library(dplyr)
library(stringr)
library(useful)
library(MASS)
library(reshape2)
library(epiDisplay)
library(ggplot2)
Dataf <- read.csv( "D:/Pipeline comparisons/Writing/Main/Figure 2/Data for Figure 2.csv")
Dataf95 <-Dataf[Dataf$Comparison=='pSTY95_to_pASTY',]
Dataf95 <-Dataf95[Dataf95$Category!='No Matching Sequences' & Dataf95$Category!='Matching Sequences',]
ggp95 <- ggplot(Dataf95[order(Dataf95$Category, decreasing = T),],            # Create ggplot2 plot scaled to 1.00
aes(x = Dataset,
y = Matches,
fill=factor(Category, levels=c("NoMSeq","MSeq_NoMSite","Mseq MSite" )))) +
geom_bar(position = "fill", stat = "identity") +
facet_wrap(~ Pipeline, ncol= 1)
ggp95 + scale_y_continuous(labels = scales::percent_format()) +
theme(legend.title=element_blank())
# Draw ggplot2 plot scaled to 1.00
Dataf05 <-Dataf[Dataf$Comparison=='pASTY05_to_pSTY',]
Dataf05 <-Dataf05[Dataf05$Category!='No Matching Sequences' & Dataf05$Category!='Matching Sequences',]
ggp05 <- ggplot(Dataf05[order(Dataf05$Category, decreasing = T),],            # Create ggplot2 plot scaled to 1.00
aes(x = Dataset,
y = Matches,
fill=factor(Category, levels=c("NoMSeq","MSeq_NoMSite","Mseq MSite" )))) +
geom_bar(position = "fill", stat = "identity") +
facet_wrap(~ Pipeline, ncol= 1)
ggp05 + scale_y_continuous(labels = scales::percent_format()) +
theme(legend.title=element_blank())
# Comparing scans #
source('D:/Pipeline comparisons/Writing/R Functions/Binomial Scores Function Peptidoform level scans.R')
source('D:/Pipeline comparisons/Writing/R Functions/FLR function Bin Adjusted.R')
source('D:/Pipeline comparisons/Writing/R Functions/Function frequency of site.R')
source('D:/Pipeline comparisons/Writing/R Functions/CompScans_05pASTYtoAllpSTY.R')
source('D:/Pipeline comparisons/Writing/R Functions/CompScans_95pSTYtoAllpASTY.R')
# We want to assess if there are any differences between the Max and MM collapsing methods using all rice data sets #
#> [conflicted] Will prefer dplyr::filter over any other package
suppressPackageStartupMessages(library("tidyverse"))
library(dplyr)
library(stringr)
library(useful)
library(MASS)
library(reshape2)
library(epiDisplay)
PXD000923 <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD000923_pSTY.csv")
PXD002222 <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD002222_pSTY.csv")
PXD002756 <- read.csv("D:/Pipeline comparisons/Writing/Data/TPP/PXD002756_pSTY.csv")
PXD004705 <- read.csv("D:/Pipeline comparisons/Writing/Data/TPP/PXD004705_pSTY.csv")
PXD004939 <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD004939_pSTY.csv")
PXD005241 <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD005241_pSTY.csv")
PXD005241$Spectrum <- str_remove(PXD005241$Spectrum, '.raw')
PXD012764 <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD012764_pSTY.csv")
PXD019291 <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD019291_pSTY.csv")
PXD000923A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD000923_pASTY.csv")
PXD002222A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD002222_pASTY.csv")
PXD002756A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD002756_pASTY.csv")
PXD004705A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD004705_pASTY.csv")
PXD004939A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD004939_pASTY.csv")
PXD005241A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD005241_pASTY.csv")
PXD005241A$Spectrum <- str_remove(PXD005241A$Spectrum, '_raw')
PXD012764A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD012764_pASTY.csv")
PXD019291A <- read.csv( "D:/Pipeline comparisons/Writing/Data/TPP/PXD019291_pASTY.csv")
Comp_A05_PXD000923 <- CompScans_05toAll(PXD000923A,PXD000923)
Comp_95toA_PXD000923 <- CompScans_95toA(PXD000923,PXD000923A)
Comp_A05_PXD002222 <- CompScans_05toAll(PXD002222A,PXD002222)
Comp_95toA_PXD002222 <- CompScans_95toA(PXD002222,PXD002222A)
