mutate(value_mean=mean(value[strain=="HT115"]),value_sd=sd(value[strain=="HT115"])) %>%
mutate(value=(value-value_mean)/value_sd) %>%
mutate(strain = gsub("\\.","_",strain)) %>%
data.frame()
###Significances
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnai <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])!="HT115"][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
data.test <- data.frame(cbind(strain=names(unlist(test.rnai)),significance=unlist(test.rnai))) %>%
separate(strain,into=c("metabolite","strain"),sep="\\.") %>%
mutate(significance=as.numeric(as.character(unlist(significance)))) %>%
group_by(metabolite) %>%
mutate(p.adjust=p.adjust(significance,method="fdr")) %>%
mutate(labs=ifelse(p.adjust>0.05,"NS",ifelse(p.adjust<0.001,"***",ifelse(p.adjust<0.01,"**",ifelse(p.adjust<0.05,"*",NA))))) %>%
merge(filter(select(data.plot,strain),!duplicated(strain)))
metabolites.plot <- group_by(data.test,metabolite) %>%
summarise(n=sum(p.adjust<0.05)) %>%
data.frame() %>%
filter(n>0)
data.overview <- group_by(data.plot,strain,metabolite,metabolite_fullname) %>%
summarise(value=mean(value,na.rm=T)) %>%
group_by(metabolite_fullname) %>%
mutate(value_HT115=value[strain=="HT115"]) %>%
mutate(value_log=log2(value/value_HT115)) %>%
group_by(strain) %>%
mutate(val.order=median(value_log)) %>%
data.frame() %>%
arrange(val.order) %>%
mutate(strain=factor(strain,levels=unique(strain))) %>%
select(strain,metabolite,metabolite_fullname,value_log) %>%
merge(data.test,by.x=c(1,2),by.y=c(1,2)) %>%
mutate(labs=ifelse(labs=="NS","",labs)) %>%
mutate(strain = gsub("_","\\.",strain)) %>%
mutate(strain_type=ifelse(strain %in% C14met,"metabolism","transcription\nfactor"))
p1 <- ggplot(data.overview,aes(x=strain,y=metabolite_fullname,fill=value_log,label=labs)) +
geom_bin2d() + scale_fill_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="log2\n(Strain/HT115)") +
geom_text() + facet_grid(.~strain_type,scales="free_x",space = "free_x") + presentation + ylab("Metabolite") +
xlab("Strain") + theme(axis.text.x = element_text(angle = 45, hjust = 1))
data.plot <- filter(Metabolomics_normalized_RNAi,strain %in% c(C14TF,C14met)) %>%
filter(trait_transformation == "Abs.batch", !metabolite %in% c("C22:4","C22:5","C27:1","C28:0","C28:1","C29:0","C29:1","C30:0")) %>%
mutate(strain=ifelse(strain=="acox-1","acox-1.1",
ifelse(strain=="F08A8.3","acox-1.3",
ifelse(strain=="F08A8.4","acox-1.4",strain)))) %>%
group_by(metabolite,batch) %>%
mutate(value_mean=mean(value[strain=="HT115"],na.rm=T),value_sd=sd(value[strain=="HT115"],na.rm=T)) %>%
mutate(value=(value-value_mean)/value_sd) %>%
mutate(strain = gsub("\\.","_",strain)) %>%
data.frame()
###Significances
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnai <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])!="HT115"][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
data.test <- data.frame(cbind(strain=names(unlist(test.rnai)),significance=unlist(test.rnai))) %>%
separate(strain,into=c("metabolite","strain"),sep="\\.") %>%
mutate(significance=as.numeric(as.character(unlist(significance)))) %>%
group_by(metabolite) %>%
mutate(p.adjust=p.adjust(significance,method="fdr")) %>%
mutate(labs=ifelse(p.adjust>0.05,"NS",ifelse(p.adjust<0.001,"***",ifelse(p.adjust<0.01,"**",ifelse(p.adjust<0.05,"*",NA))))) %>%
merge(filter(select(data.plot,strain),!duplicated(strain)))
metabolites.plot <- group_by(data.test,metabolite) %>%
summarise(n=sum(p.adjust<0.05)) %>%
data.frame() %>%
filter(n>0)
