update

.Rhistory

@@ -1,15 +1,3 @@
-loh.name.mapping <-  scell_gbm$loh.name.mapping
-## generate annotation data.frame
-annotation <- generateAnnotation(id_type="hgnc_symbol", genes=rownames(data), ishg19=T, centromere, host="uswest.ensembl.org")
-data <- data[match(annotation$Gene,rownames(data)), ]
-dim(data)
-object <- CreateCasperObject(raw.data=data,loh.name.mapping=loh.name.mapping,
-sequencing.type="single-cell",
-cnv.scale=3, loh.scale=3,expr.cutoff=0.1,matrix.type="normalized", filter="median",
-annotation=annotation, method="iterative", loh=loh,
-control.sample.ids="REF", cytoband=cytoband)
-[email protected]
-object <- CreateCasperObject(raw.data=data,loh.name.mapping=loh.name.mapping,
 sequencing.type="single-cell",
 cnv.scale=3, loh.scale=3,expr.cutoff=0.1,matrix.type="normalized", filter="median",
 annotation=annotation, method="iterative", loh=loh,
@@ -510,3 +498,15 @@ log.ge <- as.matrix(mm135@assays$RNA@data)
 control <- names(Idents(mm135) )[Idents(mm135) %in% c(2,7)]
 mm <- names(Idents(mm135) )[Idents(mm135) %in% c(0, 1, 3, 4)]
 Sys.getenv("PATH")
+require(devtools)
+install_github("akdess/CaSpER")
+require(devtools)
+install_github("akdess/CaSpER")
+require(devtools)
+install_github("akdess/CaSpER", force=T)
+require(devtools)
+install_github("akdess/CaSpER", force=T)
+?install_github
+require(devtools)
+install_github("akdess/CaSpER", force=TRUE
+)

.Rproj.user/shared/notebooks/paths

@@ -1,12 +1,10 @@
+C:/Users/aharmanci/Documents/GitHub/CaSpER/vignettes/Introduction.Rmd="3445A632"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/.Rbuildignore="38A4872D"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/.gitignore="F2FE8DC2"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/DESCRIPTION="51BDE6AB"
-C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/Meningioma.md="1D94301A"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/NAMESPACE="C7A3CBD9"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/README.md="A57B336"
-C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/TCGA_GBM.md="4529EA05"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/man/CreateCasperObject.Rd="4F09AFAF"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/man/PerformMedianFilter.Rd="B751D7E3"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/man/casper.Rd="DD56F016"
 C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/man/hello.Rd="F920EFF7"
-C:/Users/aharmanci/Google Drive/uthealth/codebase_yale/codebase_uthealth/CaSpER/sCell_GBM.md="38931473"

vignettes/Introduction.Rmd

@@ -101,7 +101,7 @@ mkdir test; samtools view SRR1295366.sorted.bam | ./bin/BAFExtract -generate_com
 
 **2. Normalized gene expression data** 
 
-The expression values should be normalized using  TPM or FPKM. Below is an example normalized gene expression input :
+The expression values can be normalized using  TPM or FPKM or raw. Below is an example normalized gene expression input :
 ```{r, include=FALSE}
 library(knitr)
 ```
@@ -125,6 +125,24 @@ data(hg19_cytoband)
 kable(cytoband[1:5, ])
 ```
 
+HG38 cytoband information can be genrated using the flooing commands: 
+
+``` r
+http://hgdownload.cse.ucsc.edu/goldenPath/hg38/database/cytoBand.txt.gz
+```
+```{r, eval=T}
+cytoband <- read.delim("cytoBand.txt", header=F)
+cytoband$V4 <-substring(cytoband$V4, 1, 1)
+start <-  do.call(rbind, lapply(split(cytoband$V2, paste0(cytoband$V1, cytoband$V4)), min))
+end <- do.call(rbind, lapply(split(cytoband$V3, paste0(cytoband$V1, cytoband$V4)), max))
+cytoband <- data.frame(V1=gsub("p", "", gsub("q", "",  rownames(start))), V2=start, V3=end, V4=rownames(start), stringsAsFactors=F)
+cytoband$V4[grep("q", cytoband$V4)] <- "q"
+cytoband$V4[grep("p", cytoband$V4)] <- "p"
+cytoband <- cytoband [ as.vector(sapply(c(1:22, "X"), function(x)  which(cytoband$V1 %in% x))), ]
+rownames(cytoband) <- NULL
+```
+
+
 Centromere information can be downloaded from UCSC. 
 ``` r
 #curl -s "http://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/cytoBand.txt.gz" | gunzip -c | grep acen | head
@@ -136,7 +154,7 @@ Annotation data which contains the positions of each gene along each chromosome
 
 
 ```{r, eval=F}
-annotation <- generateAnnotation(id_type="ensembl_gene_id", genes=rownames(yale_meningioma$data), ishg19=T, centromere)
+annotation <- generateAnnotation(id_type="ensembl_gene_id", genes=rownames(yale_meningioma$data), ishg19=T, centromere, host="uswest.ensembl.org")
 ```
 
 ```{r, include=FALSE}
@@ -164,8 +182,8 @@ Casper object is created using following functions
 
 ```{r, eval=F}
 object <- CreateCasperObject(raw.data=data,loh.name.mapping=loh.name.mapping, sequencing.type="bulk", 
-  cnv.scale=3, loh.scale=3,
-  annotation=annotation, method="iterative", loh=loh, 
+  cnv.scale=3, loh.scale=3, matrix.type="normalized", expr.cutoff=4.5,
+  annotation=annotation, method="iterative", loh=loh, filter="median",  
   control.sample.ids=control.sample.ids, cytoband=cytoband)
 ```