diff PDAUG_Sequence_Network/PDAUG_Sequence_Network.py @ 0:7557b48b2872 draft

"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/PDAUG_Sequence_Network/PDAUG_Sequence_Network.py	Wed Oct 28 02:10:12 2020 +0000
@@ -0,0 +1,53 @@
+import Levenshtein
+import matplotlib.pyplot as plt
+import networkx as nx
+import os
+
+
+def SeqSimilarityNetwork(InFile, OutFile):
+
+    f = open(InFile)
+    lines = f.readlines()
+
+    record = []
+    seq = []
+
+    G = nx.Graph()
+
+    for line in lines:
+
+        if ">" in line:
+            record.append(line.strip('\n'))
+        else:
+            seq.append(line.strip('\n'))
+
+    for x, i in enumerate(seq):
+        for X, I in enumerate(seq):
+            L = Levenshtein.ratio(i, I )
+            if  L >= 0.4:
+                G.add_edge(record[x], record[X], weight=float(Levenshtein.ratio(i, I )))
+
+    elarge = [(u, v) for (u, v, d) in G.edges(data=True) if d['weight'] >= 0.4]
+
+    pos = nx.spring_layout(G)
+    nx.draw_networkx_nodes(G, pos, node_size=10)
+    nx.draw_networkx_edges(G, pos, edgelist=elarge,width=1)
+    plt.axis('off')
+
+    plt.savefig(OutFile)
+
+
+
+if __name__=="__main__":
+
+    import argparse
+    
+    parser = argparse.ArgumentParser()
+    
+    parser.add_argument("-I", "--InFile", required=True, default=None, help="Path to target tsv file")
+    parser.add_argument("-O","--OutFile", required=False, help="HTML out file", default="out.png")
+    args = parser.parse_args()
+
+    SeqSimilarityNetwork(args.InFile, args.OutFile)
+
+