From 49fdd614d4b18f7d28126e4ebbf3adca57f0416f Mon Sep 17 00:00:00 2001
From: Alexander Kabui
Date: Tue, 14 Sep 2021 22:31:18 +0300
Subject: Checking data for excessive missing values

---
 scripts/wgcna_analysis.R | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/scripts/wgcna_analysis.R b/scripts/wgcna_analysis.R
index a8170b6..8e90d7d 100644
--- a/scripts/wgcna_analysis.R
+++ b/scripts/wgcna_analysis.R
@@ -10,10 +10,28 @@ wgcnaRawData <- read.csv(file = "wgcna_data.csv")
 
 # transform expressionData
 
-datExpr <- as.data.frame(t(wgcnaRawData));
+dataExpr <- as.data.frame(t(wgcnaRawData));
 
 
 
+# data cleaning
+
+# adopted from docs
+gsg = goodSamplesGenes(dataExpr, verbose = 3);
+
+
+
+if (!gsg$allOK)
+{
+# Optionally, print the gene and sample names that were removed:
+if (sum(!gsg$goodGenes)>0)
+printFlush(paste("Removing genes:", paste(names(datExpr0)[!gsg$goodGenes], collapse = ", ")));
+if (sum(!gsg$goodSamples)>0)
+printFlush(paste("Removing samples:", paste(rownames(datExpr0)[!gsg$goodSamples], collapse = ", ")));
+# Remove the offending genes and samples from the data:
+dataExpr <- dataExpr[gsg$goodSamples, gsg$goodGenes]
+}
+
 
 
 
-- 
cgit v1.2.3