1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
|
#!/usr/bin/env python
# File created on 09 Feb 2010
#file make_2d_plots.py
from __future__ import division
__author__ = "Jesse Stombaugh"
__copyright__ = "Copyright 2011, The QIIME Project"
__credits__ = ["Jesse Stombaugh"]
__license__ = "GPL"
__version__ = "1.4.0"
__maintainer__ = "Jesse Stombaugh"
__email__ = "jesse.stombaugh@colorado.edu"
__status__ = "Release"
from matplotlib import use
use('Agg',warn=False)
import matplotlib,re
from qiime.util import parse_command_line_parameters, get_options_lookup
from qiime.util import make_option
from qiime.make_2d_plots import generate_2d_plots
from qiime.parse import parse_coords,group_by_field,group_by_fields
import shutil
import os
from qiime.colors import sample_color_prefs_and_map_data_from_options
from qiime.util import get_qiime_project_dir,load_pcoa_files
from qiime.make_3d_plots import get_coord
from cogent.util.misc import get_random_directory_name
options_lookup = get_options_lookup()
#make_2d_plots.py
script_info={}
script_info['brief_description']="""Make 2D PCoA Plots"""
script_info['script_description']="""This script generates 2D PCoA plots using the principal coordinates file generated by performing beta diversity measures of an OTU table."""
script_info['script_usage']=[]
script_info['script_usage'].append(("""Default Example:""","""If you just want to use the default output, you can supply the principal coordinates file (i.e., resulting file from principal_coordinates.py), where the default coloring will be based on the SampleID as follows:""","""%prog -i beta_div_coords.txt -m Mapping_file.txt"""))
script_info['script_usage'].append(("""Output Directory Usage:""","""If you want to give an specific output directory (e.g. \"2d_plots\"), use the following code.""", """%prog -i beta_div_coords.txt -o 2d_plots/"""))
script_info['script_usage'].append(("""Mapping File Usage:""","""Additionally, the user can supply their mapping file ("-m") and a specific category to color by ("-b") or any combination of categories. When using the -b option, the user can specify the coloring for multiple mapping labels, where each mapping label is separated by a comma, for example: -b \'mapping_column1,mapping_column2\'. The user can also combine mapping labels and color by the combined label that is created by inserting an \'&&\' between the input columns, for example: -b \'mapping_column1&&mapping_column2\'.
If the user wants to color by specific mapping labels, they can use the following code:""","""%prog -i beta_div_coords.txt -m Mapping_file.txt -b 'mapping_column'"""))
script_info['script_usage'].append(("""""","""If the user would like to color all categories in their metadata mapping file, they can pass 'ALL' to the '-b' option, as follows:""","""%prog -i beta_div_coords.txt -m Mapping_file.txt -b ALL"""))
script_info['script_usage'].append(("""Prefs File:""","""The user can supply a prefs file to color by, as follows:""", """%prog -i beta_div_coords.txt -m Mapping_file.txt -p prefs.txt"""))
script_info['script_usage'].append(("""Jackknifed Principal Coordinates (w/ confidence intervals):""","""If you have created jackknifed PCoA files, you can pass the folder containing those files, instead of a single file. The user can also specify the opacity of the ellipses around each point "--ellipsoid_opacity", which is a value from 0-1. Currently there are two metrics "--ellipsoid_method" that can be used for generating the ellipsoids, which are 'IQR' and 'sdev'. The user can specify all of these options as follows:""", """%prog -i jackknifed_pcoas/ -m Mapping_file.txt -b \'mapping_column1,mapping_column1&&mapping_column2\' --ellipsoid_opacity=0.5 --ellipsoid_method=IQR"""))
script_info['output_description']="""This script generates an output folder, which contains several files. To best view the 2D plots, it is recommended that the user views the _pcoa_2D.html file."""