data.overview <- group_by(data.plot,strain,metabolite,metabolite_fullname) %>%
summarise(value=mean(value,na.rm=T)) %>%
group_by(metabolite_fullname) %>%
mutate(value_HT115=value[strain=="HT115"]) %>%
mutate(value_log=log2(value/value_HT115)) %>%
group_by(strain) %>%
mutate(val.order=median(value_log)) %>%
data.frame() %>%
arrange(val.order) %>%
mutate(strain=factor(strain,levels=unique(strain))) %>%
select(strain,metabolite,metabolite_fullname,value_log) %>%
merge(data.test,by.x=c(1,2),by.y=c(1,2)) %>%
mutate(labs=ifelse(labs=="NS","",labs)) %>%
mutate(strain = gsub("_","\\.",strain)) %>%
mutate(strain_type=ifelse(strain %in% C14met,"metabolism","transcription\nfactor"))
p1 <- ggplot(data.overview,aes(x=strain,y=metabolite_fullname,fill=value_log,label=labs)) +
geom_bin2d() + scale_fill_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="log2\n(Strain/HT115)") +
geom_text() + facet_grid(.~strain_type,scales="free_x",space = "free_x") + presentation + ylab("Metabolite") +
xlab("Strain") + theme(axis.text.x = element_text(angle = 45, hjust = 1))
p1
data.plot <- filter(Metabolomics_normalized_RNAi,strain %in% c(C14TF,C14met)) %>%
filter(trait_transformation == "Abs.batch", !metabolite %in% c("C22:4","C22:5","C27:1","C28:0","C28:1","C29:0","C29:1","C30:0")) %>%
mutate(strain=ifelse(strain=="acox-1","acox-1.1",
ifelse(strain=="F08A8.3","acox-1.3",
ifelse(strain=="F08A8.4","acox-1.4",strain)))) %>%
group_by(metabolite,batch) %>%
mutate(value_mean=mean(value,na.rm=T),value_sd=sd(value,na.rm=T)) %>%
mutate(value=(value-value_mean)/value_sd) %>%
mutate(strain = gsub("\\.","_",strain)) %>%
data.frame()
###Significances
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnai <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])!="HT115"][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
data.test <- data.frame(cbind(strain=names(unlist(test.rnai)),significance=unlist(test.rnai))) %>%
separate(strain,into=c("metabolite","strain"),sep="\\.") %>%
mutate(significance=as.numeric(as.character(unlist(significance)))) %>%
group_by(metabolite) %>%
mutate(p.adjust=p.adjust(significance,method="fdr")) %>%
mutate(labs=ifelse(p.adjust>0.05,"NS",ifelse(p.adjust<0.001,"***",ifelse(p.adjust<0.01,"**",ifelse(p.adjust<0.05,"*",NA))))) %>%
merge(filter(select(data.plot,strain),!duplicated(strain)))
metabolites.plot <- group_by(data.test,metabolite) %>%
summarise(n=sum(p.adjust<0.05)) %>%
data.frame() %>%
filter(n>0)
data.overview <- group_by(data.plot,strain,metabolite,metabolite_fullname) %>%
summarise(value=mean(value,na.rm=T)) %>%
group_by(metabolite_fullname) %>%
mutate(value_HT115=value[strain=="HT115"]) %>%
mutate(value_log=log2(value/value_HT115)) %>%
group_by(strain) %>%
mutate(val.order=median(value_log)) %>%
data.frame() %>%
arrange(val.order) %>%
mutate(strain=factor(strain,levels=unique(strain))) %>%
select(strain,metabolite,metabolite_fullname,value_log) %>%
merge(data.test,by.x=c(1,2),by.y=c(1,2)) %>%
mutate(labs=ifelse(labs=="NS","",labs)) %>%
mutate(strain = gsub("_","\\.",strain)) %>%
mutate(strain_type=ifelse(strain %in% C14met,"metabolism","transcription\nfactor"))
p1 <- ggplot(data.overview,aes(x=strain,y=metabolite_fullname,fill=value_log,label=labs)) +
geom_bin2d() + scale_fill_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="log2\n(Strain/HT115)") +
geom_text() + facet_grid(.~strain_type,scales="free_x",space = "free_x") + presentation + ylab("Metabolite") +
xlab("Strain") + theme(axis.text.x = element_text(angle = 45, hjust = 1))
p1
data.test
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
