update

---

title: "Visualizing single cell data"

author: 

- name: Guangchuang Yu

  email: guangchuangyu@gmail.com

  affiliation: Department of Bioinformatics, School of Basic Medical Sciences, Southern Medical University

date: "`r Sys.Date()`"

output:

  prettydoc::html_pretty:

    theme: cayman

    highlight: github

  pdf_document:

    toc: true

vignette: >

  %\VignetteIndexEntry{Visualizing single cell data}

  %\VignetteEngine{knitr::rmarkdown}

  %\usepackage[utf8]{inputenc}

  %\VignetteEncoding{UTF-8}

---

```{r style, echo=FALSE, results="asis", message=FALSE}

knitr::opts_chunk$set(tidy = FALSE,

                      warning = FALSE,

                      message = FALSE, 

                      fig.width = 9,

                      fig.height = 6)

library(Seurat)

library(ggplot2)

library(scplot)                      

```

```{r}

library(Seurat)

dir = "filtered_gene_bc_matrices/hg19"

pbmc.data <- Read10X(data.dir = dir)

pbmc <- CreateSeuratObject(counts = pbmc.data, project = "pbmc3k", min.cells=3, min.features=200)

pbmc

## Normalizing the data

pbmc <- NormalizeData(pbmc, normalization.method = "LogNormalize", 

                      scale.factor = 10000)

pbmc <- NormalizeData(pbmc)

## Identify the 2000 most highly variable genes

pbmc <- FindVariableFeatures(pbmc, selection.method = "vst", nfeatures = 2000)

## In addition we scale the data

all.genes <- rownames(pbmc)

pbmc <- ScaleData(pbmc, features = all.genes)

pbmc <- RunPCA(pbmc, features = VariableFeatures(object = pbmc), 

               verbose = FALSE)

pbmc <- FindNeighbors(pbmc, dims = 1:10, verbose = FALSE)

pbmc <- FindClusters(pbmc, resolution = 0.5, verbose = FALSE)

pbmc <- RunUMAP(pbmc, dims = 1:10, umap.method = "uwot", metric = "cosine")

## Assigning cell type identity to clusters

new.cluster.ids <- c("Naive CD4 T", "CD14+ Mono", "Memory CD4 T", "B", "CD8 T",

                     "FCGR3A+ Mono", "NK", "DC", "Platelet")

names(new.cluster.ids) <- levels(pbmc)

pbmc <- RenameIdents(pbmc, new.cluster.ids)

```

## Dimensional reduction plot

```{r fig.width=9, fig.height=6}

DimPlot(pbmc, reduction = "umap",

        label = TRUE, pt.size = 0.5) 

library(ggplot2)

library(scplot)

sc_dim(pbmc) + sc_dim_geom_label()

sc_dim(pbmc) + 

    sc_dim_geom_label(geom = shadowtext::geom_shadowtext, 

            color='black', bg.color='white')

```

## Visualize 'features' on a dimensional reduction plot

```{r}

features = c("MS4A1", "GNLY", "CD3E", 

            "CD14", "FCER1A", "FCGR3A", 

            "LYZ", "PPBP", "CD8A")

FeaturePlot(pbmc,'CD4')

FeaturePlot(pbmc, features)

sc_feature(pbmc, 'CD4')

sc_feature(pbmc, features)

```

Here is the real 'features' on dimensional plot

```{r}

sc_dim(pbmc) + 

   sc_dim_geom_feature(pbmc, 'CD4', color='black')

sc_dim(pbmc, alpha=.3) + 

    ggnewscale::new_scale_color() + 

    sc_dim_geom_feature(pbmc, features, mapping=aes(color=features)) +

    scale_color_viridis_d()

```    

## Dot plot

```{r eval=FALSE}

DotPlot(pbmc, features = c("MS4A1", "GNLY", "CD3E", 

                           "CD14", "FCER1A", "FCGR3A", 

                           "LYZ", "PPBP", "CD8A"),

        group.by = 'seurat_clusters')

```        

## Violin plot of gene expression

```{r}

VlnPlot(pbmc,'CD4')

sc_violin(pbmc, 'CD4')

## allows applying an user-defined function to transform/filter the data

sc_violin(pbmc, 'CD4', .fun=function(d) dplyr::filter(d, value > 0))

```

```{r fig.height=9}

VlnPlot(pbmc, features)

sc_violin(pbmc, features)

```