---
title: "Validation_sparc_hcn2_OLIG2_IF"
author: "Luise A. Seeker"
date: "09/08/2022"
output: html_document
---
HCN2 SPARC and OLIG2 co-labelling in 3 BA4 and 2 CSC samples
```{r}
library(ggplot2)
library(lme4)
library(lmerTest)
library(here)
library(tidyr)
library(ggsci)
library(Seurat)
```
```{r, echo = F}
mypal <- pal_npg("nrc", alpha = 0.7)(10)
mypal2 <-pal_tron("legacy", alpha = 0.7)(7)
mypal3 <- pal_lancet("lanonc", alpha = 0.7)(9)
mypal4 <- pal_simpsons(palette = c("springfield"), alpha = 0.7)(16)
mypal5 <- pal_rickandmorty(palette = c("schwifty"), alpha = 0.7)(6)
mypal6 <- pal_futurama(palette = c("planetexpress"), alpha = 0.7)(5)
mypal7 <- pal_startrek(palette = c("uniform"), alpha = 0.7)(5)
mycoloursP<- c(mypal, mypal2, mypal3, mypal4, mypal5, mypal6, mypal7)
```
```{r}
sparc_hcn2 <- read.csv(here("data",
"validation_data",
"20220819_HCN2_SPARC_OLIG2_quant.csv"))
```
```{r}
names(sparc_hcn2)
sparc_hcn2$tissue <- as.factor(sparc_hcn2$tissue)
sparc_hcn2$sample_id <- factor(sparc_hcn2$sample_id, levels = c("SD008_18_BA4",
"SD012_15_BA4",
"SD031_14_BA4",
"SD011_18_CSC",
"SD042_18_CSC"))
```
Convert from wide to long format to see how many single, double and triple
positive cells are in each sample
```{r}
keycol <- "sample_id"
valuecol <- "count"
gathercols <- c("Num_Detections",
"Num_HCN2",
"Num_OLIG2",
"Num_OLIG2_HCN2",
"Num_OLIG2_SPARC",
"Num_OLIG2_SPARC_HCN2",
"Num_SPARC",
"SPARC_HCN2")
long_data <- gather(sparc_hcn2, keycol, valuecol, gathercols)
head(long_data)
nrow(long_data)
names(long_data)
```
```{r}
ggplot(long_data, aes(x = sample_id ,
y = valuecol,
fill = keycol)) +
geom_bar(position="stack", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))+scale_fill_manual(values= mycoloursP[25:50])
ggplot(long_data, aes(x = sample_id ,
y = valuecol,
fill = keycol)) +
geom_bar(position="fill", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +scale_fill_manual(values= mycoloursP[25:50])
```
Remove cells that are negative for all tested markers:
```{r}
keycol <- "sample_id"
valuecol <- "count"
gathercols <- c("Num_HCN2",
"Num_OLIG2",
"Num_OLIG2_HCN2",
"Num_OLIG2_SPARC",
"Num_OLIG2_SPARC_HCN2",
"Num_SPARC",
"SPARC_HCN2")
long_data <- gather(sparc_hcn2, keycol, valuecol, gathercols)
head(long_data)
nrow(long_data)
names(long_data)
ggplot(long_data, aes(x = sample_id ,
y = valuecol,
fill = keycol)) +
geom_bar(position="stack", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))+scale_fill_manual(values= mycoloursP[25:50])
ggplot(long_data, aes(x = sample_id ,
y = valuecol,
fill = keycol)) +
geom_bar(position="fill", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +scale_fill_manual(values= mycoloursP[25:50])
```
Exclude cells that are not positive for OLIG2
```{r}
keycol <- "sample_id"
valuecol <- "count"
gathercols <- c("Num_OLIG2",
"Num_OLIG2_HCN2",
"Num_OLIG2_SPARC",
"Num_OLIG2_SPARC_HCN2")
long_data <- gather(sparc_hcn2, keycol, valuecol, gathercols)
ggplot(long_data, aes(x = sample_id ,
y = valuecol,
fill = keycol)) +
geom_bar(position="stack", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))+scale_fill_manual(values= mycoloursP[25:50])
ggplot(long_data, aes(x = sample_id ,
y = valuecol,
fill = keycol)) +
geom_bar(position="fill", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +scale_fill_manual(values= mycoloursP[25:50])
```
collapse tissue
```{r}
ggplot(long_data, aes(x = tissue ,
y = valuecol,
fill = keycol)) +
geom_bar(position="stack", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))+scale_fill_manual(values= mycoloursP[25:50])
ggplot(long_data, aes(x = tissue,
y = valuecol,
fill = keycol)) +
geom_bar(position="fill", stat="identity")+ theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +scale_fill_manual(values= mycoloursP[25:50])
```
```{r}
sparc_hcn2$perc_HCN2 <- ((sparc_hcn2$Num_OLIG2_HCN2 +
sparc_hcn2$Num_OLIG2_SPARC_HCN2)/
(sparc_hcn2$Num_OLIG2_HCN2 +
sparc_hcn2$Num_OLIG2_SPARC_HCN2 +
sparc_hcn2$Num_OLIG2_SPARC +
sparc_hcn2$Num_OLIG2))*100
ggplot(sparc_hcn2, aes(x = tissue, y = perc_HCN2)) +
geom_boxplot()+ geom_jitter(width = 0.2, aes(colour = sample_id)) +
theme_bw(14) + ylab("HCN2+OLIG2+ (% of OLIG2)") + xlab("Tissue")
```
```{r}
wilcox.test(perc_HCN2 ~ tissue, data=sparc_hcn2)
```
```{r}
ggplot(sparc_hcn2, aes(x = tissue, y = perc_HCN2_SPARC_oligos)) +
geom_boxplot()+ geom_jitter(width = 0.2, aes(colour = sample_id)) +
theme_bw(14) + ylab("HCN2+OLIG2+SPARC+ (% of OLIG2)") + xlab("Tissue")
```
```{r}
wilcox.test(perc_HCN2_SPARC_oligos ~ tissue, data=sparc_hcn2)
```
```{r}
summary(sparc_hcn2$perc_HCN2_SPARC_oligos)
```
```{r}
nad_ol <- readRDS(here("data",
"single_nuc_data",
"oligodendroglia",
"srt_oligos_and_opcs_LS.RDS"))
Idents(nad_ol) <- "ol_clusters_named"
oligos <- subset(nad_ol, idents = c("Oligo_A",
"Oligo_B",
"Oligo_C",
"Oligo_D",
"Oligo_E",
"Oligo_F"))
cd_genes <- c("HCN2")
a <- DotPlot(object = oligos, features = cd_genes)
a$data
mean(a$data$pct.exp)
df <- data.frame(modality = c("HCN2_pos", "HCN2_neg"),
percentage = c(mean(a$data$pct.exp),
100- mean(a$data$pct.exp)))
df$gene <- "HCN2"
ggplot(df, aes(x = gene, y=percentage, fill = modality))+
geom_bar(stat="identity")+scale_fill_manual(values= mycoloursP[25:50])
```
Conclusion:
HCN2 expressing oligos are more abundant in CSC compared to BA4. Some but
not all of them are co-expressing SPARC.
```{r}
sessionInfo()
```