added ENA data mining slides 13.12.2022

Microbio_practical_2022/R_script_practical.R

@@ -52,7 +52,7 @@ TAX <- read.table(
 
 # sample metadata (experimental conditions)
 META <- read.table(
-  "results_read_run_tsv.txt",
+  "results_read_run_tsv_20221018.txt",
   h = T, 
   sep = "\t"
 )
@@ -67,6 +67,11 @@ str(META)
 # RNA and DNA level in the same sample. We need the DNA (library source = METAGENOMIC) data here.
 META <- META[META$library_source == "METAGENOMIC" & META$sample_title %in% colnames(ASV),]
 
+META$fastq_ftp
+plotQualityProfile("ERR7719921_1.fastq.gz")
+plotQualityProfile("ERR7719921_2.fastq.gz")
+
+
 # Now we can set the sample title as row names
 rownames(META) <- META$sample_title
 
@@ -213,10 +218,10 @@ mtext(text = "Sequencing depth", side = 1, line = 2.5)
 
 # Bray-Curtis dissimilarity
 bc <- vegdist(t(ASV.rel), method = "bray")
-
+bc
 # Jaccard dissimilarity
 jc <- vegdist(t(ASV.rel), method = "jaccard", binary = T)
-
+jc
 # How similar are the samples to each other?
 # What is the difference in the interpretation between the 2 dissimilarity measures?