baf3_alkati_transformations

Please not that while we performed a total of 48 ALKATI transductions, we only counted the first 9 transductions.

library(ggplot2)
library(reshape2)
library(Hmisc)

Loading required package: lattice

Loading required package: survival

Loading required package: Formula

Attaching package: 'Hmisc'

The following objects are masked from 'package:dplyr':

    src, summarize

The following objects are masked from 'package:base':

    format.pval, units

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"))

# setwd("../Box/AlkAti/figures/baf3transformationsfigure/")

baf3data=read.table("data/alkati_growthcurvedata_popdoublings.csv",header=T,stringsAsFactors = F,sep = ",")
###Removing 7th march data because the cells grew a lot in the first day post selection
baf3data=baf3data[!grepl("7-Mar",baf3data$Infection),]
baf3data=baf3data[,c(1:11)]
###If you want only eml4alk and alk ati data, do this:
# baf3data=baf3data[,c(1:8)]

#
baf3data2=melt(baf3data,id.vars = c("Time","Infection"))

baf3data2=baf3data2 %>%
  filter(value>=-10)


baf3data2=na.omit(baf3data2)

baf3data2$variable=as.character(baf3data2$variable)
###Transforming counts into actual numbers because these counts represent x1000s
# baf3data2$value=baf3data2$value*1000
###Creating a boolean for Type of infection
baf3data2$type="EML4ALK"
baf3data2$type[grep("alkati",baf3data2$variable,ignore.case = T)]="ALKATI"
baf3data2$type[grep("vector",baf3data2$variable,ignore.case = T)]="VECTOR"
#
#

ggplot(baf3data2,aes(x=Time,y=value,color=type,fill=Infection,shape=variable))+
  geom_line(size=3)+
  geom_point(size=5,shape=16)+
  # scale_y_continuous(limits = c(1,1e8))+
  ggtitle("ALK-ATI sporadically promotes growth-factor-independent proliferation")+
  xlab("Days after Transduction")+
  ylab("Number of Cell Doublings")+
  cleanup+
  theme(plot.title = element_text(hjust=.5),
        text = element_text(size=24,face = "bold"),
        axis.title = element_text(face="bold",size="24"),
        axis.text=element_text(face="bold",size="24"))+
  theme(legend.position="none")+
  xlim(0,14)+
  scale_colour_brewer(palette="Set2")

Warning: The shape palette can deal with a maximum of 6 discrete values
because more than 6 becomes difficult to discriminate; you have 9.
Consider specifying shapes manually if you must have them.

Warning: Removed 1 rows containing missing values (geom_path).

Warning: Removed 1 rows containing missing values (geom_point).

#Can also make your own palette and color manually. Obtained from http://www.cookbook-r.com/Graphs/Colors_(ggplot2)/
ggsave("output/baf3_alkati_figure_deltaadjusted_doublings.pdf",width = 16, height = 12, units = "in")

Warning: The shape palette can deal with a maximum of 6 discrete values
because more than 6 becomes difficult to discriminate; you have 9.
Consider specifying shapes manually if you must have them.

Warning: Removed 1 rows containing missing values (geom_path).

Warning: Removed 1 rows containing missing values (geom_point).

# Mean and standard deviation to grow out:
#Our criteria for cells "growing out" was when they reached two population doublings
#I extracted the number of days it took for ALKATI and EML4ALK samples to reach 2 population doublings by looking at the data of cells growing out.
head(baf3data2)

  Time Infection variable     value   type
1  1.0    24-Nov  ALKATI1 0.0000000 ALKATI
2  2.0    24-Nov  ALKATI1 0.6918777 ALKATI
3  3.5    24-Nov  ALKATI1 0.9142701 ALKATI
4  5.0    24-Nov  ALKATI1 0.7589919 ALKATI
5  6.0    24-Nov  ALKATI1 0.4694853 ALKATI
6  9.0    24-Nov  ALKATI1 2.8387191 ALKATI

#ALKATI grew out in 9,10, and 11 days.
mean(c(9,10,11))

[1] 10

sd(c(9,10,11))

[1] 1

#Eml4ALK grew out in 6,6,6,6,6, and 5 days
mean(c(6,6,6,6,6,10))

[1] 6.666667

sd(c(6,6,6,6,6,5))

[1] 0.4082483

Another way of displaying Fig 4a using unn

##################Baf3 figure based on raw numbers  
baf3data=read.table("data/alkati_growthcurvedata.csv",header=T,stringsAsFactors = F,sep = ",")
# ###Removing 7th march data because the cells grew a lot in the first day post selection
baf3data=baf3data[!grepl("7-Mar",baf3data$Infection),]
baf3data=baf3data[,c(1:11)]
# ###If you want only eml4alk and alk ati data, do this:
# # baf3data=baf3data[,c(1:8)]
# 
# 
baf3data2=melt(baf3data,id.vars = c("Time","Infection"))
baf3data2=na.omit(baf3data2)
baf3data2$variable=as.character(baf3data2$variable)
# ###Transforming counts into actual numbers because these counts represent x1000s
baf3data2$value=baf3data2$value*1000
# ###Creating a boolean for Type of infection
baf3data2$type="EML4ALK"
baf3data2$type[grep("alkati",baf3data2$variable,ignore.case = T)]="ALKATI"
baf3data2$type[grep("vector",baf3data2$variable,ignore.case = T)]="VECTOR"
# ###We will use the log2 ratio of the starting population to the pop of interest to get the number of doubling of a population
# ###These are called pseudo counts
# ###To avoid the problem of undefined regions when the populations go to 0, we have 
ggplot(baf3data2,aes(x=Time,y=value,color=type,fill=Infection,shape=variable))+
  geom_line(size=3)+
  geom_point(size=5,shape=16)+
  scale_y_continuous(trans = "log10")+
  ggtitle("ALK-ATI sporadically promotes growth-factor-independent proliferation")+
  xlab("Days after Transduction")+
  ylab(expression(paste(~Delta,"Cell Number (", ~10^6, ")")))+
  cleanup+
  theme(plot.title = element_text(hjust=.5),
       text = element_text(size=24,face = "bold"),
       axis.title = element_text(face="bold",size="24"),
       axis.text=element_text(face="bold",size="24"))+
  theme(legend.position="none")

Warning: The shape palette can deal with a maximum of 6 discrete values
because more than 6 becomes difficult to discriminate; you have 9.
Consider specifying shapes manually if you must have them.