data.test
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])%in% C14met][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])%in% C14TF][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
test.rnaimet
colnames(data.test[[1]])
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])%in% C14TF[-1]][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
C14TF <- c("HT115","nhr-165","nhr-169","nhr-174","nhr-217","ces-2","nhr-265","nhr-276","nhr-77","nhr-81","nhr-82")
C14met <- c("HT115","acox-1","ech-7","gpdh-1","lagr-1","scrm-2","T27F6.6","Y87G2A.2","oac-45","F08A8.3","F08A8.4","acox-1.1","acox-1.3","acox-1.4")
data.plot <- filter(Metabolomics_normalized_RNAi,strain %in% c(C14TF,C14met)) %>%
filter(trait_transformation == "Abs.batch", !metabolite %in% c("C22:4","C22:5","C27:1","C28:0","C28:1","C29:0","C29:1","C30:0")) %>%
mutate(strain=ifelse(strain=="acox-1","acox-1.1",
ifelse(strain=="F08A8.3","acox-1.3",
ifelse(strain=="F08A8.4","acox-1.4",strain)))) %>%
mutate(strain = gsub("\\.","_",strain)) %>%
data.frame()
###Significances
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])%in% C14met[-1]][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])%in% C14TF[-1]][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
test.rnaitf
test.rnaimet
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])%in% gsub("\\.","_",C14met[-1])][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(data.test[[1]])%in% C14TF[-1]][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(data.test[[1]])=="HT115"],alternative="two.sided")})
test.rnaimet
colnames(data.test[[1]])
gsub("\\.","_",C14met[-1])
colnames(data.test[[1]])%in% gsub("\\.","_",C14met[-1])
test.rnaimet[[1]]
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(z)%in% gsub("\\.","_",C14met[-1])][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(z)=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(z)%in% C14TF[-1]][,-c(1,2)],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(z)=="HT115"],alternative="two.sided")})
test.rnaimet
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(z)%in% gsub("\\.","_",C14met[-1])],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(z)=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(z)%in% C14TF[-1]],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(z)=="HT115"],alternative="two.sided")})
test.rnaimet
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(z)%in% gsub("\\.","_",C14met[-1])],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(z)=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(z)%in% C14TF[-1]],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(z)=="HT115"],alternative="two.sided")})
data.test <- data.frame(rbind(cbind(strain=names(unlist(test.rnaimet),significance=unlist(test.rnaimet)),
cbind(strain=names(unlist(test.rnaitf)),significance=unlist(test.rnaitf)))))
data.test <- data.frame(cbind(strain=names(unlist(test.rnai)),significance=unlist(test.rnai))) %>%
separate(strain,into=c("metabolite","strain"),sep="\\.") %>%
mutate(significance=as.numeric(as.character(unlist(significance)))) %>%
group_by(metabolite) %>%
mutate(p.adjust=p.adjust(significance,method="fdr")) %>%
mutate(labs=ifelse(p.adjust>0.05,"NS",ifelse(p.adjust<0.001,"***",ifelse(p.adjust<0.01,"**",ifelse(p.adjust<0.05,"*",NA))))) %>%
merge(filter(select(data.plot,strain),!duplicated(strain)))
metabolites.plot <- group_by(data.test,metabolite) %>%
summarise(n=sum(p.adjust<0.05)) %>%
data.frame() %>%
filter(n>0)