Comp_A05_PXD002756 <- CompScans_05toAll(PXD002756A,PXD002756)
Comp_95toA_PXD002756 <- CompScans_95toA(PXD002756,PXD002756A)
Comp_A05_PXD004705 <- CompScans_05toAll(PXD004705A,PXD004705)
Comp_95toA_PXD004705 <- CompScans_95toA(PXD004705,PXD004705A)
Comp_A05_PXD004939 <- CompScans_05toAll(PXD004939A,PXD004939)
Comp_95toA_PXD004939 <- CompScans_95toA(PXD004939,PXD004939A)
Comp_A05_PXD005241 <- CompScans_05toAll(PXD005241A,PXD005241)
Comp_95toA_PXD005241 <- CompScans_95toA(PXD005241,PXD005241A)
Comp_A05_PXD012764 <- CompScans_05toAll(PXD012764A,PXD012764)
Comp_95toA_PXD012764 <- CompScans_95toA(PXD012764,PXD012764A)
Comp_A05_PXD019291 <- CompScans_05toAll(PXD019291A,PXD019291)
Comp_95toA_PXD019291 <- CompScans_95toA(PXD019291,PXD019291A)
Table_A05_PXD000923 <- Comp_A05_PXD000923[2]
Table_95toA_PXD000923 <- Comp_95toA_PXD000923[2]
Comp_A05_PXD000923[1]
Comp_A05_PXD000923[3]
Comp_95toA_PXD000923[1]
Comp_95toA_PXD000923[3]
Table_A05_PXD002222 <- Comp_A05_PXD002222[2]
Table_95toA_PXD002222 <- Comp_95toA_PXD002222[2]
Comp_A05_PXD002222[1]
Comp_A05_PXD002222[3]
Comp_95toA_PXD002222[1]
Comp_95toA_PXD002222[3]
Table_A05_PXD002756 <- Comp_A05_PXD002756[2]
Table_95toA_PXD002756 <- Comp_95toA_PXD002756[2]
Comp_A05_PXD002756[1]
Comp_A05_PXD002756[3]
Comp_95toA_PXD002756[1]
Comp_95toA_PXD002756[3]
Table_A05_PXD004705<- Comp_A05_PXD004705[2]
Table_95toA_PXD004705 <- Comp_95toA_PXD004705[2]
Comp_A05_PXD004705[1]
Comp_A05_PXD004705[3]
Comp_95toA_PXD004705[1]
Comp_95toA_PXD004705[3]
Table_A05_PXD004939<- Comp_A05_PXD004939[2]
Table_95toA_PXD004939 <- Comp_95toA_PXD004939[2]
Comp_A05_PXD004939[1]
Comp_A05_PXD004939[3]
Comp_95toA_PXD004939[1]
Comp_95toA_PXD004939[3]
Table_A05_PXD005241<- Comp_A05_PXD005241[2]
Table_95toA_PXD005241 <- Comp_95toA_PXD005241[2]
Comp_A05_PXD005241[1]
Comp_A05_PXD005241[3]
Comp_95toA_PXD005241[1]
Comp_95toA_PXD005241[3]
Table_A05_PXD012764<- Comp_A05_PXD012764[2]
Table_95toA_PXD012764 <- Comp_95toA_PXD012764[2]
Comp_A05_PXD012764[1]
Comp_A05_PXD012764[3]
Comp_95toA_PXD012764[1]
Comp_95toA_PXD012764[3]
Table_A05_PXD019291<- Comp_A05_PXD019291[2]
Table_95toA_PXD019291 <- Comp_95toA_PXD019291[2]
Comp_A05_PXD019291[1]
Comp_A05_PXD019291[3]
Comp_95toA_PXD019291[1]
Comp_95toA_PXD019291[3]
View(CompScans_95toA)
View(CompScans_05toAll)
View(CompScans_95toA)
library(dplyr)
library(stringr)
library(useful)
library(MASS)
library(reshape2)
library(epiDisplay)
library(ggplot2)
Dataf <- read.csv( "D:/Pipeline comparisons/Writing/Main/Figure 2/Data for Figure 2.csv")
Dataf95 <-Dataf[Dataf$Comparison=='pSTY95_to_pASTY',]
Dataf95 <-Dataf95[Dataf95$Category!='No Matching Sequences' & Dataf95$Category!='Matching Sequences',]
ggp95 <- ggplot(Dataf95[order(Dataf95$Category, decreasing = T),],            # Create ggplot2 plot scaled to 1.00
aes(x = Dataset,
y = Matches,
fill=factor(Category, levels=c("NoMSeq","MSeq_NoMSite","Mseq MSite" )))) +
geom_bar(position = "fill", stat = "identity") +
facet_wrap(~ Pipeline, ncol= 1)
ggp95 + scale_y_continuous(labels = scales::percent_format()) +
theme(legend.title=element_blank())
# Draw ggplot2 plot scaled to 1.00
Dataf05 <-Dataf[Dataf$Comparison=='pASTY05_to_pSTY',]
Dataf05 <-Dataf05[Dataf05$Category!='No Matching Sequences' & Dataf05$Category!='Matching Sequences',]
ggp05 <- ggplot(Dataf05[order(Dataf05$Category, decreasing = T),],            # Create ggplot2 plot scaled to 1.00
aes(x = Dataset,
y = Matches,
fill=factor(Category, levels=c("NoMSeq","MSeq_NoMSite","Mseq MSite" )))) +
geom_bar(position = "fill", stat = "identity") +
facet_wrap(~ Pipeline, ncol= 1)
ggp05 + scale_y_continuous(labels = scales::percent_format()) +
theme(legend.title=element_blank())
View(Dataf95)
ggp95 + scale_y_continuous(labels = scales::percent_format()) +
theme(legend.title=element_blank(),text = element_text(size = 14))
