Running Overview and Anno Markdown

Author: phoman14

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: SCWorkflow
 Title: SCWorkflow from NIDAP
 Version: 1.0.2
-Authors@R:  c(person("Maggie", "Cam", email = "maggie.cam@nih.gov", role = "aut", comment = c(ORCID = "0000-0001-8190-9766")), 
+Authors@R: c(person("Maggie", "Cam", email = "maggie.cam@nih.gov", role = "aut", comment = c(ORCID = "0000-0001-8190-9766")), 
     person("Thomas", "Meyer", email = "thomas.meyer@nih.gov", role = c("aut", "cre"), comment = c(ORCID = "0000-0002-7185-5597")), 
     person("Jing", "Bian", email = "bianjh@nih.gov", role = "aut", comment = c(ORCID = "0000-0001-7109-716X")), 
     person("Alexandra", "Michalowski", email = "michaloa@mail.nih.gov", role = "aut", comment = c(ORCID = "0000-0001-9259-6101")),
@@ -18,7 +18,7 @@ Description: A set of functions for analyzing single-cell RNA-seq data using the
 License: MIT
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.3
 Suggests: 
     testthat (>= 3.0.0)
 Depends:

NAMESPACE

@@ -83,13 +83,7 @@ importFrom(dplyr,rename)
 importFrom(dplyr,row_number)
 importFrom(dplyr,select)
 importFrom(dplyr,summarise)
-importFrom(ggExtra,aes)
-importFrom(ggExtra,coord_fixed)
-importFrom(ggExtra,geom_hline)
 importFrom(ggExtra,ggMarginal)
-importFrom(ggExtra,ggtitle)
-importFrom(ggExtra,scale_color_identity)
-importFrom(ggExtra,theme_bw)
 importFrom(ggplot2,aes)
 importFrom(ggplot2,geom_point)
 importFrom(ggplot2,geom_vline)

vignettes/SCWorkflow-Annotations.Rmd

@@ -21,7 +21,11 @@ library(dplyr)
 library(ggplot2)
 library(tibble)
 
-Comb_SO=readRDS("./images/CN_SO.rds")
+Comb_SO=list()
+Comb_SO$object=readRDS("./images/CN_SO.rds")
+evalChunk=F
+
+
 ```
 
 
@@ -32,7 +36,7 @@ This function automates cell type annotation in single-cell RNA sequencing data
 SingleR is an automatic annotation method for single-cell RNA sequencing data that uses a given reference dataset of samples (single-cell or bulk) with known labels to label new cells from a test dataset based on similarity to the reference. Two mouse reference datasets (MouseRNAseqData and ImmGenData) and two human reference datasets (HumanPrimaryCellAtlasData and BlueprintEncodeData) from CellDex R package [2] are currently available.
 
 
-```{r,eval=F}
+```{r,eval=evalChunk}
 Anno_SO=annotateCellTypes(object=Comb_SO$object,
                   species = "Mouse",
                   reduction.type = "umap",
@@ -43,7 +47,7 @@ Anno_SO=annotateCellTypes(object=Comb_SO$object,
 ```
 
 
-```{r,echo=F,eval=F}
+```{r,echo=F,eval=evalChunk}
 saveRDS(Anno_SO, file="./images/Anno_SO.rds")
 
 ggsave(Anno_SO$p1, filename = "./images/Anno1.png", width = 10, height = 10)
@@ -67,7 +71,7 @@ CellType_Anno_Table=read.csv("PerCell_Metadata.csv")
 
 ```
 
-```{r,eval=T,echo=F}
+```{r,eval=evalChunk,echo=F}
 Anno_SO=readRDS("./images/Anno_SO.rds")
 
 
@@ -228,7 +232,7 @@ This function enables users to visualize the association between two selected ge
 
 Furthermore, the tool allows for the application of filters to the data, setting thresholds, and providing annotations to notify users if cells meet the established thresholds. The visualization can be improved by omitting extreme values. The tool also facilitates the creation of a heatmap to represent the density distribution of cells and exhibit the raw gene/protein expression values.
 
-```{r,eval=F,echo=T,results='hide'}
+```{r,eval=evalChunk,echo=T,results='hide'}
 grep('Cd4',rownames(Anno_SO$object@assays$RNA),ignore.case = T,value=T)
 
 DLAnno_SO=dualLabeling(object = Anno_SO$object, 
@@ -261,7 +265,7 @@ plot(DLAnno_SO$plot_densityHM)
 plot(DLAnno_SO$plot_umap)
 ```
 
