bin assembly stats script

bin_assembly_stats.sh

+#!/bin/bash
+
+# Loops through a folder of fasta files and calculates #contigs, total length, N50, largst contig and GC%.
+# (also works on gzipped fasta files)
+#
+# The raw_n50 executeable comes from the idba_ud assembler.
+
+echo -e 'bin\tcontigs\ttotal_length\tN50\tlargest\tGC%'
+for filepath in `ls $1/*.fa*`; do
+  bin=$(basename $filepath | sed s'/.fa.*//'g)
+  raw_n50_stats=$(/unlock/infrastructure/binaries/raw_n50 $filepath)
+  
+  GC=$(grep -v ">" $filepath | sed -e 's/\(.\)/\1\n/g' | grep -c "G\|C")
+  size=$(echo $raw_n50_stats | awk '{print $11}')
+  GCcontent=$(echo | awk -v GC=$GC -v size=$size '{printf "%.2f", GC/size*100}')
+  
+  stats=$(echo $raw_n50_stats | awk '{print $2"\t"$11"\t"$4"\t"$6}')
+  echo -e $bin"\t"$stats"\t"$GCcontent | sed 's/ /\t/g'
+done