mbk0asis

# change chr order vcf using 'VCF-TOOLS'
# to check and change order of vcf
$ cat variants.vcf | cut -f 1 | uniq 
$ vcf-sort -c variants.vcf > variants_sorted.vcf
$ cat variants.vcf | cut -f 1 | uniq 



# download chr fasta files

mbk0asis

# Files used here
All_COSMIC_Genes.fasta - mRNA sequences for all cancer genes (normal)
Pongo_abelii.Ensembl.PPYG2.cdna.all.fa - Orangutan mRNAs
CosmicCodingMuts.vcf  - mutation information
ID coversion file - Ensembl transcript ID and gene symbols from biomart ( e.g. mart_export.txt)


1. Select high frequency MUT cancer genes (cnt >= 10)
$ cat CosmicCodingMuts_SORTED.vcf | grep -v "#" | grep -v SNV | cut -f 1,2,4,5,8 | \
sed 's/;/\t/g' | cut -f 1,2,3,4,5,6,9,11 | sed 's/=/\t/g' | cut -f 1,2,3,4,6,8,10,12 | \