diff rename.py @ 0:1a0e39acb62f draft

planemo upload commit 3431b38459716fd36c193c1035ede040f7ca2e87-dirty
author yating-l
date Mon, 19 Dec 2016 17:14:55 -0500
parents
children 148e353417e7
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/rename.py	Mon Dec 19 17:14:55 2016 -0500
@@ -0,0 +1,34 @@
+"""
+Call rename to rename scaffolds in reference genome so that the sequence names are less than 31 characters. Rename all scaffolds to scaffold_1, scaffold_2, ..., scaffold_N and provide a name mapping file
+"""
+import sys
+from collections import OrderedDict
+
+def rename(inputfile, outputfile, indexfile):
+    namemap = OrderedDict()
+    with open(outputfile, 'w') as out:
+        with open(inputfile, 'r') as rf:
+            lines = rf.readlines()
+            i = 1
+            for line in lines:
+                if ">" in line:
+                    oldname = line[1:].rstrip()
+                    newname = "scaffold_" + str(i)
+                    line = ">" + newname + "\n"
+                    i = i+1
+                    namemap[oldname] = newname
+                out.write(line)
+    with open(indexfile, 'w') as index:
+        for k in namemap:
+            index.write(k + "=>" + namemap[k] + "\n")
+
+def main():
+    inputfile = str(sys.argv[1])
+    outputfile = str(sys.argv[2])
+    indexfile = str(sys.argv[3])
+    rename(inputfile, outputfile, indexfile)
+
+if __name__ == "__main__":
+    main()
+    
+