update with new readme info

.gitignore

@@ -2,4 +2,5 @@
 .Rhistory
 .RData
 .Ruserdata
-*.Rproj
+*.Rproj
+test/*

R/bcbioR-package.R

@@ -2,6 +2,7 @@
 "_PACKAGE"
 
 ## usethis namespace: start
+#' @importFrom magrittr %>%
 #' @importFrom stringr str_replace_all
 ## usethis namespace: end
 #' @import ggplot2

inst/rmarkdown/templates/rnaseq/skeleton/reports/DEG/DEG.Rmd → inst/rmarkdown/templates/rnaseqv2/skeleton/DE/DEG.Rmd

@@ -20,11 +20,12 @@ params:
   numerator: tumor
   denominator: normal
   subset_value: NA
-  params_file: ./inst/rmarkdown/templates/rnaseq/skeleton/params_de.R
+  params_file: params_de.R
 ---
 
 ```{r load_params, echo = F}
 source(params$params_file)
+source(params$project_file)
 ```
 
 ```{r load_libraries, cache = FALSE, message = FALSE, warning=FALSE, echo=FALSE,}
@@ -84,13 +85,13 @@ if (!is.na(params$subset_value)){
 
 contrasts = c(column,params$numerator,params$denominator)
 
-name_expression_fn=file.path(root,
+name_expression_fn=file.path(
                              basedir,
                              str_interp("${filenames}_expression.csv"))
-name_deg_fn=file.path(root,
+name_deg_fn=file.path(
                       basedir,
                       str_interp("${filenames}_deg.csv"))
-name_pathways_fn=file.path(root,
+name_pathways_fn=file.path(
                            basedir,
                            str_interp("${filenames}_pathways.csv"))
 

inst/rmarkdown/templates/rnaseq/skeleton/params_de.R → inst/rmarkdown/templates/rnaseqv2/skeleton/DE/params_de.R

@@ -1,16 +1,8 @@
-# info params
-project = "name_hbcXXXXX"
-PI = 'person name'
-experiment = 'short description'
-aim = 'short description'
-analyst = 'person in the core'
-
 # project params
-root = "../.."
 date = "YYYYMMDD"
 column = "sample_type"
 subset_column = NA
 coldata_fn = "https://raw.githubusercontent.com/bcbio/bcbioR-test-data/main/rnaseq/bcbio/coldata.csv"
 counts_fn = 'https://raw.githubusercontent.com/bcbio/bcbioR-test-data/main/rnaseq/bcbio/tximport-counts.csv'
 se_object=url("https://raw.githubusercontent.com/bcbio/bcbioR-test-data/main/rnaseq/bcbio/bcbio-se.rds")
-basedir <- 'results'
+basedir <- './'

inst/rmarkdown/templates/rnaseq/skeleton/reports/DEG/run_markdown.R → inst/rmarkdown/templates/rnaseqv2/skeleton/DE/run_markdown.R

@@ -3,8 +3,8 @@ library(rmarkdown)
 render_de <- function(numerator, denominator, subset_value = NA, 
                       params_file = '../../params_de.R'){
 
-  rmarkdown::render(input = "./inst/rmarkdown/templates/rnaseq/skeleton/reports/DEG/DEG.Rmd",
-                    output_dir = "./inst/rmarkdown/templates/rnaseq/skeleton/reports/DEG/",
+  rmarkdown::render(input = "DEG.Rmd",
+                    output_dir = "./",
                     output_format = "html_document",
                     output_file = ifelse(!is.na(subset_value), 
                                          paste0('DE_', subset_value, '_', numerator, '_vs_', denominator, '.html'),
@@ -16,7 +16,8 @@ render_de <- function(numerator, denominator, subset_value = NA,
                       subset_value = subset_value,
                       numerator = numerator,
                       denominator = denominator,
-                      params_file = params_file
+                      params_file = params_file,
+                      project_file = '../information.R'
                     )
   )
 }

inst/rmarkdown/templates/rnaseq/skeleton/reports/QC/QC.Rmd → inst/rmarkdown/templates/rnaseqv2/skeleton/QC/QC.Rmd

@@ -17,12 +17,14 @@ output:
 editor_options: 
   chunk_output_type: console
 params:
-  params_file: ./inst/rmarkdown/templates/rnaseq/skeleton/params_qc.R
+  params_file: params_qc.R
+  project_file: ../information.R
 ---
 
 
 ```{r source_params, echo = F}
 source(params$params_file)
+source(params$project_file)
 ```
 
 ```{r load_libraries, cache = FALSE, message = FALSE, warning=FALSE}
@@ -405,4 +407,4 @@ List and version of tools used for the QC report generation.
 
 ```{r}
 sessionInfo()
-```
+```

inst/rmarkdown/templates/rnaseq/skeleton/params_qc.R → inst/rmarkdown/templates/rnaseqv2/skeleton/QC/params_qc.R

@@ -1,10 +1,4 @@
 # info params
-project = "name_hbcXXXXX"
-PI = 'person name'
-experiment = 'short description'
-aim = 'short description'
-analyst = 'person in the core'
-
 
 metadata_fn='https://raw.githubusercontent.com/bcbio/bcbioR-test-data/main/rnaseq/bcbio/coldata.csv'
 se_object=url("https://raw.githubusercontent.com/bcbio/bcbioR-test-data/main/rnaseq/bcbio/bcbio-se.rds")

inst/rmarkdown/templates/rnaseqv2/skeleton/QC/run_markdown.R

@@ -0,0 +1,10 @@
+library(rmarkdown)
+
+rmarkdown::render("QC.Rmd",
+                  output_dir = "./", 
+                  clean = TRUE,
+                  output_format = "html_document",
+                  params = list(
+                    params_file = 'params_qc.R',
+                    project_file = '../information.R')
+                  )

inst/rmarkdown/templates/rnaseqv2/skeleton/README.md

@@ -0,0 +1,23 @@
+# Guideline for RNAseq downstream analysis
+
+# DropBox
+
+- In `reports/QC`
+  - [ ] copy `bcbio-se.rds` and `tximport-counts.csv`
+  - [ ] copy QC `Rmd/R/html/figures`
+- In `reports/DE`
+  -	[ ] Normalized counts for all genes x all samples (csv format)
+- In `reports/DE`, for *each analysis*:
+  - **Note** For multiple comparisons/analysis, do a single report/template if possible in the parent folder using parameters whenever possible. 
+  - Create a folder with the comparison names in the files. Numbering by comparison (`01.1_DE_comp1`, `01.2_DE_comp2`, etc.). If you’re running multiple models for the same comparison, append `_M#`. Add the following files under each folder:
+  - [ ] Normalized count table with the samples used in this analysis/comparison.
+  -	[ ] Full results `DESeq2` for all genes (csv format) with annotation columns appended. 
+  -	[ ] Significant genes results file (subset of annotated full results by chosen p-value and LFC). Separate files will be created for each individual contrast.
+  -	[ ] Significant genes results file as described above, but additionally append columns containing normalized count values for each sample.
+  -	Make sure to append the gene symbols to these tables so the researcher can interpret the results.
+
+# GitHub
+
+- [ ] Push all `*Rmd` `*R` files used for the *QC* and *DE* analysis respecting folder structure.
+
+Please, ignore `*html/figures/csv` and any output of the code.

inst/rmarkdown/templates/rnaseqv2/skeleton/information.R

@@ -0,0 +1,6 @@
+# info params
+project = "name_hbcXXXXX"
+PI = 'person name'
+experiment = 'short description'
+aim = 'short description'
+analyst = 'person in the core'

inst/rmarkdown/templates/rnaseq/skeleton/skeleton.Rmd → inst/rmarkdown/templates/rnaseqv2/skeleton/skeleton.Rmd

@@ -17,7 +17,7 @@ output:
 editor_options: 
   chunk_output_type: console
 params:
-  params_file: params_de.R
+  params_file: information.R
 ---
 
 ```{r echo = F}

inst/rmarkdown/templates/rnaseq/template.yaml → inst/rmarkdown/templates/rnaseqv2/template.yaml

@@ -1,3 +1,3 @@
 name: bcbio RNAseq
 description: Standard RNAseq down-stream analyses
-create_dir: true
+create_dir: false

inst/rmarkdown/templates/singlecell/skeleton/Integration/helpers.R

@@ -0,0 +1,61 @@
+# some code showing integrating two seurat objects
+library(Seurat)
+library(tidyverse)
+library(harmony)
+
+# We assume exp1 and exp2 has a Group column with naming the sample groups
+# We create a batch annotation for each batch
+exp1=readRDS("data/exp1.rds")
+exp1$batch="n10"
+exp2=readRDS("data/exp2.rds")
+exp2$batch="n6"
+
+# Normalize ----
+exp = SCTransform(exp, verbose = FALSE,conserve.memory=TRUE,
+                  variable.features.n = 3000)
+exp <- RunPCA(exp)
+ElbowPlot(exp,ndims=40)
+end_dimension=35
+resolution=0.5
+
+# Clustering for each batch ----
+exp <- FindNeighbors(exp, dims = 1:end_dimension, reduction = "pca")
+exp <- FindClusters(exp, resolution = resolution, cluster.name = "unintegrated_clusters")
+exp <- RunUMAP(exp, dims = 1:end_dimension, reduction = "pca", reduction.name = "umap.unintegrated")
+saveRDS(exp, file="data/merged_umap.rds")
+
+## Plot by batch----
+DimPlot(exp, reduction = "umap.unintegrated", split.by = c("Group"),
+        group.by = c("batch"))
+
+# Integration ----
+exp <- IntegrateLayers(
+  object = exp, method = HarmonyIntegration,
+  orig.reduction = "pca", new.reduction = "harmony",
+  verbose = FALSE
+)
+exp[["RNA"]] <- JoinLayers(exp[["RNA"]])
+end_dimension=35
+resolution=0.5
+exp <- FindNeighbors(exp, reduction = "harmony", dims = 1:end_dimension)
+exp <- FindClusters(exp, resolution = resolution, cluster.name = "harmony_clusters")
+exp <- RunUMAP(exp, reduction = "harmony", dims = 1:end_dimension, reduction.name = "umap.harmony")
+saveRDS(exp, file="data/integrated_harmony.rds")
+
+## Plot by Group and Cluster ----
+DimPlot(
+  exp,
+  reduction = "umap.harmony",
+  split.by = c("Group"),
+  group.by = c("batch"),
+  combine = TRUE, label.size = 2
+)
+
+DimPlot(
+  exp,
+  reduction = "umap.harmony",
+  split.by = c("Group"),
+  group.by = c("ident"),
+  combine = TRUE, label.size = 2
+)
+

inst/rmarkdown/templates/singlecell/skeleton/README.md

@@ -0,0 +1,17 @@
+# Tipical steps for scRNAseq downstream analysis
+
+# DropBox
+
+-   In `reports/QC`
+    -   [ ] copy QC `Rmd/R/html/figures`
+-   In `reports/Clusters`
+    -   [ ] the analysis of `SCTransform`, ,`RunPCA` ,`FindNeighbors`, ,`FindClusters`, `RunUMAP`
+    - [ ] the analysis of `FindMarkers` and `Cell Identification`
+-   In `reports/DE`, for *each analysis*:
+    -   TBD
+
+# GitHub
+
+-   [ ] Push all `*Rmd` `*R` files used for the *QC* and *DE* analysis respecting folder structure.
+
+Please, ignore `*html/figures/csv` and any output of the code.

inst/rmarkdown/templates/singlecell/skeleton/information.R

@@ -0,0 +1,8 @@
+# project params
+root = "../"
+date = "YYYYMMDD"
+column = "treatment"
+subset_column = 'cell'
+metadata_fn = "../meta/samplesheet.csv"
+counts_fn = '../data/tximport-counts.csv'
+basedir <- 'reports'

inst/rmarkdown/templates/singlecell/skeleton/skeleton.Rmd

@@ -0,0 +1,25 @@
+---
+title: "General Project Information"
+author: "Harvard Chan Bioinformatics Core"
+date: "`r Sys.Date()`"
+output:
+   html_document:
+      code_folding: hide
+      df_print: paged
+      highlights: pygments
+      number_sections: true
+      self_contained: true
+      theme: default
+      toc: true
+      toc_float:
+         collapsed: true
+         smooth_scroll: true
+editor_options: 
+  chunk_output_type: console
+params:
+  params_file: information.R
+---
+
+```{r echo = F}
+source(params$params_file)
+```

inst/rmarkdown/templates/singlecell/template.yml

@@ -0,0 +1,3 @@
+name: bcbio scRNAseq
+description: Standard scRNAseq down-stream analyses
+create_dir: false