Add enzymatic digestion

bin/insilicoRRBSdigestion.py

@@ -31,11 +31,12 @@ from subprocess import Popen, PIPE
 import tempfile
 import json
 import re
-sys.path.insert(0, os.path.join(os.path.dirname(os.path.realpath(__file__)), '..', '..', '..', 'src'))
-import jflow.seqio as seqio
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.realpath(__file__)),'..', 'lib'))
+import seqio as seqio
 
 GRAPH_CLASS_PARTITION = 100
 MAX_FRAGMENT_LEN_IN_HISTOGRAM = 5000
+ENZYME_PATH=os.path.join(os.path.dirname(os.path.realpath(__file__)),"..","lib","enzyme.txt")
 
 def version_string ():
     """
@@ -268,7 +269,10 @@ def compute_fragment_size_per_range(ranges,fragments_length):
 if __name__ == "__main__":
 
     # Get available enzyme
-    all_enzymes = get_available_enzymes(os.path.join(os.path.dirname(os.path.realpath(__file__)),"enzyme.txt"))
+    
+    all_enzymes = {'None':0}
+    if os.path.exists(ENZYME_PATH) :
+        all_enzymes = get_available_enzymes(ENZYME_PATH)
     
     parser = OptionParser(usage="Usage: insilicoRRBS.py -i FILE [options]")
 

lib/enzyme.txt

+SbfI	CCTGCAGG	CCTGCA*GG
+PstI	CTGCAG	CTGCA*G
+NsiI	ATGCAT	ATGCA*T
+NotI	GCGGCCGC	GC*GGCCGC
+EagI	CGGCCG	C*GGCCG
+EcoRI	GAATTC	G*AATTC
+MfeI	CAATTG	C*AATTG
+BamHI	GGATCC	G*GATCC
+BclI	TGATCA	T*GATCA
+BglII	AGATCT	A*GATCT
+BbvCI	CCTCAGC	CC*TCAGC
+HaeIII	GGCC	GG*CC
+RsaI	GTAC	GT*AC
+MspI	CCGG	C*CGG
+TaqI	TCGA	T*CGA
+Alu	AGCT	AG*CT
\ No newline at end of file