-```{r,echo=F,eval=F}
+```{r,echo=F,eval=evalChunk}
 png(filename="./images/DL1.png")
 plot(DLAnno_SO$plot_densityHM)
 dev.off()
@@ -289,41 +293,43 @@ The output of this function is a detailed figure showing the activity of chosen
 Marker_Table <- read.csv("Marker_Table_demo.csv")
 ```
 
-```{r,eval=T,echo=F}
+```{r,eval=evalChunk,echo=F}
 Marker_Table_demo <- read.csv("../tests/testthat/fixtures/Marker_Table_demo.csv")
 Marker_Table_demo%>%head()%>%
   knitr::kable()
 
 Marker_Table=Marker_Table_demo[1:4,]
 ```
 
-```{r,eval=F,echo=T,results='hide'}
+```{r,eval=evalChunk,echo=T,results='hide',fig.width=10,fig.asp=.9}
     
-FigOut=colorByMarkerTable(object=Anno_SO$object,
+  colorByMarkerTable(object=Anno_SO$object,
                    samples.subset=c("PBS","ENT","NHSIL12", "Combo","CD8dep" ),
                    samples.to.display=c("PBS","ENT","NHSIL12", "Combo","CD8dep" ),
                    marker.table=Marker_Table,
-                   cells.of.interest=c("Macrophages","M1","M2" ),
+                   cells.of.interest=c("Neutrophils","Macrophages","CD8_T" ),
                    protein.presence = FALSE,
                    assay = "SCT",
                    reduction.type = "umap",
                    point.transparency = 0.5,
                    point.shape = 16,
                    cite.seq = FALSE
                    )
-plot(FigOut)
+
 
 ```
 
-```{r,echo=F,eval=F}
+```{r,echo=F,eval=evalChunk}
 png(filename="./images/CBM1.png",width=1000,height=700)
-plot(FigOut)
+FigOut
 dev.off()
 
 ```
 
-![](./images/CBM1.png){width=600}
-
+<!-- ![](./images/CBM1.png){width=400} -->
+<p align="center" width="100%">
+    <img width="66%" src="./images/CBM1.png">
+</p>
 
 
 ## Module Score Cell Classification
@@ -334,23 +340,29 @@ This function can be used to quantify the expression of marker sets in each indi
 
 This function aids in identifying cell types based on average gene expression. It uses a feature of the Seurat software known as the AddModuleScore function. This function calculates the gene expression of specific sets and records them within a designated area of the Seurat object. The program then forecasts cell identities by comparing these recorded scores across various gene sets. You have the ability to adjust the identification process by designating cutoff points for a bimodal distribution in a parameter known as manual threshold. Any thresholds below this cutoff will not be considered during the identification process.
 
