On 12-16-15 I gave a set of purified shRNA barcodes to Jennifer in the Sequencing Core. The barcodes were purified from genomic DNA taken from HCC1143 breast cancer cells as part of my lab’s Palbociclib modifier screen. We typically run each module on its’ own flow cell lane for sequencing. In this experiment we also tried combining purified barcodes for Module 1 with purified barcodes for Module 2 and running them both on the same lane i.e. multiplexing. This R markdown file shows an analyis of the data generated from that sequencing run and compares multiplexed to non-multiplexed results.

setwd("Z:/Dr. Ethier Lab/Steve G/Data/Negative Selection Screens/Palbociclib Modifier Screen")
M1T3norm <- read.csv(file = "Output Lane 2.csv", header=T)
M1T3normP <- read.csv(file = "Output Lane 3.csv", header=T)
M2T3norm <- read.csv(file = "Output Lane 5.csv", header=T)
M2T3normP <- read.csv(file = "Output Lane 6.csv", header=T)
setwd("Z:/Dr. Ethier Lab/Steve G/Data/Negative Selection Screens/Palbociclib Modifier Screen/SG_Multiplex_Analysis")
M1T3multi <- read.csv(file = "Lane7_ModI_Library_Output.csv", header=T)
M1T3multiP <- read.csv(file = "Lane8_ModI_Library_Output.csv", header=T)
M2T3multi <- read.csv(file = "Lane7_ModII_Library_Output.csv", header=T)
M2T3multiP <- read.csv(file = "Lane8_ModII_Library_Output.csv", header=T)
M1T3norm <- M1T3norm[,c(4,19)]
M1T3normP <- M1T3normP[,c(4,19)]
M1T3multi <- M1T3multi[,c(4,19)]
M1T3multiP <- M1T3multiP[,c(4,19)]
M2T3norm <- M2T3norm[,c(4,19)]
M2T3normP <- M2T3normP[,c(4,19)]
M2T3multi <- M2T3multi[,c(4,19)]
M2T3multiP <- M2T3multiP[,c(4,19)]

Comparing the mean read counts for nonmultiplexed versus multiplexed samples

## [1] 1086.2242  550.5176
## [1] 1016.2419  528.8292
## [1] 956.6671 482.7992
## [1] 1047.8336  498.3206

Comparing reads in normal versus multiplexed

library(ggplot2)
library(jsonlite)
library(plotly)
## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:graphics':
## 
##     layout
M1T3_compare <- merge(M1T3norm,M1T3multi, by="Cellecta.ID")
names(M1T3_compare)[2:3] <- c("M1T3_nonmultiplexed", "M1T3_multiplexed")
G1 <- ggplot(M1T3_compare, aes(x = M1T3_nonmultiplexed, y= M1T3_multiplexed)) + geom_point() + scale_x_continuous(limits=c(0, 20000)) + scale_y_continuous(limits=c(0, 20000))
(gg <- ggplotly(G1))

M1T3P_compare <- merge(M1T3normP,M1T3multiP, by="Cellecta.ID")
names(M1T3P_compare)[2:3] <- c("M1T3P_nonmultiplexed", "M1T3P_multiplexed")
G2 <- ggplot(M1T3P_compare, aes(x = M1T3P_nonmultiplexed, y = M1T3P_multiplexed)) + geom_point() + scale_x_continuous(limits=c(0, 20000)) + scale_y_continuous(limits=c(0, 20000))
(gg <- ggplotly(G2))

M2T3_compare <- merge(M2T3norm,M2T3multi, by="Cellecta.ID")
names(M2T3_compare)[2:3] <- c("M2T3_nonmultiplexed", "M2T3_multiplexed")
G3 <- ggplot(M2T3_compare, aes(x = M2T3_nonmultiplexed, y = M2T3_multiplexed)) + geom_point() + scale_x_continuous(limits=c(0, 10000)) + scale_y_continuous(limits=c(0, 10000))
(gg <- ggplotly(G3))

M2T3P_compare <- merge(M2T3normP,M2T3multiP, by="Cellecta.ID")
names(M2T3P_compare)[2:3] <- c("M2T3P_nonmultiplexed", "M2T3P_multiplexed")
G4 <- ggplot(M2T3P_compare, aes(x = M2T3P_nonmultiplexed, y = M2T3P_multiplexed)) + geom_point() + scale_x_continuous(limits=c(0, 20000)) + scale_y_continuous(limits=c(0, 20000))
(gg <- ggplotly(G4))

Calculating M1T3 fold depletion scores for comparison

M1T3normFDs <- merge(M1T3norm, M1T3normP, by="Cellecta.ID")
M1T3normFDs$FD <- M1T3normFDs[,2]/M1T3normFDs[,3]
M1T3multiFDs <- merge(M1T3multi, M1T3multiP, by="Cellecta.ID")
M1T3multiFDs$FD <- M1T3multiFDs[,2]/M1T3multiFDs[,3]
compareFDs <- merge(M1T3normFDs, M1T3multiFDs, by="Cellecta.ID")
G5 <- ggplot(compareFDs, aes(x= FD.x, y= FD.y)) + geom_point() + scale_x_continuous(limits=c(0,50)) + scale_y_continuous(limits=c(0,50))
(gg <- ggplotly(G5))

compareFDs$comp <- compareFDs$FD.x/compareFDs$FD.y
G6 <- ggplot(compareFDs, aes(x = mix1_NoIndex_L007_R1_001trimmed.Processed, y = compareFDs$comp)) + geom_point()
(gg <- ggplotly(G6))

G7 <- ggplot(compareFDs, aes(x = mix1_NoIndex_L007_R1_001trimmed.Processed, y = compareFDs$comp)) + geom_point() + geom_vline(xintercept = 150, colour = "red", size = 1)
(gg <- ggplotly(G7))

Calculating M2T3 fold depletion scores for comparison

M2T3normFDs <- merge(M2T3norm, M2T3normP, by="Cellecta.ID")
M2T3normFDs$FD <- M2T3normFDs[,2]/M2T3normFDs[,3]
M2T3multiFDs <- merge(M2T3multi, M2T3multiP, by="Cellecta.ID")
M2T3multiFDs$FD <- M2T3multiFDs[,2]/M2T3multiFDs[,3]
compareFDs <- merge(M2T3normFDs, M2T3multiFDs, by="Cellecta.ID")
library(ggplot2)
G8 <- ggplot(compareFDs, aes(x= FD.x, y= FD.y)) + geom_point() + scale_x_continuous(limits=c(0,50)) + scale_y_continuous(limits=c(0,50))
(gg <- ggplotly(G8))

compareFDs$comp <- compareFDs$FD.x/compareFDs$FD.y
G9 <- ggplot(compareFDs, aes(x = mix1_NoIndex_L007_R1_001trimmed.Processed, y = compareFDs$comp)) + geom_point()
(gg <- ggplotly(G9))

G10 <- ggplot(compareFDs, aes(x = mix1_NoIndex_L007_R1_001trimmed.Processed, y = compareFDs$comp)) + geom_point() + geom_vline(xintercept = 150, colour = "red", size = 1)
(gg <- ggplotly(G10))