Commit a4971b88 authored by Malte Herold's avatar Malte Herold
Browse files

asd

parent 01cc3a7e
PROKKA_00042
PROKKA_01867
PROKKA_00534
PROKKA_01618
PROKKA_00311
PROKKA_00704
PROKKA_01184
PROKKA_01185
PROKKA_01200
PROKKA_01203
PROKKA_02313
PROKKA_02317
PROKKA_01202
PROKKA_01201
PROKKA_02431
PROKKA_01169
PROKKA_01163
PROKKA_01165
PROKKA_01162
PROKKA_01164
PROKKA_01166
PROKKA_00421
PROKKA_01174
PROKKA_01179
PROKKA_00420
PROKKA_01178
PROKKA_01167
PROKKA_01177
PROKKA_01168
PROKKA_01182
PROKKA_01183
PROKKA_00588
PROKKA_02121
PROKKA_02379
PROKKA_02380
PROKKA_00334
PROKKA_00463
PROKKA_00141
PROKKA_00956
PROKKA_00464
PROKKA_02122
PROKKA_02123
PROKKA_00361
PROKKA_01356
PROKKA_00965
PROKKA_00966
PROKKA_00293
PROKKA_00852
PROKKA_00318
PROKKA_02417
PROKKA_00473
PROKKA_00823
......@@ -126,23 +126,41 @@ x2=tab[!(tab$Signif),]
#
# p=p+theme_bw() +theme(axis.text.x = element_text(angle = 90, hjust = 1)) + theme(panel.grid.minor = element_blank())
x1= x1 %>%
mutate(general_cats= gsub("via ", "via\n", general_cats)) %>%
mutate(general_cats= gsub("NADH ", "NADH\n", general_cats)) %>%
mutate(general_cats= gsub("stress ", "NADH\n", general_cats))
x1$general_cats = gsub("z_Other", "Other/None", x1$general_cats)
x1$general_cats = forcats::fct_relevel(x1$general_cats, "Other/None", after = Inf)
p <- ggplot() +
#p <- ggplot(m_split,aes(x=cog_name,y=value)) +
#p <- ggplot(xxx,aes(x=Class_from_Pwy_association,y=value)) +
geom_point(data=x1,stat="identity",aes(x=general_cats,y=log2FC,fill=type),position= position_jitterdodge(), alpha = 0.6,size=2.0,shape=21) +
geom_point(data=x2,stat="identity",aes(x=general_cats,y=log2FC,fill=type),position= position_jitterdodge(), alpha = 0.4,size=1.5,shape=23)+
geom_point(data=x1,stat="identity",aes(x=general_cats,y=log2FC,fill=type),position= position_jitterdodge(), alpha = 0.6,size=2.7,shape=21) +
#geom_point(data=x2,stat="identity",aes(x=general_cats,y=log2FC,fill=type),position= position_jitterdodge(), alpha = 0.4,size=1.5,shape=23)+
#geom_point(aes(shape=Signif),position = position_jitterdodge(), alpha = 0.7) +
geom_hline(yintercept = 0,alpha=0.4) +
geom_hline(yintercept = 2,alpha=0.15) +
geom_hline(yintercept = -2,alpha=0.15) +
theme_bw()+
#geom_line(aes(group = Geneid))+
ylab("log2FC") +
xlab("Generalised functional category")
xlab("Generalised functional category")+
scale_fill_manual(values=x[1:2]) +
guides(fill= guide_legend(override.aes = list(size=3,alpha=1))) +
theme(axis.text.y = element_text(size=13)) +
theme(axis.text.x = element_text(size=13, angle=90, hjust=1)) +
theme(legend.text = element_text(size=13),
legend.title = element_text(size=13),
axis.title = element_text( size = 14)) +
theme(axis.text.x = ) +
theme(panel.grid.minor = element_blank())
#scale_fill_manual(values=c("red","green"))+
#scale_shape_manual(name = 'Significance', guide = 'legend',values=c(21,23),labels = c("True","False"))
p=p+theme_bw() +theme(axis.text.x = element_text(angle = 90, hjust = 1)) + theme(panel.grid.minor = element_blank())
outname.p=paste(REPODIR,"Combined/data/Prot_RNA_comparisons_fig4_all.pdf",sep="/")
outname.p=paste(REPODIR,"Combined/data/Prot_RNA_comparisons_fig4_onlysignif.pdf",sep="/")
pdf(file = outname.p,width=12,height=8)
p
......
