/
pQTLexampleplot.Rmd
94 lines (54 loc) · 3.02 KB
/
pQTLexampleplot.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
---
title: "pQTL not eQTL example"
author: "Briana Mittleman"
date: "6/27/2019"
output: html_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
```{r}
library(tidyverse)
```
Protien specific qtl example
```{r}
totQTL=read.table("../data/apaQTLs/Total_apaQTLs4pc_5fdr.txt", header = T, stringsAsFactors = F)
nucQTL=read.table("../data/apaQTLs/Nuclear_apaQTLs4pc_5fdr.txt", stringsAsFactors = F, header = T)
```
rs9820529
peak93951
```{r}
genohead=as.data.frame(read.table("../data/ExampleQTLPlots/genotypeHeader.txt", stringsAsFactors = F, header = F)[,10:128] %>% t())
colnames(genohead)=c("header")
genotype=as.data.frame(read.table("../data/ExampleQTLPlots/EIF2A_TotalPeaksGenotype.txt", stringsAsFactors = F, header = F) [,10:128] %>% t())
full_geno=bind_cols(Ind=genohead$header, dose=genotype$V1) %>% mutate(numdose=round(dose), genotype=ifelse(numdose==0, "TT", ifelse(numdose==1, "TA", "AA")))
RNAhead=as.data.frame(read.table("../data/molPhenos/RNAhead.txt", stringsAsFactors = F, header = F)[,5:73] %>% t())
RNApheno=as.data.frame(read.table("../data/molPhenos/RNA_EIF2a.txt", stringsAsFactors = F, header = F) [,5:73] %>% t())
full_pheno=bind_cols(Ind=RNAhead$V1, Expression=RNApheno$V1)
allRNA=full_geno %>% inner_join(full_pheno, by="Ind")
allRNA$genotype=as.factor(allRNA$genotype)
ggplot(allRNA, aes(x=genotype, y=Expression,group=genotype, fill=genotype)) + geom_boxplot() + geom_jitter()+scale_fill_brewer(palette = "Dark2") + labs(title="eQTL: EIF2A - rs9820529") + theme(legend.position = "bottom")
```
```{r}
prothead=as.data.frame(read.table("../data/molPhenos/ProtHead.txt", stringsAsFactors = F, header = F)[,5:66] %>% t())
protpheno=as.data.frame(read.table("../data/molPhenos/prot_EIF2A.txt", stringsAsFactors = F, header = F) [,5:66] %>% t())
full_phenoprot=bind_cols(Ind=prothead$V1, Expression=protpheno$V1)
allprot=full_geno %>% inner_join(full_phenoprot, by="Ind")
allprot$genotype=as.factor(allprot$genotype)
ggplot(allprot, aes(x=genotype, y=Expression,group=genotype, fill=genotype)) + geom_boxplot() + geom_jitter()+scale_fill_brewer(palette = "Dark2") + labs(title="pQTL: EIF2A - rs9820529", y="Protein Level")+ theme(legend.position = "bottom")
```
Broader: Ask how many examples:
Ask for apaQTLs sig in P not in E
```{bash,eval=F}
mkdir ../data/pQTLoverlap
python apaInPandE.py
```
```{r}
apaQTL=read.table("../data/apaQTLs/Nuclear_apaQTLs4pc_5fdr.txt", stringsAsFactors = F, header = T)
apainE=read.table("../data/pQTLoverlap/NucAPAinExpression.txt", stringsAsFactors = F, col.names = c("Gene", 'sid','dist', 'Exppval', 'Eslope')) %>% select(Gene, sid, Exppval,Eslope)
apainP=read.table("../data/pQTLoverlap/NucAPAinProt.txt", stringsAsFactors = F, col.names = c("Gene", 'sid','dist', 'Protppval', 'Pslope')) %>% select(Gene, sid, Protppval ,Pslope)
#combine
allQTL=apaQTL %>% inner_join(apainE,by=c("Gene", "sid")) %>% inner_join(apainP, by=c("Gene","sid"))
#select sig in p not e
pnote=allQTL %>% filter(Exppval>.05) %>% filter(Protppval<.05) %>% select(Gene, sid) %>% unique()
```