crazyhottommy

```r
library(TxDb.Hsapiens.UCSC.hg19.knownGene)
UCSC.hg19<- TxDb.Hsapiens.UCSC.hg19.knownGene
hg19.genes<- genes(UCSC.hg19)
transcriptsBy(UCSC.hg19, "gene")

library("org.Hs.eg.db")

## note that dplyr and AnnotationDbi both have a function called select
## use dplyr::select when use dplyr

crazyhottommy

### Define intronic, exonic and intergenic regions

```{r}
library(AnnotationHub)
library(dplyr) ## for %>%
ah = AnnotationHub()
possibleDates(ah)
AnnotationHub::query(ah, c("gtf", "Homo_sapiens", "GRCh37"))

GRCh37.gtf<- ah[['AH10684']]

crazyhottommy

A dummy example for testing

cat DATA.tsv 
ID	head1	head2	head3	head4
1	25.5	1364.0	22.5	13.2
2	10.1	215.56	1.15	22.2

cat LIST.TXT 
ID

crazyhottommy

#! /bin/bash

set -e
set -u
set -o pipefail

#### Author: Ming Tang (Tommy)
#### Date 09/29/2016
#### I got the idea from this stackOverflow post http://stackoverflow.com/questions/11098189/awk-extract-columns-from-file-based-on-header-selected-from-2nd-file

crazyhottommy

Make a heatmap with colored dendrogram by `complexHeatmap` and `Dendsort`.
See help [here](https://bioconductor.org/packages/release/bioc/vignettes/ComplexHeatmap/inst/doc/s2.single_heatmap.html)
```r
##### a make_hc function to receive different distance_measure and linkage_method
make_hc<- function(x, distance_measure, linkage_method){
        if (distance_measure == "pearson"){
                ## cor calculate for columns, needs to transpose x first
                distance <- as.dist(1-cor(t(x), method = "pearson"))
                hc<- hclust(distance, method = linkage_method)

crazyhottommy

## devtools::install_github("stephenturner/msigdf")
library(msigdf)
library(dplyr)
library(clusterProfiler)

c2 <- msigdf.human %>% 
    filter(collection == "c2") %>% select(geneset, entrez) %>% as.data.frame

data(geneList)
de <- names(geneList)[1:100]

crazyhottommy

---
title: "lncRNA_heatmap"
author: "Ming Tang"
date: "July 28, 2016"
output: html_document
---

Read in the bigwig files for each mark. bigwig files were generated by Deeptools from bam files.
```{r}
library(EnrichedHeatmap)

crazyhottommy

get rid of the digits (gene version) in the end for the gene names (gencode v19)

cat STAR_WT-30393468_htseq.cnt| sed -E 's/\.[0-9]+//' > WT_htseq.cnt

transcript to gene mapping file:

library(EnsDb.Hsapiens.v75)

crazyhottommy

aDict = {"B":"inputG1", "A":"inputG1", "C":"inputG2"}

rule all:
	input: ["C.bed", "A.bed", "B.bed"]

def get_files(wildcards):
	case = wildcards.case
	control = aDict[case]
	return [case + ".sorted.bam", control + ".sorted.bam"]

crazyhottommy

## http://stackoverflow.com/questions/19876505/boxplot-show-the-value-of-mean
## plot adding mean value
ggplot(NLR.tidy, aes(x=NLR, y=ratio_value, color= NLR,fill= NLR)) + 
        geom_point(position=position_jitterdodge(dodge.width=0.9)) +
        geom_boxplot(fill="white", alpha=0.1, outlier.colour = NA, 
                     position = position_dodge(width=0.9)) + 
        coord_cartesian(ylim = c(-0.5, 15)) +
        stat_summary(fun.y = mean, geom="point",colour="black", size=3, show.legend = FALSE) +
        stat_summary(fun.y=mean, colour="red", geom="text", show.legend =FALSE, 
                       vjust=-0.7, aes( label=round(..y.., digits=1)))