library(tidyverse)
library(reshape2)
library(plyr)
REPODIR="/home/mh/Uni_Lux/REPOS/LF_omics_analysis"
incompl=paste(REPODIR,"Combined/data/combined_full_table.tsv",sep="/")
compl=read.csv(incompl,sep="\t")
tpm_all_c=compl[c(1,2,3,4)]
tpm_all_m=compl[c(1,8,9)]
lfq_scaled_c=compl[c(1,13,14,15,16,17)]
lfq_scaled_m=compl[c(1,21,22,23)]
lfq_raw_c=compl[c(1,27,28,29,30,31)]
lfq_raw_m=compl[c(1,35,36,37)]
anno=compl[c(1,seq(42,66))]
plot_single_gene<-function(anno,genelist,tab_c,tab_m,mod_names=T){
m_c=melt(tab_c)
m_c$variable="continuous"
m_m=melt(tab_m)
m_m$variable="mineral"
mer=rbind(m_c,m_m)
#select genes from list
ff=mer[mer$Protein.IDs %in% genelist,]
ff=join(ff,anno)
if(mod_names==T){
ff$PROKKA_productname=gsub("alpha|beta|delta|gamma|subunit|,","",ff$PROKKA_productname)
ff$PROKKA_productname=gsub("putative|large","",ff$PROKKA_productname)
ff$PROKKA_productname=gsub(":"," ",ff$PROKKA_productname)
ff$PROKKA_productname=gsub("^\\s|\\s$","",ff$PROKKA_productname)
ff$PROKKA_productname=tolower(ff$PROKKA_productname)
}
#TODO add list of gene names
#p<-ggplot(ff,aes(y=value,x=PROKKA_productname))+
p<-ggplot(ff,aes(y=value,x=PROKKA_productname))+
geom_boxplot(aes(fill=variable)) +
geom_jitter(aes(color=variable,fill=variable,group=variable),alpha=0.3,position = position_dodge(width=0.75))+
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
return(p)
}
pp=plot_single_gene(anno,c("PROKKA_00005","PROKKA_00006"),tpm_all_c,tpm_all_m)
#pp+facet_wrap(~ variable)
list_of_choice=mot
outf.dist.tpm="/home/mh/Dropbox/phd_project/Lepto_Paper/submission_final/rtca_tpm.pdf"
outf.dist.lfq="/home/mh/Dropbox/phd_project/Lepto_Paper/submission_final/rtca_lfq.pdf"
pdf(file = outf.dist.tpm,width=12,height=8)
plot_single_gene(anno,list_of_choice,tpm_all_c,tpm_all_m,T)
dev.off()
pdf(file = outf.dist.lfq,width=12,height=8)
plot_single_gene(anno,list_of_choice,lfq_raw_c,lfq_raw_m,T)
dev.off()
pp=plot_single_gene(anno,list_of_choice,tpm_all_c,tpm_all_m)
plot_single_gene(anno,list_of_choice,lfq_scaled_c,lfq_scaled_m)
plot_single_gene(anno,list_of_choice,lfq_raw_c,lfq_raw_m)
###protstats
p=join(lfq_raw_c,lfq_raw_m)
ff=lfq_raw_c[complete.cases(lfq_raw_m),]
ff=lfq_raw_c[-1]
ff=lfq_raw_m[-1]
ff=lfq_scaled_c[-1]
ff=lfq_scaled_m[-1]
ff[!is.na(ff)]<-1
ff[is.na(ff)]<-0
table(colSums(ff))
###sort by TPM, LFQ_mean
tpm_arr_c <- compl %>% arrange(desc(tpm_continuous.means))
tpm_arr_m <- compl %>% arrange(desc(tpm_mineral.means))
lfq_arr_c <- compl %>% arrange(desc(lfq_cont_raw.means))
lfq_arr_m <- compl %>% arrange(desc(lfq_min_raw.means))
##plot dists
plot_dist <- function(tab_c,tab_m){