data.overview <- group_by(data.plot,strain,metabolite,metabolite_fullname) %>%
summarise(value=mean(value,na.rm=T)) %>%
group_by(metabolite_fullname) %>%
mutate(value_HT115=value[strain=="HT115"]) %>%
mutate(value_log=log2(value/value_HT115)) %>%
group_by(strain) %>%
mutate(val.order=median(value_log)) %>%
data.frame() %>%
arrange(val.order) %>%
mutate(strain=factor(strain,levels=unique(strain))) %>%
select(strain,metabolite,metabolite_fullname,value_log) %>%
merge(data.test,by.x=c(1,2),by.y=c(1,2)) %>%
mutate(labs=ifelse(labs=="NS","",labs)) %>%
mutate(strain = gsub("_","\\.",strain)) %>%
mutate(strain_type=ifelse(strain %in% C14met,"metabolism","transcription\nfactor"))
p1 <- ggplot(data.overview,aes(x=strain,y=metabolite_fullname,fill=value_log,label=labs)) +
geom_bin2d() + scale_fill_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="log2\n(Strain/HT115)") +
geom_text() + facet_grid(.~strain_type,scales="free_x",space = "free_x") + presentation + ylab("Metabolite") +
xlab("Strain") + theme(axis.text.x = element_text(angle = 45, hjust = 1))
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(z)%in% gsub("\\.","_",C14met[-1])],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(z)=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(z)%in% C14TF[-1]],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(z)=="HT115"],alternative="two.sided")})
data.test <- data.frame(rbind(cbind(strain=names(unlist(test.rnaimet)),significance=unlist(test.rnaimet)),
cbind(strain=names(unlist(test.rnaitf)),significance=unlist(test.rnaitf))))
data.test <- data.frame(cbind(strain=names(unlist(test.rnai)),significance=unlist(test.rnai))) %>%
separate(strain,into=c("metabolite","strain"),sep="\\.") %>%
mutate(significance=as.numeric(as.character(unlist(significance)))) %>%
group_by(metabolite) %>%
mutate(p.adjust=p.adjust(significance,method="fdr")) %>%
mutate(labs=ifelse(p.adjust>0.05,"NS",ifelse(p.adjust<0.001,"***",ifelse(p.adjust<0.01,"**",ifelse(p.adjust<0.05,"*",NA))))) %>%
merge(filter(select(data.plot,strain),!duplicated(strain)))
metabolites.plot <- group_by(data.test,metabolite) %>%
summarise(n=sum(p.adjust<0.05)) %>%
data.frame() %>%
filter(n>0)
data.overview <- group_by(data.plot,strain,metabolite,metabolite_fullname) %>%
summarise(value=mean(value,na.rm=T)) %>%
group_by(metabolite_fullname) %>%
mutate(value_HT115=value[strain=="HT115"]) %>%
mutate(value_log=log2(value/value_HT115)) %>%
group_by(strain) %>%
mutate(val.order=median(value_log)) %>%
data.frame() %>%
arrange(val.order) %>%
mutate(strain=factor(strain,levels=unique(strain))) %>%
select(strain,metabolite,metabolite_fullname,value_log) %>%
merge(data.test,by.x=c(1,2),by.y=c(1,2)) %>%
mutate(labs=ifelse(labs=="NS","",labs)) %>%
mutate(strain = gsub("_","\\.",strain)) %>%
mutate(strain_type=ifelse(strain %in% C14met,"metabolism","transcription\nfactor"))
p1 <- ggplot(data.overview,aes(x=strain,y=metabolite_fullname,fill=value_log,label=labs)) +
geom_bin2d() + scale_fill_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="log2\n(Strain/HT115)") +
geom_text() + facet_grid(.~strain_type,scales="free_x",space = "free_x") + presentation + ylab("Metabolite") +
xlab("Strain") + theme(axis.text.x = element_text(angle = 45, hjust = 1))
p1
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(z)%in% gsub("\\.","_",C14met[-1])],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(z)=="HT115"],alternative="two.sided")})
test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(z)%in% C14TF[-1]],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(z)=="HT115"],alternative="two.sided")})
