Skip to content

Commit

Permalink
Minor updates to the vignettes.
Browse files Browse the repository at this point in the history
  • Loading branch information
@PratibhaPanwar
PratibhaPanwar committed Sep 8, 2024
1 parent 6b04c97 commit b0de42b
Show file tree
Hide file tree
Showing 2 changed files with 43 additions and 43 deletions.
42 changes: 21 additions & 21 deletions vignettes/v1_seqFISH_mouseEmbryo.Rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9,9 +9,9 @@ output:
BiocStyle::pdf_document: default
package: clustSIGNAL
vignette: |
%\VignetteIndexEntry{Single sample analysis}
%\VignetteEngine{knitr::rmarkdown}
%\VignetteEncoding{UTF-8}
%\VignetteEngine{knitr::rmarkdown}
%\VignetteIndexEntry{Single sample analysis}
%\VignetteEncoding{UTF-8}
---

```{r, include = FALSE}
Expand All @@ -38,7 +38,7 @@ library(patchwork)

```{r}
data(mEmbryo2)
spe = SpatialExperiment(assays = list(logcounts = me_expr),
spe <- SpatialExperiment(assays = list(logcounts = me_expr),
colData = me_data, spatialCoordsNames = c("X", "Y"))
spe
```
Expand All @@ -53,9 +53,9 @@ To run clustSIGNAL, we need the column names of sample and cell labels in the co

```{r}
set.seed(100)
samples = "sample_id"
cells = "uniqueID"
res_emb = clustSIGNAL(spe, samples, cells, outputs = "a")
samples <- "sample_id"
cells <- "uniqueID"
res_emb <- clustSIGNAL(spe, samples, cells, outputs = "a")
```

The output variable is a list that can contain dataframe of cluster names, matrix of NN neighbours of each cell, final spe object, or a combination of these, depending on the choice of 'outputs' selected.
Expand All @@ -69,7 +69,7 @@ head(res_emb$clusters, n = 3)
```

```{r}
spe = res_emb$spe_final
spe <- res_emb$spe_final
spe
```

Expand All @@ -83,7 +83,7 @@ distMat <- distances(cXg_mat)
silCluster <- as.matrix(silhouette(clusts, distMat))
spe$rcSil <- silCluster[, 3]
# for datasets with annotated cell type information, we can also calculate
# for datasets with annotated cell type information, we can also calculate
# metrics like adjusted rand index (ARI) and normalised mutual information (NMI)
as.data.frame(colData(spe)) %>%
summarise(ARI = aricode::ARI(celltype_mapped_refined, reCluster),
Expand All @@ -97,7 +97,7 @@ as.data.frame(colData(spe)) %>%
# Visualising clustSIGNAL outputs

```{r}
colors = c("#635547", "#8EC792", "#9e6762", "#FACB12", "#3F84AA", "#0F4A9C",
colors <- c("#635547", "#8EC792", "#9e6762", "#FACB12", "#3F84AA", "#0F4A9C",
"#ff891c", "#EF5A9D", "#C594BF", "#DFCDE4", "#139992", "#65A83E",
"#8DB5CE", "#005579", "#C9EBFB", "#B51D8D", "#532C8A", "#8870ad",
"#cc7818", "#FBBE92", "#EF4E22", "#f9decf", "#c9a997", "#C72228",
Expand All @@ -121,9 +121,9 @@ hst_ent <- as.data.frame(colData(spe)) %>%
# Spatial plot showing sample entropy distribution
spt_ent <- as.data.frame(colData(spe)) %>%
ggplot(aes(x = spatialCoords(spe)[, 1],
ggplot(aes(x = spatialCoords(spe)[, 1],
y = -spatialCoords(spe)[, 2])) +
geom_point(size = 0.5,
geom_point(size = 0.5,
aes(colour = entropy)) +
scale_colour_gradient2("Entropy", low = "grey", high = "blue") +
scale_size_continuous(range = c(0, max(spe$entropy))) +
Expand All @@ -140,33 +140,33 @@ The spread (A) and spatial distribution (B) of region entropy measures can be ve
## clustSIGNAL clusters visualisation

