Merge pull request #634 from PatrickDeelen/master

Recount3 scripts and new release for genotype harmonizer

Author: CAWarmerdam

.gitignore

@@ -35,3 +35,4 @@ deconvolutionTestResults/
 .Rproj.user
 .Rhistory
 /DEPICT2/src/main/r/downstreamer_main/downstreamer_main.Rproj
+Downstreamer/src/main/r/downstreamer_main/.remoterserverlog

Downstreamer/pom.xml

@@ -7,7 +7,7 @@
 		<version>1.0.4-SNAPSHOT</version>
 	</parent>
 	<artifactId>Downstreamer</artifactId> 
-	<version>1.29-SNAPSHOT</version>
+	<version>1.30-SNAPSHOT</version>
 	<packaging>jar</packaging>
 	<build>
 		<resources>

Downstreamer/src/main/r/downstreamer_main/downstreamer_main.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

Downstreamer/src/main/r/downstreamer_main/legacy_scripts/combineAnnotations.R

@@ -1564,7 +1564,7 @@ combinedMeta$CelllineName[studySamples] <- ""
 combinedMeta$Cancer[studySamples] <- FALSE
 
 #SRP081020 is mis-anotated in SRA as PBMC, paper and clustering both state wholeblood
-studySamples <- combinedMeta$study %in% c("ERP114104", "SRP051848", "SRP056784", "SRP071965", "SRP077975", "SRP081020", "SRP098758", "SRP113245", "SRP126580", "SRP126582", "SRP126583", "SRP136057", "SRP144583", "SRP150872", "SRP214077")
+studySamples <- combinedMeta$study %in% c("ERP114104", "SRP051848", "SRP056784", "SRP071965", "SRP077975", "SRP081020", "SRP098758", "SRP113245", "SRP126580", "SRP126582", "SRP126583", "SRP136057", "SRP144583", "SRP150872", "SRP214077", "SRP056443")
 combinedMeta$Tissue[studySamples] <- ""
 combinedMeta$Tissue2[studySamples] <- ""
 combinedMeta$Cellline[studySamples] <- NA
@@ -1573,6 +1573,9 @@ combinedMeta$Cancer[studySamples] <- NA
 
 
 
+
+
+
 combinedMeta$Cellline[!is.na(combinedMeta$CelllineName)&combinedMeta$CelllineName=="iPSC"] <- TRUE
 combinedMeta$Cancer[!is.na(combinedMeta$Cellline) & combinedMeta$Cellline] <- NA
 
@@ -1613,7 +1616,7 @@ combinedMeta$Tissue[combinedMeta$Cohort == "GSA"]
 
 
 
-#save(combinedMeta, file = "combinedMeta_2022_09_02.RData")
+#save(combinedMeta, file = "combinedMeta_2022_09_15.RData")
 
 load(file = "combinedMeta_2022_08_19.RData")
 

Downstreamer/src/main/r/downstreamer_main/legacy_scripts/metaBrain2.R

@@ -0,0 +1,31 @@
+setwd("D:\\UMCG\\Genetica\\Projects\\Depict2Pgs")
+
+source(paste0("C:\\Users\\patri\\Documents\\GitHub\\systemsgenetics\\Downstreamer\\src\\main\\r\\downstreamer_main/downstreamer_functions.r"))
+
+traits <- read.delim("MetaBrain/traits.txt")
+
+
+i <- 1
+
+pdf("MetaBrain/withAndWithoutEqtls.pdf", height = 20, width = 10)
+#png("MetaBrain/withAndWithoutEqtls.png", height = 2000, width = 1000)
+layout(matrix(1:8, ncol =2))
+par(pty="s")
+for(i in 1:nrow(traits)){
+
+  
+
+trait <- traits[i, "trait"]
+name <- traits[i, "name"]
+
+enrichments <- read.depict2(paste0("MetaBrain/normal/",trait,"_enrichtments.xlsx"))$GenePrioritization_MetaBrain
+enrichmentsIncEqtl <- read.depict2(paste0("MetaBrain/inceqt/",trait,"_enrichtments.xlsx"))$GenePrioritization_MetaBrain
+
+enrichmentsBoth <- merge(enrichments, enrichmentsIncEqtl,  "Gene.ID" , suffixes= c("Normal", "incEqtl"))
+
+maxZ <- max(range(enrichmentsBoth$Enrichment.Z.scoreNormal, enrichmentsBoth$Enrichment.Z.scoreincEqtl))
+r <- cor(enrichmentsBoth$Enrichment.Z.scoreNormal, enrichmentsBoth$Enrichment.Z.scoreincEqtl)
+plot(enrichmentsBoth$Enrichment.Z.scoreNormal, enrichmentsBoth$Enrichment.Z.scoreincEqtl, bg = adjustcolor("dodgerblue2", alpha.f = 0.3), pch = 21, col=adjustcolor("dodgerblue2", alpha.f = 0.5), asp = 1, xlab = "Key gene score without eqtl information",  ylab = "Key gene score without eqtl information", xlim = c(-maxZ,maxZ), ylim = c(-maxZ,maxZ), main = name)
+mtext(paste0("Pearson r: ", signif(r,2)))
+}
+dev.off()

Downstreamer/src/main/r/downstreamer_main/legacy_scripts/playingWithPcaSvd.R

@@ -270,12 +270,6 @@ plot(log(expSvd$d))
 abline(v=60)
 
 
-library(rpca)
-
-
-expRpca <- rpca(t(expSub2))
-
-
 
 library(corpcor)
 expSvdFast <- fast.svd(expSubScale)