script_info['required_options']=[\
make_option('-i', '--coord_fname', \
help='Input principal coordinates filepath (i.e.,' +\
' resulting file from principal_coordinates.py). Alternatively,' +\
' a directory containing multiple principal coordinates files for' +\
' jackknifed PCoA results.',
type='existing_path'),
make_option('-m', '--map_fname', dest='map_fname', \
help='Input metadata mapping filepath',
type='existing_filepath')
]
script_info['optional_options']=[\
make_option('-b', '--colorby', dest='colorby',\
help='Comma-separated list categories metadata categories' +\
' (column headers) ' +\
'to color by in the plots. The categories must match the name of a ' +\
'column header in the mapping file exactly. Multiple categories ' +\
'can be list by comma separating them without spaces. The user can ' +\
'also combine columns in the mapping file by separating the ' +\
'categories by "&&" without spaces. [default=color by all]'),
make_option('-p', '--prefs_path',
help='Input user-generated preferences filepath. NOTE: This is a' +\
' file with a dictionary containing preferences for the analysis.' +\
' [default: %default]',
type='existing_filepath'),
make_option('-k', '--background_color',
help='Background color to use in the plots. [default: %default]',
default='white', type='choice',choices=['black','white'],),
make_option('--ellipsoid_opacity',
help='Used only when plotting ellipsoids for jackknifed' +\
' beta diversity (i.e. using a directory of coord files' +\
' instead of a single coord file). The valid range is between 0-1.' +\
' 0 produces completely transparent (invisible) ellipsoids' +\
' and 1 produces completely opaque ellipsoids.' +\
' [default=%default]', \
default=0.33,type=float),
make_option('--ellipsoid_method',
help='Used only when plotting ellipsoids for jackknifed' +\
' beta diversity (i.e. using a directory of coord files' +\
' instead of a single coord file). Valid values are "IQR" and' +\
' "sdev". [default=%default]',default="IQR",
type="choice",choices=["IQR","sdev"]),
make_option('--master_pcoa',
help='Used only when plotting ellipsoids for jackknifed beta diversity' +\
' (i.e. using a directory of coord files' +\
' instead of a single coord file). These coordinates will be the' +\
' center of each ellipisoid. [default: %default; arbitrarily chosen' +\
' PC matrix will define the center point]',default=None,
type='existing_filepath'),
options_lookup['output_dir']
]
script_info['option_label']={'coord_fname':'Principal coordinates filepath',
'map_fname':'QIIME-formatted mapping filepath',
'colorby': 'Colorby category',
'prefs_path': 'Preferences filepath',
'background_color': 'Background color',
'ellipsoid_opacity':'Ellipsoid opacity',
'ellipsoid_method':'Ellipsoid method',
'master_pcoa':'Master principal coordinates filepath',
'output_dir': 'Output directory'}
script_info['version'] = __version__
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
matplotlib_version = re.split("[^\d]", matplotlib.__version__)
matplotlib_version_info = tuple([int(i) for i in matplotlib_version if \
i.isdigit()])
if matplotlib_version_info != (1,1,0):
print "This code was only tested with Matplotlib-1.1.0"
data = {}
prefs,data,background_color,label_color,ball_scale, arrow_colors= \
sample_color_prefs_and_map_data_from_options(opts)
data['ellipsoid_method']=opts.ellipsoid_method
if 0.00 <= opts.ellipsoid_opacity <= 1.00:
data['alpha']=opts.ellipsoid_opacity
else:
raise ValueError, 'The opacity must be a value between 0 and 1!'
#Open and get coord data
if os.path.isdir(opts.coord_fname) and opts.master_pcoa:
data['coord'],data['support_pcoas'] = load_pcoa_files(opts.coord_fname)
data['coord']=get_coord(opts.master_pcoa)
elif os.path.isdir(opts.coord_fname):
data['coord'],data['support_pcoas'] = load_pcoa_files(opts.coord_fname)
else:
data['coord'] = get_coord(opts.coord_fname)
filepath=opts.coord_fname
basename,extension=os.path.splitext(filepath)
filename='%s_2D_PCoA_plots' % (basename)
qiime_dir=get_qiime_project_dir()
js_path=os.path.join(qiime_dir,'qiime','support_files','js')
if opts.output_dir:
if os.path.exists(opts.output_dir):
dir_path=opts.output_dir
else:
try:
os.mkdir(opts.output_dir)
dir_path=opts.output_dir
except OSError:
pass
else:
dir_path='./'
html_dir_path=dir_path
data_dir_path = get_random_directory_name(output_dir=dir_path)
try:
os.mkdir(data_dir_path)
except OSError:
pass
js_dir_path = os.path.join(html_dir_path,'js')
try:
os.mkdir(js_dir_path)
except OSError:
pass
shutil.copyfile(os.path.join(js_path,'overlib.js'), \
os.path.join(js_dir_path,'overlib.js'))
try:
action = generate_2d_plots
except NameError:
action = None
#Place this outside try/except so we don't mask NameError in action
if action:
action(prefs,data,html_dir_path,data_dir_path,filename,background_color,
label_color)
if __name__ == "__main__":
main()
|
