-
Notifications
You must be signed in to change notification settings - Fork 0
/
alkati_subsampling_simulations.Rmd
159 lines (137 loc) · 5.29 KB
/
alkati_subsampling_simulations.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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
---
title: "alkati_subsampling_simulations"
author: "Haider Inam"
date: "1/31/2019"
output: html_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_knit$set(root.dir = "..")
library(knitr)
library(tictoc)
library(workflowr)
library(VennDiagram)
library(dplyr)
library(foreach)
library(doParallel)
library(ggplot2)
library(reshape2)
library(RColorBrewer)
library(devtools)
library(ggsignif)
source("code/contab_maker.R")
source("code/alldata_compiler.R")
source("code/quadratic_solver.R")
source("code/mut_excl_genes_generator.R")
source("code/mut_excl_genes_datapoints.R")
source("code/simresults_generator.R")
######################Cleanup for GGPlot2#########################################
cleanup=theme_bw() +
theme(plot.title = element_text(hjust=.5),
panel.grid.major = element_blank(),
panel.grid.major.y = element_blank(),
panel.background = element_blank(),
axis.line = element_line(color = "black"))
```
Just want to make quick P-value distribution plots for Figure 1C.
This is a tiny bit more tricky than previously because right now, my simresults_generator does not look at a bunch of subsample sizes
```{r}
nsubsamples=12 # maybe this can be removed and instead calculated later.
nsims<-100 #
#Positive control 1
nameposctrl1<-'BRAF'
#Positive control 1
nameposctrl2<-'NRAS'
#Oncogene in Question
namegene<-'ATI'
#Mutation Boolean (Y or N)
mtn<-'N'
#Name Mutation for Positive Ctrl 1
nameposctrl1mt<-'V600E'
#Name of Mutation for Positive Ctrl 2
nameposctrl2mt<-'Q61L'
alldata=read.csv("data/All_Data_V2.csv",sep=",",header=T,stringsAsFactors=F)
nexperiments=7
alldata_comp=alldata_compiler(alldata,nameposctrl1,nameposctrl2,namegene,mtn,"N/A","N/A")[[2]]
genex_replication_prop=alldata_compiler(alldata,nameposctrl1,nameposctrl2,namegene,mtn,"N/A","N/A")[[1]]
simresults_comb=data.frame()
for(subsample_number in c(1:12)){
nsubsamples=subsample_number
simresults=simresults_generator(alldata_comp,7)
simresults_comb=rbind(simresults_comb,simresults) ##ik this is not a good way to do this but whatever
}
```
```{r}
simresults_concat=simresults_comb%>%
filter(exp_num%in%c(4))
# simresults_concat=simresults_comb
ggplot(simresults_concat,aes(x=factor(subsample_size),y=-log10(p_val)))+
geom_boxplot(aes(fill=factor(exp_num)))+
cleanup+
guides(fill=F)+
scale_y_continuous(name="-log(P-Value)")+
scale_x_discrete(name="Subsample size")+
# scale_color_manual(values="#E78AC3")+
theme(plot.title = element_text(hjust=.5),
text = element_text(size=26,face="bold"),
axis.title = element_text(face="bold",size="26",color="black"),
axis.text=element_text(face="bold",size="24",color="black"))
# ggsave("alkati_subsamplesize_pval_fig1c.pdf",width = 10,height = 10,units = "in",useDingbats=F)
```
Doing simulations with mutations
```{r}
nsubsamples=12 # maybe this can be removed and instead calculated later.
nsims<-100 #
#Positive control 1
nameposctrl1<-'BRAF'
#Positive control 1
nameposctrl2<-'NRAS'
#Oncogene in Question
namegene<-'ATI'
#Mutation Boolean (Y or N)
mtn<-'Y'
#Name Mutation for Positive Ctrl 1
nameposctrl1mt<-'V600E'
#Name of Mutation for Positive Ctrl 2
nameposctrl2mt<-'Q61L'
alldata=read.csv("data/All_Data_V2.csv",sep=",",header=T,stringsAsFactors=F)
nexperiments=7
###For mutation
alldata_comp=alldata_compiler(alldata,nameposctrl1,nameposctrl2,namegene,mtn,nameposctrl1mt,nameposctrl2mt)[[2]]
genex_replication_prop=alldata_compiler(alldata,nameposctrl1,nameposctrl2,namegene,mtn,nameposctrl1mt,nameposctrl2mt)[[1]]
simresults=simresults_generator(alldata_comp,7)
simresults$mtn='Y'
####For no mutation
mtn='N'
alldata_comp=alldata_compiler(alldata,nameposctrl1,nameposctrl2,namegene,mtn,"N/A","N/A")[[2]]
genex_replication_prop=alldata_compiler(alldata,nameposctrl1,nameposctrl2,namegene,mtn,"N/A","N/A")[[1]]
simresults_nomtn=simresults_generator(alldata_comp,7)
simresults_nomtn$mtn='N'
simresults=rbind(simresults,simresults_nomtn)
```
Now doing the p-values for Figure 2b. Will show ati vs braf, ati vs nras, and mutations
```{r}
simresults[simresults$exp_num==1,]$exp_name="BRAF & ALKATI"
simresults[simresults$exp_num==3,]$exp_name="NRAS & ALKATI"
simresults[simresults$exp_num==4,]$exp_name="BRAF & NRAS"
simresults$exp_name=factor(simresults$exp_name,levels=c("1","5","6","7","BRAF & ALKATI","NRAS & ALKATI","BRAF & NRAS"))
simresults$mtn_tag='N'
simresults[simresults$mtn=='Y',]$mtn_tag="Mutation-specific"
simresults[simresults$mtn=='N',]$mtn_tag="Non mutation-specific"
simresults$mtn_tag=factor(simresults$mtn_tag,levels=c("Non mutation-specific","Mutation-specific"))
simresults_concat=simresults%>%
filter(exp_num==c(1,3,4))
ggplot(simresults_concat,aes(x=factor(exp_name),y=-log10(p_val)))+
geom_boxplot(aes(fill=factor(exp_name)))+
facet_wrap(~factor(mtn_tag))+
cleanup+
guides(fill=F)+
scale_y_continuous(name="-log(P-Value)")+
scale_x_discrete(name="Gene Pair")+
scale_fill_brewer(palette = "Set2",name="Gene Pair")+
theme(plot.title = element_text(hjust=.5),
text = element_text(size=26,face="bold"),
axis.title = element_text(face="bold",size="26",color="black"),
axis.text=element_text(face="bold",size="20",color="black"))
ggsave("output/alkati_mtn_pval_fig2B.pdf",width = 16,height = 10,units = "in",useDingbats=F)
```