Mercurial > repos > rnateam > graphclust_motif_finder_plot

comparison MotifFinderPlot.py @ 0:bfae792ea7f1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/master/tools/GraphClust/Plotting commit f971832d2b34a182314e5201ea6895dd207c5923
author rnateam
date Mon, 13 Mar 2017 17:57:19 -0400
parents
children a85e3675e50d
comparison
equal deleted inserted replaced
-1:000000000000 0:bfae792ea7f1
1 #!/usr/bin/env python
2
3 import matplotlib
4 matplotlib.use('Agg')
5 from matplotlib import pyplot as plt
6 import matplotlib.patches as mpatches
7 from collections import defaultdict
8 import glob
9 import pandas as pd
10 import itertools
11 import seaborn as sns
12
13
14 def plot_bar(ranges, colors, orig_names, cluster_nums):
15 fig, ax = plt.subplots()
16 for i, k in enumerate(sorted(ranges.keys())):
17 ax.broken_barh(ranges[k], (i-0.25, 0.5), facecolors=colors[k])
18
19 ax.set_xlim(0)
20 ax.set_xlabel('position in sequence')
21 ax.set_yticklabels(['']+[k+'-'+orig_names[k] for k in sorted(ranges.keys())])
22 ax.grid(True)
23 fig.suptitle('Structure motif prediction\nRegions with same color are prediticted to have similar structures')
24 # Add the legend
25 patches = [mpatches.Patch(color=cluster_nums[lab], label=lab) for lab in sorted(cluster_nums)]
26 ax.legend(handles=patches, loc='best') # , bbox_to_anchor=(1, 0.5), loc='center left')
27 plt.savefig("motif_plot.png", bbox_inches='tight')
28
29
30 def parse_clusters():
31 currentdir_files = sorted(list(glob.glob('*')))
32 print ("currentdir_files are: ", currentdir_files)
33 print ("RESULTS_files are: ", sorted(list(glob.glob('RESULTS/*'))))
34
35 cluster_files = sorted(list(glob.glob('RESULTS/*.cluster.all')))
36 if len(cluster_files) == 0:
37 raise RuntimeError('Expected cluster.all search path is empty:{}'.format(cluster_files))
38 palette = itertools.cycle(sns.color_palette("Set2", len(cluster_files)))
39
40
41 ranges = defaultdict(list)
42 colors = defaultdict(list)
43 orig_names = defaultdict(list)
44 cluster_nums = defaultdict(list)
45 for cluster_file in cluster_files:
46 cluster_color = next(palette)
47 df_cluster = pd.read_csv(cluster_file, sep='\s+', header=None)
48 for irow, row in df_cluster.iterrows():
49 seq, start, end, strand = row[0].split("#")
50 ranges[seq].append((int(start), int(end)-int(start)+1))
51 colors[seq].append(cluster_color)
52 assert row[1] == 'RESULT'
53 cluster_nums['cluster-{}'.format(row[2])] = cluster_color
54 assert row[9] == 'ORIGHEAD'
55 orig_names[seq] = row[10]
56 return ranges, colors, orig_names, cluster_nums
57
58
59 my_ranges, my_colors, my_orig_names, my_cluster_nums = parse_clusters()
60 plot_bar(my_ranges, my_colors, my_orig_names, my_cluster_nums)