data.test <- data.frame(rbind(cbind(strain=names(unlist(test.rnaimet)),significance=unlist(test.rnaimet)),
cbind(strain=names(unlist(test.rnaitf)),significance=unlist(test.rnaitf)))) %>%
#data.test <- data.frame(cbind(strain=names(unlist(test.rnai)),significance=unlist(test.rnai))) %>%
separate(strain,into=c("metabolite","strain"),sep="\\.") %>%
mutate(significance=as.numeric(as.character(unlist(significance)))) %>%
group_by(metabolite) %>%
mutate(p.adjust=p.adjust(significance,method="fdr")) %>%
mutate(labs=ifelse(p.adjust>0.05,"NS",ifelse(p.adjust<0.001,"***",ifelse(p.adjust<0.01,"**",ifelse(p.adjust<0.05,"*",NA))))) %>%
merge(filter(select(data.plot,strain),!duplicated(strain)))
metabolites.plot <- group_by(data.test,metabolite) %>%
summarise(n=sum(p.adjust<0.05)) %>%
data.frame() %>%
filter(n>0)
data.overview <- group_by(data.plot,strain,metabolite,metabolite_fullname) %>%
summarise(value=mean(value,na.rm=T)) %>%
group_by(metabolite_fullname) %>%
mutate(value_HT115=value[strain=="HT115"]) %>%
mutate(value_log=log2(value/value_HT115)) %>%
group_by(strain) %>%
mutate(val.order=median(value_log)) %>%
data.frame() %>%
arrange(val.order) %>%
mutate(strain=factor(strain,levels=unique(strain))) %>%
select(strain,metabolite,metabolite_fullname,value_log) %>%
merge(data.test,by.x=c(1,2),by.y=c(1,2)) %>%
mutate(labs=ifelse(labs=="NS","",labs)) %>%
mutate(strain = gsub("_","\\.",strain)) %>%
mutate(strain_type=ifelse(strain %in% C14met,"metabolism","transcription\nfactor"))
p1 <- ggplot(data.overview,aes(x=strain,y=metabolite_fullname,fill=value_log,label=labs)) +
geom_bin2d() + scale_fill_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="log2\n(Strain/HT115)") +
geom_text() + facet_grid(.~strain_type,scales="free_x",space = "free_x") + presentation + ylab("Metabolite") +
xlab("Strain") + theme(axis.text.x = element_text(angle = 45, hjust = 1))
p1
data.test <- spread(select(data.plot,metabolite,strain,biological,value),key=strain,value=value)
data.test <- split(data.test,data.test$metabolite)
test.rnai <- lapply(data.test, function(z){apply(z[,colnames(z)%in% gsub("\\.","_",c(C14met[-1],C14TF))],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[,colnames(z)=="HT115"],alternative="two.sided")})
#test.rnaimet <- lapply(data.test, function(z){apply(z[,colnames(z)%in% gsub("\\.","_",C14met[-1])],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[1:4,colnames(z)=="HT115"],alternative="two.sided")})
#test.rnaitf <- lapply(data.test, function(z){apply(z[,colnames(z)%in% C14TF[-1]],2,function(x,y,alternative){t.test(x,y,alternative,var.equal = T)$p.value},y=z[5:8,colnames(z)=="HT115"],alternative="two.sided")})
#data.test <- data.frame(rbind(cbind(strain=names(unlist(test.rnaimet)),significance=unlist(test.rnaimet)),
#                              cbind(strain=names(unlist(test.rnaitf)),significance=unlist(test.rnaitf)))) %>%
data.test <- data.frame(cbind(strain=names(unlist(test.rnai)),significance=unlist(test.rnai))) %>%
separate(strain,into=c("metabolite","strain"),sep="\\.") %>%
mutate(significance=as.numeric(as.character(unlist(significance)))) %>%
group_by(metabolite) %>%
mutate(p.adjust=p.adjust(significance,method="fdr")) %>%
mutate(labs=ifelse(p.adjust>0.05,"NS",ifelse(p.adjust<0.001,"***",ifelse(p.adjust<0.01,"**",ifelse(p.adjust<0.05,"*",NA))))) %>%
merge(filter(select(data.plot,strain),!duplicated(strain)))
metabolites.plot <- group_by(data.test,metabolite) %>%