```{r}
df_ent = as.data.frame(colData(spe))
df_ent <- as.data.frame(colData(spe))
# spatial plot
spt_clust <- df_ent %>%
ggplot(aes(x = spatialCoords(spe)[, 1],
ggplot(aes(x = spatialCoords(spe)[, 1],
y = -spatialCoords(spe)[, 2])) +
geom_point(size = 0.5, aes(colour = reCluster)) +
scale_color_manual(values = colors) +
ggtitle("A") +
labs(x = "x-coordinate", y = "y-coordinate") +
guides(color = guide_legend(title = "Clusters",
guides(color = guide_legend(title = "Clusters",
override.aes = list(size = 3))) +
theme_classic() +
theme(text = element_text(size = 12))
# calculating median entropy of each cluster
celltype_ent = df_ent %>%
celltype_ent <- df_ent %>%
group_by(as.character(reCluster)) %>%
summarise(meanEntropy = median(entropy))
# reordering clusters by their median entropy
# low to high median entropy
cellOrder = celltype_ent$meanEntropy
names(cellOrder) = celltype_ent$`as.character(reCluster)`
cellOrder = sort(cellOrder)
df_ent$reCluster = factor(df_ent$reCluster, levels = names(cellOrder))
cellOrder <- celltype_ent$meanEntropy
names(cellOrder) <- celltype_ent$`as.character(reCluster)`
cellOrder <- sort(cellOrder)
df_ent$reCluster <- factor(df_ent$reCluster, levels = names(cellOrder))
# box plot of cluster entropy
colors_ent = colors[as.numeric(names(cellOrder))]
colors_ent <- colors[as.numeric(names(cellOrder))]
box_clust <- df_ent %>%
ggplot(aes(x = reCluster, y = entropy, fill = reCluster)) +
geom_boxplot() +
Expand Down
44 changes: 22 additions & 22 deletions vignettes/v2_MERFISH_mouseHypothalamus.Rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ library(patchwork)

```{r}
data(mHypothal)
spe = SpatialExperiment(assays = list(logcounts = mh_expr),
spe <- SpatialExperiment(assays = list(logcounts = mh_expr),
colData = mh_data, spatialCoordsNames = c("X", "Y"))
spe
```
Expand All @@ -53,13 +53,13 @@ To run clustSIGNAL, we need the column names of sample and cell IDs in the colDa

```{r}
set.seed(101)
samples = "samples"
cells = "Cell_ID"
res_hyp = clustSIGNAL(spe, samples, cells, outputs = "a")
samples <- "samples"
cells <- "Cell_ID"
res_hyp <- clustSIGNAL(spe, samples, cells, outputs = "a")
```

```{r}
spe = res_hyp$spe_final
spe <- res_hyp$spe_final
spe
```