m_c=melt(tab_c)
m_c$variable="continuous"
m_m=melt(tab_m)
m_m$variable="mineral"
mer=rbind(m_c,m_m)
print(dim(m_c))
print(dim(m_m))
print(dim(mer))
p <- ggplot(mer,aes(x=log2(value),fill=variable))+
geom_density(alpha=0.5)+
theme_bw()
return(p)
}
plot_dist(tpm_all_c,tpm_all_m)
plot_dist(lfq_scaled_c,lfq_scaled_m)
pp=plot_dist(lfq_raw_c,lfq_raw_m)
outf.dist.tpm="/home/mh/Dropbox/phd_project/Lepto_Paper/submission_final/dist_tpm.pdf"
outf.dist.lfq="/home/mh/Dropbox/phd_project/Lepto_Paper/submission_final/dist_lfq.pdf"
pdf(file = outf.dist.tpm,width=12,height=8)
p
dev.off()
pdf(file = outf.dist.lfq,width=12,height=8)
pp
dev.off()
###prepare input for circos
out.tpm.c="/home/mh/Uni_Lux/software/circos/circos-0.69/lepto/data/tpm_cont.tsv"
out.tpm.m="/home/mh/Uni_Lux/software/circos/circos-0.69/lepto/data/tpm_min.tsv"
out.lfq.c="/home/mh/Uni_Lux/software/circos/circos-0.69/lepto/data/lfq_cont.tsv"
out.lfq.m="/home/mh/Uni_Lux/software/circos/circos-0.69/lepto/data/lfq_min.tsv"
#get coordinates
coords=read.csv("/home/mh/Uni_Lux/software/circos/circos-0.69/lepto/data/coords.genes.txt",sep="\t",header=F)
coords=cbind(Protein.IDs=compl$Protein.IDs,coords)
write.table(file=out.tpm.c,cbind(coords[-1],compl$tpm_continuous.means),sep="\t",col.names = F,row.names=F,quote=F)
write.table(file=out.tpm.m,data.frame(coords[-1],compl$tpm_mineral.means),sep="\t",col.names = F,row.names=F,quote=F)
#for proteins instead of compl use really unfiltered
infile.lf.cont.scaled=paste(REPODIR,"Proteomics/data/LFQs_continuous_scaled_unfilt.tsv",sep="/")
infile.lf.min.scaled=paste(REPODIR,"Proteomics/data/LFQs_mineral_scaled_unfilt.tsv",sep="/")
#optionally filter
lf.c=read.csv(infile.lf.cont.scaled,sep="\t")
lf.m=read.csv(infile.lf.min.scaled,sep="\t")
lf.cf=lf.c[apply(lf.c[,c(2,3,4,5,6)],1,function(x) length(which(is.na(x)))=<3),]
lf.mf=lf.m[apply(lf.m[,c(2,3,4)],1,function(x) length(which(is.na(x)))<2),]
lf.mf=lf.m
lf.cf=lf.c
lf.mf=lf.mf[!is.na(lf.mf$means),]
lf.cf=lf.cf[!is.na(lf.cf$means),]
lf.m=lf.mf
lf.c=lf.cf
lf.mm=join(coords,lf.m)
lf.cc=join(coords,lf.c)
write.table(file=out.lfq.c,data.frame(lf.cc[c(2,3,4)],lf.cc$means),sep="\t",col.names = F,row.names=F,quote=F)
write.table(file=out.lfq.m,data.frame(lf.mm[c(2,3,4)],lf.mm$means),sep="\t",col.names = F,row.names=F,quote=F)
#write out
#write.table()
###GENELISTS
#for cytochromes bd
cyt=c("PROKKA_00439",
"PROKKA_00440",
"PROKKA_00822")
#cytochrome c
cyt=c("PROKKA_00766",
"PROKKA_02381",
"PROKKA_02382",
"PROKKA_01388",
"PROKKA_00732",
"PROKKA_00740",
"PROKKA_00940",
"PROKKA_00730",
"PROKKA_00731",
"PROKKA_00741",
"PROKKA_02378",