summarise(n=sum(p.adjust<0.05)) %>%
data.frame() %>%
filter(n>0)
data.overview <- group_by(data.plot,strain,metabolite,metabolite_fullname) %>%
summarise(value=mean(value,na.rm=T)) %>%
group_by(metabolite_fullname) %>%
mutate(value_HT115=value[strain=="HT115"]) %>%
mutate(value_log=log2(value/value_HT115)) %>%
group_by(strain) %>%
mutate(val.order=median(value_log)) %>%
data.frame() %>%
arrange(val.order) %>%
mutate(strain=factor(strain,levels=unique(strain))) %>%
select(strain,metabolite,metabolite_fullname,value_log) %>%
merge(data.test,by.x=c(1,2),by.y=c(1,2)) %>%
mutate(labs=ifelse(labs=="NS","",labs)) %>%
mutate(strain = gsub("_","\\.",strain)) %>%
mutate(strain_type=ifelse(strain %in% C14met,"metabolism","transcription\nfactor"))
p1 <- ggplot(data.overview,aes(x=strain,y=metabolite_fullname,fill=value_log,label=labs)) +
geom_bin2d() + scale_fill_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="log2\n(Strain/HT115)") +
geom_text() + facet_grid(.~strain_type,scales="free_x",space = "free_x") + presentation + ylab("Metabolite") +
xlab("Strain") + theme(axis.text.x = element_text(angle = 45, hjust = 1))
p1
###Set your work directory
setwd("H:/Nemawork/Projects/Metabolomics")
workwd <- getwd()
filename <- "mQTL"
###Load pre-made functions
#uses eQTL pipeline functions https://git.wur.nl/mark_sterken/eQTL_pipeline
#     transcriptomics functions https://git.wur.nl/mark_sterken/Transcriptomics.workbench
git_dir <- "H:/Nemawork/Projects_R_zone/Git"
source(paste(git_dir,"/Loader_git.R",sep=""))
###Set data locations
support_git_dir <- paste(git_dir,"/Metabolomics/Supporting_files/",sep="")
###Load convenience functions
source(paste(support_git_dir,"../Supporting_scripts/convenience_functions.R",sep=""))
################################################################################
###Dependencies
################################################################################
install <- FALSE
#.libPaths(.libPaths("C:/Program Files/R/R-3.4.2/library"))
if(install){
install.packages("tidyverse")
install.packages("colorspace")
install.packages("RColorBrewer")
install.packages("BiocInstaller",repos="http://bioconductor.org/packages/3.3/bioc")
source("http://www.bioconductor.org/biocLite.R") ; biocLite("limma") ; biocLite("statmod"); biocLite("KEGGREST")
install.packages("gridExtra")
install.packages("VennDiagram")
install.packages("openxlsx")
install.packages("rmarkdown")
install.packages("lme4")
}
###load
library("colorspace")
library("RColorBrewer")
library(limma)
library(gridExtra)
library("VennDiagram")
library(openxlsx)
library("rmarkdown")
library(tidyverse)
library(lme4)
library(KEGGREST)
################################################################################
###Plotting theme, colours
################################################################################
###Set plotting theme
presentation <- theme(axis.text.x = element_text(size=10, face="bold", color="black"),
axis.text.y = element_text(size=10, face="bold", color="black"),
axis.title.x = element_text(size=12, face="bold", color="black"),
axis.title.y = element_text(size=12, face="bold", color="black"),
strip.text.x = element_text(size=12, face="bold", color="black"),
strip.text.y = element_text(size=12, face="bold", color="black"),
plot.title = element_text(size=14, face="bold"),
strip.background = element_rect(fill= "grey80",color="black"),
panel.background = element_rect(fill = "white",color="black"),
panel.grid.major = element_line(colour = "grey80"),
panel.grid.minor = element_blank(),
