Mercurial > repos > jay > pdaug_peptide_sequence_analysis

comparison PDAUG_Sequence_Network/PDAUG_Sequence_Network.py @ 0:e59674e3a391 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 6f53ad797ec1af02b41510063a86bec7d121abf3"
author jay
date Fri, 20 Nov 2020 19:47:44 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:e59674e3a391
1 import Levenshtein
2 import matplotlib.pyplot as plt
3 import networkx as nx
4 import os
5
6
7 def SeqSimilarityNetwork(InFile, OutFile):
8
9 f = open(InFile)
10 lines = f.readlines()
11
12 record = []
13 seq = []
14
15 G = nx.Graph()
16
17 for line in lines:
18
19 if ">" in line:
20 record.append(line.strip('\n'))
21 else:
22 seq.append(line.strip('\n'))
23
24 for x, i in enumerate(seq):
25 for X, I in enumerate(seq):
26 L = Levenshtein.ratio(i, I )
27 if L >= 0.4:
28 G.add_edge(record[x], record[X], weight=float(Levenshtein.ratio(i, I )))
29
30 elarge = [(u, v) for (u, v, d) in G.edges(data=True) if d['weight'] >= 0.4]
31
32 pos = nx.spring_layout(G)
33 nx.draw_networkx_nodes(G, pos, node_size=10)
34 nx.draw_networkx_edges(G, pos, edgelist=elarge,width=1)
35 plt.axis('off')
36
37 plt.savefig(OutFile)
38
39
40
41 if __name__=="__main__":
42
43 import argparse
44
45 parser = argparse.ArgumentParser()
46
47 parser.add_argument("-I", "--InFile", required=True, default=None, help="Path to target tsv file")
48 parser.add_argument("-O","--OutFile", required=False, help="HTML out file", default="out.png")
49 args = parser.parse_args()
50
51 SeqSimilarityNetwork(args.InFile, args.OutFile)
52
53