Midlige Tutorial 11

tutorial11part1.sh

@@ -0,0 +1,17 @@
+./Muscle -in ./Problem1/sigma.ref -out sigma.align
+./Hammer/binaries/hmmbuild sigma.hmm sigma.align 
+
+./Muscle -in ./Problem1/sporecoat.ref -out sporecoat.align
+./Hammer/binaries/hmmbuild sporecoat.hmm sporecoat.align
+
+./Muscle -in ./Problem1/transporter.ref -out transporter.align
+./Hammer/binaries/hmmbuild transporter.hmm transporter.align 
+
+for file in Problem1/*.fasta
+do
+    ./Hammer/binaries/hmmsearch --tblout $file.sigma.hits sigma.hmm $file
+    ./Hammer/binaries/hmmsearch --tblout $file.sporecoat.hits sporecoat.hmm $file
+    ./Hammer/binaries/hmmsearch --tblout $file.transporter.hits transporter.hmm $file
+done
+
+cat Problem1/*.hits | grep -v "#" | awk '{print $1,$3,$5}' | sed -E 's/tr\|[A-Z0-9]+\|[A-Z0-9]+_9//' > results.txt

tutorial11part2.py

@@ -0,0 +1,22 @@
+import numpy
+import pandas
+
+sequences=open("motifsort.fasta","r")
+motif1file=open(motif1.txt,"w")
+motif2file=open(motif2.txt,"w")
+others=open(nonMotif.txt,"w")
+
+for line in sequences:
+    motif1= re.match(AKKPRVZE,str(sequences))
+    motif2- re.match(AAQWWRNYGG,str(sequences))
+
+    if motif1:
+        motif1file.write(line + '\n')
+    if motif2:
+        motif2file.write(line + '\n')
+    else:
+        others.write(line + '\n')
+
+print motif1file
+print motif2file
+print others