legend.position = "right")
blank_theme <- theme(plot.background = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank(),
axis.title.x = element_blank(),
axis.title.y = element_blank(),
axis.text.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks = element_blank())
###Here you can set colours for plotting in theme using ggplot2
#display.brewer.all()
myColors <- c(brewer.pal(12,"Paired")[c(8,2,8,2,7,1)],brewer.pal(9,"Set1")[9])
names(myColors) <- c("PL_N2","PL_CB4856","N2","CB4856","IL_N2","IL_CB4856","RIL")
colScale <- scale_colour_manual(name = "Genotype",values = myColors)
fillScale <- scale_fill_manual(name = "Genotype",values = myColors)
################################################################################
###Dataprep
###If from scratch
#source(paste(support_git_dir,"../Supporting_scripts/load_normalized_data.R",sep=""))
###Or, if already normalized
load(paste(support_git_dir,"obj_Metabolomics_normalized_data.Rdata",sep=""))
currents <- dir(paste(git_dir,"/WormQTL_III/supporting_files/current/",sep=""))
popmap <- data.matrix(read.delim(file=paste(git_dir,"/WormQTL_III/supporting_files/current/",currents[grepl("WUR_populations",currents) & grepl("map",currents)],sep=""),row.names=1))
popmrk <- read.delim(file=paste(git_dir,"/WormQTL_III/supporting_files/current/",currents[grepl("WUR_populations",currents) & grepl("marker",currents)],sep=""))
###CBN subset (unpublished)
source(paste(support_git_dir,"../Supporting_scripts/load_CBN_map.R",sep=""))
###Set your work directory
setwd("H:/Nemawork/Projects/Metabolomics")
workwd <- getwd()
filename <- "mQTL"
###Load pre-made functions
#uses eQTL pipeline functions https://git.wur.nl/mark_sterken/eQTL_pipeline
#     transcriptomics functions https://git.wur.nl/mark_sterken/Transcriptomics.workbench
git_dir <- "H:/Nemawork/Projects_R_zone/Git"
source(paste(git_dir,"/Loader_git.R",sep=""))
###Set data locations
support_git_dir <- paste(git_dir,"/Metabolomics/Supporting_files/",sep="")
###Load convenience functions
source(paste(support_git_dir,"../Supporting_scripts/convenience_functions.R",sep=""))
################################################################################
###Dependencies
################################################################################
install <- FALSE
#.libPaths(.libPaths("C:/Program Files/R/R-3.4.2/library"))
if(install){
install.packages("tidyverse")
install.packages("colorspace")
install.packages("RColorBrewer")
install.packages("BiocInstaller",repos="http://bioconductor.org/packages/3.3/bioc")
source("http://www.bioconductor.org/biocLite.R") ; biocLite("limma") ; biocLite("statmod"); biocLite("KEGGREST")
install.packages("gridExtra")
install.packages("VennDiagram")
install.packages("openxlsx")
install.packages("rmarkdown")
install.packages("lme4")
}
###load
library("colorspace")
library("RColorBrewer")
library(limma)
library(gridExtra)
library("VennDiagram")
library(openxlsx)
library("rmarkdown")
library(tidyverse)
library(lme4)
library(KEGGREST)
################################################################################
###Plotting theme, colours
################################################################################
###Set plotting theme
presentation <- theme(axis.text.x = element_text(size=10, face="bold", color="black"),
axis.text.y = element_text(size=10, face="bold", color="black"),
axis.title.x = element_text(size=12, face="bold", color="black"),
axis.title.y = element_text(size=12, face="bold", color="black"),