-**Inputs:** The program takes several inputs. These include the single-cell RNA sequencing (scRNA-seq) object, a selection of samples for analysis, a table of gene markers for different cell types, and optionally, a hierarchical table for directing the order of cell classification.
-**Data Preparation:** The program prepares the scRNA-seq object, assigns names to the samples, and selects data based on your specified samples.
-**Module Score Calculation:** The program calculates module scores, a measure of gene set activity or expression [1], for each cell type based on your provided marker table.
+**Inputs:** The program takes several inputs. These include the single-cell RNA sequencing (scRNA-seq) object, a selection of samples for analysis, a table of gene markers for different cell types, and optionally, a hierarchical table for directing the order of cell classification. 
+
+**Data Preparation:** The program prepares the scRNA-seq object, assigns names to the samples, and selects data based on your specified samples. 
+
+**Module Score Calculation:** The program calculates module scores, a measure of gene set activity or expression [1], for each cell type based on your provided marker table. 
+
 **Visualization:** Density distribution plots and colored reduction plots will be generated to help you visualize the module scores, their relationship with cell types, and sample identities.
-**Thresholding:** Users can select threshold values to aid in the classification of cells. Cells with scores below your designated threshold will be labeled as "unknown".
+
+**Thresholding:** Users can select threshold values to aid in the classification of cells. Cells with scores below your designated threshold will be labeled as "unknown". 
+
 Subclass Identification: If desired, the program can identify subclasses within cell types by further analyzing subpopulations. 
-**Updating Cell Type Labels:** The program appends a "Likely_CellType" column to the metadata of the scRNA-seq object, based on the results of the module score analysis.
+**Updating Cell Type Labels:** The program appends a "Likely_CellType" column to the metadata of the scRNA-seq object, based on the results of the module score analysis. 
+
 **Output:** An updated scRNA-seq object with new cell type labels.
 
-```{r,eval=F}
+```{r,eval=evalChunk}
 
 MS_object=modScore(object=Anno_SO$object, 
-                   marker.table=Marker_Table[,c("Macrophages","M1","M2" )], 
-                   ms.threshold=c("Macrophages .40","M1 .25","M2 .14"), 
-                   use_assay = "SCT",
-                   general.class=c("Macrophages"), 
-                   lvl.vec = c('Macrophages-M1','Macrophages-M2'), 
+                   marker.table=Marker_Table,
+                   use_columns = c("Neutrophils","Macrophages","CD8_T" ),
+                   ms_threshold=c("Neutrophils .25","Macrophages .40","CD8_T .14"), 
+                   general.class=c("Neutrophils","Macrophages","CD8_T"), 
+                   multi.lvl = FALSE, 
                    reduction = "umap",
                    nbins = 10, 
                    gradient.ft.size = 6,
@@ -361,7 +373,7 @@ MS_object=modScore(object=Anno_SO$object,
 ```
 ![](./images/MS1.png){width=600}
 
-![](./images/MS2.png){width=300} ![](./images/MS3.png){width=300}
+<!-- ![](./images/MS2.png){width=300} ![](./images/MS3.png){width=300} -->
 
 
 
@@ -377,9 +389,10 @@ This function creates a dot plot visualization of cell types by metadata categor
 It also generates a dot plot using Seurat's Dotplot function [3], providing a visual representation of the percentage of various cell types within each cluster.  Typically, a cluster can be more distinctively named by the predominant cell type as seen in the dotplot.  The plot's order can be customized for the clusters and cell types. If no specific order is provided, the function uses a default order.
 An optional parameter allows the user to make the plot interactive. The function returns the updated Seurat object and the plot.
 
-```{r,eval=F}
+```{r,eval=evalChunk}
 
 RNC_object=nameClusters(object=Anno_SO$object,
+                          cluster.identities.table=
                          cluster.numbers= c(0,1,2,3,4,5,6,7),
                          cluster.names=c("Pop0", "Pop1", "Pop2", "Pop3","Pop4", "Pop5", "Pop6", "Pop7"),
                          cluster.column ="SCT_snn_res.0.2",
@@ -421,13 +434,12 @@ In addition to the plot, the function provides the tabular format of the dot plo
 This function can be useful for exploratory data analysis and visualizing the differences in gene expression across different conditions or groups of cells.
 
 
-```{r,eval=F}
+```{r,eval=evalChunk}
 
 FigOut=dotPlotMet(object=Anno_SO$object,
                    metadata="orig.ident",
                    cells=c("PBS","ENT","NHSIL12", "Combo","CD8dep" ),
                    markers=Marker_Table$Macrophages,
-                   use_assay = "SCT",
                    plot.reverse = FALSE,
                    cell.reverse.sort = FALSE,
                    dot.color = "darkblue"

vignettes/SCWorkflow-Overview.Rmd

@@ -20,7 +20,7 @@ library(data.table)
 library(dplyr)
 library(ggplot2)
 
-evalChunk=T
+evalChunk=F
 ```