Expand All @@ -84,7 +84,7 @@ spe$rcSil <- silWidthRC[, 3]
```

```{r}
# for datasets with annotated cell type information, we can also calculate
# for datasets with annotated cell type information, we can also calculate
# metrics like adjusted rand index (ARI) and normalised mutual information (NMI)
as.data.frame(colData(spe)) %>%
group_by(samples) %>%
Expand All @@ -99,7 +99,7 @@ as.data.frame(colData(spe)) %>%
# Visualising clustSIGNAL outputs

```{r}
colors = c("#635547", "#8EC792", "#9e6762", "#FACB12", "#3F84AA", "#0F4A9C",
colors <- c("#635547", "#8EC792", "#9e6762", "#FACB12", "#3F84AA", "#0F4A9C",
"#ff891c", "#EF5A9D", "#C594BF", "#DFCDE4", "#139992", "#65A83E",
"#8DB5CE", "#005579", "#C9EBFB", "#B51D8D", "#532C8A", "#8870ad",
"#cc7818", "#FBBE92", "#EF4E22", "#f9decf", "#c9a997", "#C72228",
Expand All @@ -123,16 +123,16 @@ hst_ent <- as.data.frame(colData(spe)) %>%
# Spatial plot showing sample entropy distribution
spt_ent <- as.data.frame(colData(spe)) %>%
ggplot(aes(x = spatialCoords(spe)[, 1],
ggplot(aes(x = spatialCoords(spe)[, 1],
y = -spatialCoords(spe)[, 2])) +
geom_point(size = 0.5,
geom_point(size = 0.5,
aes(colour = entropy)) +
scale_colour_gradient2("Entropy", low = "grey", high = "blue") +
scale_size_continuous(range = c(0, max(spe$entropy))) +
facet_wrap(vars(samples), scales = "free", nrow = 1) +
labs(x = "x-coordinate", y = "y-coordinate") +
theme_classic() +
theme(strip.text = element_blank(),
theme(strip.text = element_blank(),
text = element_text(size = 12),
axis.text.x = element_text(angle = 90, vjust = 0.5))
hst_ent / spt_ent + plot_layout(heights = c(3,5)) +
Expand All @@ -144,40 +144,40 @@ In multisample analysis, the spread (A) and spatial distribution (B) of region e
## clustSIGNAL clusters visualisation

```{r}
df_ent = as.data.frame(colData(spe))
df_ent <- as.data.frame(colData(spe))
```

```{r}
# spatial plot
spt_clust <- df_ent %>%
ggplot(aes(x = spatialCoords(spe)[, 1],
ggplot(aes(x = spatialCoords(spe)[, 1],
y = -spatialCoords(spe)[, 2])) +
geom_point(size = 0.5, aes(colour = reCluster)) +
scale_color_manual(values = colors) +
facet_wrap(vars(samples), scales = "free", nrow = 1) +
labs(x = "x-coordinate", y = "y-coordinate") +
guides(color = guide_legend(title = "Clusters",
guides(color = guide_legend(title = "Clusters",
override.aes = list(size = 3))) +
theme_classic() +
theme(text = element_text(size = 12),
axis.text.x = element_text(angle = 90, vjust = 0.5))
box_clust = list()
box_clust <- list()
for (s in samplesList) {
df_ent_sub = as.data.frame(colData(spe)[spe[[samples]] == s, ])
df_ent_sub <- as.data.frame(colData(spe)[spe[[samples]] == s, ])
# calculating median entropy of each cluster in a sample
celltype_ent = df_ent_sub %>%
celltype_ent <- df_ent_sub %>%
group_by(as.character(reCluster)) %>%
summarise(meanEntropy = median(entropy))
# reordering clusters by their median entropy
# low to high median entropy
cellOrder = celltype_ent$meanEntropy
names(cellOrder) = celltype_ent$`as.character(reCluster)`
cellOrder <- celltype_ent$meanEntropy
names(cellOrder) <- celltype_ent$`as.character(reCluster)`
cellOrder = sort(cellOrder)
df_ent_sub$reCluster = factor(df_ent_sub$reCluster, levels = names(cellOrder))
df_ent_sub$reCluster <- factor(df_ent_sub$reCluster, levels = names(cellOrder))
# box plot of cluster entropy
colors_ent = colors[as.numeric(names(cellOrder))]
colors_ent <- colors[as.numeric(names(cellOrder))]
box_clust[[s]] <- df_ent_sub %>%
ggplot(aes(x = reCluster, y = entropy, fill = reCluster)) +
geom_boxplot() +
Expand All @@ -186,7 +186,7 @@ for (s in samplesList) {
labs(x = "clustSIGNAL clusters", y = "Entropy") +
ylim(0, NA) +
theme_classic() +
theme(strip.text = element_blank(),
theme(strip.text = element_blank(),
legend.position = "none",
text = element_text(size = 12),
axis.text.x = element_text(angle = 90, vjust = 0.5))
Expand Down

0 comments on commit b0de42b

Please sign in to comment.