strip.text.x = element_text(size=12, face="bold", color="black"),
strip.text.y = element_text(size=12, face="bold", color="black"),
plot.title = element_text(size=14, face="bold"),
strip.background = element_rect(fill= "grey80",color="black"),
panel.background = element_rect(fill = "white",color="black"),
panel.grid.major = element_line(colour = "grey80"),
panel.grid.minor = element_blank(),
legend.position = "right")
blank_theme <- theme(plot.background = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank(),
axis.title.x = element_blank(),
axis.title.y = element_blank(),
axis.text.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks = element_blank())
###Here you can set colours for plotting in theme using ggplot2
#display.brewer.all()
myColors <- c(brewer.pal(12,"Paired")[c(8,2,8,2,7,1)],brewer.pal(9,"Set1")[9])
names(myColors) <- c("PL_N2","PL_CB4856","N2","CB4856","IL_N2","IL_CB4856","RIL")
colScale <- scale_colour_manual(name = "Genotype",values = myColors)
fillScale <- scale_fill_manual(name = "Genotype",values = myColors)
################################################################################
###Dataprep
###If from scratch
#source(paste(support_git_dir,"../Supporting_scripts/load_normalized_data.R",sep=""))
###Or, if already normalized
load(paste(support_git_dir,"obj_Metabolomics_normalized_data.Rdata",sep=""))
currents <- dir(paste(git_dir,"/WormQTL_III/supporting_files/current/",sep=""))
popmap <- data.matrix(read.delim(file=paste(git_dir,"/WormQTL_III/supporting_files/current/",currents[grepl("WUR_populations",currents) & grepl("map",currents)],sep=""),row.names=1))
popmrk <- read.delim(file=paste(git_dir,"/WormQTL_III/supporting_files/current/",currents[grepl("WUR_populations",currents) & grepl("marker",currents)],sep=""))
###CBN subset (unpublished)
source(paste(support_git_dir,"../Supporting_scripts/load_CBN_map.R",sep=""))
###Load data
load(file=paste(workwd,"/QTL/obj_met.QTL.Rdata",sep=""))
load(file=paste(workwd,"/QTL/obj_heritability.parental.Rdata",sep=""))
###Peak calling
met.peak.QTL <- mapping.to.list(map1.output=met.QTL) %>%
peak.finder(threshold=3.7)
###Make QTL table
met.table.QTL <- filter(met.peak.QTL,!is.na(qtl_peak)) %>%
eQTL.table.addR2(met.QTL) %>%
separate(trait,into=c("transformation","metabolite"),sep="_") %>%
mutate(measurement="") %>%
group_by(metabolite,qtl_chromosome,qtl_marker,transformation) %>%
mutate(measurement=ifelse(grepl(":",metabolite),"Fatty acid","Amino acid")) %>%
data.frame() %>%
merge(select(heritability.parental,trait,metabolite_fullname,H2_ANOVA_PL,H2_ANOVA),by.x=2,by.y=1) %>%
mutate(trait=paste(transformation,metabolite,sep="_"))
data.plot <- mutate(met.table.QTL,gene_chromosome="I",gene_bp=1000,trait=metabolite,qtl_type="trans") %>%
prep.ggplot.eQTL.table() %>%
mutate(metabolite_fullname=ifelse(measurement=="","Alanine",as.character(unlist(metabolite_fullname))),
qtl_significance=ifelse(measurement=="",NA,qtl_significance),
measurement=ifelse(measurement=="","Amino acid",measurement))
head(data.plot)
ggplot(data.plot,aes(x=qtl_bp,y=metabolite_fullname,colour=qtl_significance)) +
geom_point() + geom_segment(aes(x=qtl_bp_left,xend=qtl_bp_right,y=metabolite_fullname,yend=metabolite_fullname)) +
facet_grid(measurement~qtl_chromosome,scales="free",space="free") + scale_colour_gradientn(colours=brewer.pal(11,"RdYlBu"),na.value=NA,name="Significance\n(-log10(P))") +
presentation + scale_x_continuous(breaks=c(5,10,15,20)*10^6,labels=c(5,10,15,20)) + xlab("mQTL location (Mbp)") + ylab("Metabolite")