"PROKKA_00732")
#cytochrome c c551 c552
cyt=c("PROKKA_01388",
)
#rubisco
rub="PROKKA_02524"
#reductive TCA
rtca=c(
"PROKKA_02486",
"PROKKA_00876",
"PROKKA_01556",
"PROKKA_00585",
"PROKKA_00579",
"PROKKA_00587",
"PROKKA_00586",
"PROKKA_02458",
"PROKKA_02457",
"PROKKA_02451",
"PROKKA_02456",
"PROKKA_00965",
"PROKKA_00966",
"PROKKA_00581",
"PROKKA_00582",
"PROKKA_00578",
"PROKKA_02453",
"PROKKA_02452",
"PROKKA_02455",
"PROKKA_02450",
"PROKKA_02143"
)
#copper resistance + copper/silver resistance
cop=c(
"PROKKA_02050",
"PROKKA_00313",
"PROKKA_00752",
"PROKKA_00684",
"PROKKA_00919",
"PROKKA_00166",
"PROKKA_02435",
"PROKKA_00920",
"PROKKA_01521",
"PROKKA_02071",
"PROKKA_00918",
"PROKKA_02048"
)
#"heavy metal resistance"
heav=c(
"PROKKA_00076",
"PROKKA_00755",
"PROKKA_01059",
"PROKKA_02594"
)
sulf=c("PROKKA_00960",
"PROKKA_00427",
"PROKKA_00958",
"PROKKA_01477",
"PROKKA_00429"
)
mot=c("PROKKA_00196",
"PROKKA_00198",
"PROKKA_00199",
"PROKKA_00200",
"PROKKA_00201",
"PROKKA_00202",
"PROKKA_00203",
"PROKKA_00204",
"PROKKA_00205",
"PROKKA_00206",
"PROKKA_00207",
"PROKKA_00209",
"PROKKA_00210",
"PROKKA_00211",
"PROKKA_00212",
"PROKKA_00213",
"PROKKA_00214",
"PROKKA_00215",
"PROKKA_00216",
"PROKKA_00217",
"PROKKA_00218",
"PROKKA_00219",
"PROKKA_00220",
"PROKKA_00221",
"PROKKA_00222",
"PROKKA_02334",
"PROKKA_02335",
"PROKKA_02336",
"PROKKA_02337",
"PROKKA_02339",
"PROKKA_02340",
"PROKKA_02341",
"PROKKA_02342",
"PROKKA_02343",
"PROKKA_02344",
"PROKKA_02345",
"PROKKA_02346",
"PROKKA_02347",
"PROKKA_02348",
"PROKKA_02349"
)
ctax=c("PROKKA_00183",
"PROKKA_00227",
"PROKKA_01445",
"PROKKA_01455",
"PROKKA_01548",
"PROKKA_01731",
"PROKKA_02147",
"PROKKA_00223",
"PROKKA_00224",
"PROKKA_00225",
"PROKKA_00226",
"PROKKA_00228",
"PROKKA_00229",
"PROKKA_00230",
"PROKKA_00710",
"PROKKA_00799",
"PROKKA_02318"
)
......@@ -68,7 +68,7 @@ fff$general_cats=fff$Manually_assigned_category
fff[grep("Nitra|Nitro|Ammonia",fff$Manually_assigned_category,ignore.case=T),]$general_cats="Nitrogen metabolism"
#cytochromes not specified as left out of plot for now
groupcats_cytochromes="Cytochrome"
fff[grep(groupcats_cytochromes,fff$Manually_assigned_categor,ignore.case=T),]$general_cats="Cytochromes"
fff[grep(groupcats_cytochromes,fff$Manually_assigned_category,ignore.case=T),]$general_cats="Cytochromes"
groupcats_polysaccharides=paste("Cellulose production",
"Extracellular polysaccharide production and export",
"Lipopolysaccharide synthesis",
......
This source diff could not be displayed because it is too large. You can view the blob instead.
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment