docker file update

Dockerfile

@@ -194,10 +194,13 @@ COPY ./poststart.sh /home/jovyan
 
 # add course files
 COPY course_files /home/jovyan
-COPY case_study_data/case_study.Rmd /home/jovyan/
-COPY case_study_data/pre_processing_fq.Rmd /home/jovyan/
+COPY case_study_data /home/jovyan/case_study_data
+RUN ls -la /home/jovyan/
 
-COPY mig-sc-workshop-2019-data.tar.gz  /home/jovyan/data/
+COPY mig_2019_scrnaseq-workshop-data.tar.gz /home/jovyan
+RUN tar -xzvf mig_2019_scrnaseq-workshop-data.tar.gz -C /home/jovyan/data/ && rm mig_2019_scrnaseq-workshop-data.tar.gz
+RUN ls -la /home/jovyan/data/
+#COPY mig-sc-workshop-2019-data.tar.gz  /home/jovyan/data/
 # cp data/droplet_id_example_per_barcode.txt.gz  /home/jovyan/data/ && \
 #     cp data/pancreas -r  /home/jovyan/data/ && \
 #     cp data/tung -r /home/jovyan/data/ && \

case_study_data/case_study.Rmd

@@ -29,7 +29,7 @@ mkdir LD_cr_counts
 cd LD_cr_counts
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/samples/GSM3612nnn/GSM3612832/suppl/GSM3612832_LD_genes.tsv.gz
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/samples/GSM3612nnn/GSM3612832/suppl/GSM3612832_LD_barcodes.tsv.gz
-wget ftp://ftp.ncbi.nlm.nih.gov/geo/samples/GSM3612nnn/GSM3612832/suppl/GSM3612831_LD_matrix.mtx.gz
+wget ftp://ftp.ncbi.nlm.nih.gov/geo/samples/GSM3612nnn/GSM3612832/suppl/GSM3612832_LD_matrix.mtx.gz
 
 cd ..
 mkdir Ctrl_cr_counts
@@ -52,9 +52,9 @@ library(Matrix)
 
 ### Read in control cells 
 
-cellbarcodes <- read.table("../case_study_data/retinal/GEO_downloads/Ctrl/GSM3612831_ctrl_barcodes.tsv.gz",stringsAsFactors = FALSE)
-genenames <- read.table("../case_study_data/retinal/GEO_downloads/Ctrl/GSM3612831_ctrl_genes.tsv.gz",stringsAsFactors = FALSE)
-molecules <- readMM("../case_study_data/retinal/GEO_downloads/Ctrl/GSM3612831_ctrl_matrix.mtx.gz")
+cellbarcodes <- read.table("./case_study_data/retinal/GEO_downloads/Ctrl/GSM3612831_ctrl_barcodes.tsv.gz",stringsAsFactors = FALSE)
+genenames <- read.table("./case_study_data/retinal/GEO_downloads/Ctrl/GSM3612831_ctrl_genes.tsv.gz",stringsAsFactors = FALSE)
+molecules <- readMM("./case_study_data/retinal/GEO_downloads/Ctrl/GSM3612831_ctrl_matrix.mtx.gz")
 
 
 head(cellbarcodes)
@@ -74,9 +74,9 @@ sce_ctrl <- SingleCellExperiment(
 sce_ctrl
 
 ## Read in LD cells
-cellbarcodes <- read.table("../case_study_data/retinal/GEO_downloads/LD/GSM3612832_LD_barcodes.tsv.gz",stringsAsFactors = FALSE)
-genenames <- read.table("../case_study_data/retinal/GEO_downloads/LD/GSM3612832_LD_genes.tsv.gz",stringsAsFactors = FALSE)
-molecules <- readMM("../case_study_data/retinal/GEO_downloads/LD/GSM3612832_LD_matrix.mtx.gz")
+cellbarcodes <- read.table("./case_study_data/retinal/GEO_downloads/LD/GSM3612832_LD_barcodes.tsv.gz",stringsAsFactors = FALSE)
+genenames <- read.table("./case_study_data/retinal/GEO_downloads/LD/GSM3612832_LD_genes.tsv.gz",stringsAsFactors = FALSE)
+molecules <- readMM("./case_study_data/retinal/GEO_downloads/LD/GSM3612832_LD_matrix.mtx.gz")
 
 
 head(cellbarcodes)
@@ -246,6 +246,15 @@ plot(sce_cr$total_features_by_counts, sce_cr$pct_counts_Mito,
 
 sce_cr <- sce_cr[, keep]
 table(sce_cr$Sample)
+# relations of QC metrics respect to each other ( in rough aggreement)
+par(mfrow=c(1,2))
+plot(sce_cr$total_features_by_counts, sce_cr$total_counts/1e6,
+     xlab="Number of expressed genes",
+     ylab="Library size (millions)")
+plot(sce_cr$total_features_by_counts, sce_cr$pct_counts_Mito,
+     xlab="Number of expressed genes",
+     ylab="Mitochondrial proportion (%)")
+
 ```
 
 ### Doublets

course_files/exprs-qc.Rmd

@@ -113,6 +113,8 @@ umi <- calculateQCMetrics(
         MT = isSpike(umi, "MT")
     )
 )
+umi
+colData(umi)
 ```
 
 
@@ -218,6 +220,8 @@ filter_by_ERCC <- umi$batch != "NA19098.r2"
 table(filter_by_ERCC)
 filter_by_MT <- umi$pct_counts_MT < 10
 table(filter_by_MT)
+filter_by_total_counts <- umi$total_counts > 25000
+#filter_by_expr_features <- umi$total_features_by_counts <7000
 ```
 
 __Exercise 4__
@@ -247,6 +251,7 @@ umi$use <- (
 )
 ```
 
+
 ```{r}
 table(umi$use)
 ```

course_files/pseudotime.Rmd

@@ -319,7 +319,7 @@ There are different ways of implementing the RGE framework, `Monocle 2` uses `DD
 
 DDRTree returns a principal tree of the centroids of cell clusters in low dimension, pseudotime is derived for individual cells by calculating geomdestic distance of their projections onto the tree from the root (user-defined or arbitrarily assigned).
 
-__Note__ Informally, a principal graph is like a principal curve which passes through the ‘middle’ of a data set but is
+_Note_ Informally, a principal graph is like a principal curve which passes through the ‘middle’ of a data set but is
 allowed to have branches.
 
 ```{r monocle2-all-genes, message=FALSE, warning=FALSE,include=TRUE}