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
|
#-------------------------------------------------------------------------------------------------------
#Step to create phyla pies based on data given by the main program
#-------------------------------------------------------------------------------------------------------
i = 0
j=0
taxo_highest = list()
taxo = list()
my_samples = list()
my_pie_name = ""
my_names_for_pie = list()
my_values_for_pie = list()
my_colors = {'Acidobacteria':'Gold', 'Actinobacteria':'Darkorange', 'Aquificae':'Cyan',\
'Armatimonadetes':'OldLace', 'BRC1':'Tan', 'OD1':'RosyBrown', 'OP11':'Peru', 'SR1':'SaddleBrown',\
'TM7':'Sienna', 'WS3':'Wheat', 'Chrysiogenetes':'BurlyWood', 'Caldiserica':'AntiqueWhite', 'Bacteroidetes':'CornflowerBlue',\
'Chlamydiae':'White', 'Chloroflexi':'DarkGoldenRod', 'Crenarchaeota':'DarkGreen', 'Euryarchaeota':'DarkSeaGreen',\
'Nanoarchaeota':'GreenYellow', 'Korarchaeota':'LightGreen', 'Cyanobacteria/Chloroplast':'GreenYellow', 'Chlorobi':'Chartreuse',\
'Deferribacteres':'LighSeaGreen', 'Deinococcus-Thermus':'YellowGreen', 'Dictyoglomi':'Chocolate', 'Elusimicrobia':'DarkKhaki',\
'Fibrobacteres':'MediumVioletRed', 'Firmicutes':'FireBrick', 'Fusobacteria':'Thistle', 'Gemmatimonadetes':'DeepSkyBlue',\
'Lentisphaerae':'Moccasin', 'Nitrospira':'LightSalmon', 'Planctomycetes':'ForestGreen', 'Proteobacteria':'Blue',\
'Thermotogae':'PaleGoldenRod', 'Verrucomicrobia':'Purple', 'Spirochaetes':'PowderBlue', 'Synergistetes':'Plum',\
'Tenericutes':'Turquoise', 'Thermodesulfobacteria':'PeechPuff', 'Unknown':'Gray', 'Undefined':'Black', 'Low Groups':'LightGrey'}
#Loop to treat all files found in the Summary_files folder
for file_name in treated_files:
#If the name of the file contain Taxonomy_results, we analyze this file
if (0<=file_name.find("Taxonomy_results_")):
#Open the targeted taxonomy summary file
Taxo_file = open("../Summary_files/"+file_name, 'r')
#For each read line of the file (as the line is not empty)
Read_tot_lines = Taxo_file.readlines()
#We read each line found in the file
for i in range(len(Read_tot_lines)):
#We delete the \n character using the replace function
Read_tot_lines[i] = Read_tot_lines[i].replace("\n","")
#If we found the line corresponding to the taxonomy_highest (phylum)
if (0<=Read_tot_lines[i].find("Taxonomy_highest")):
#We store it in an array form in taxo_highest
taxo_highest = Read_tot_lines[i].split("\t")
#If we found the line corresponding to the taxonomy studied
elif (0<=Read_tot_lines[i].find("Taxonomy_phylum")):
#We store it in an array form in taxo
taxo = Read_tot_lines[i].split("\t")
#If not, it correspond to a line of a sample
else:
#We store the array in an array names my_samples
my_samples.append(Read_tot_lines[i].split("\t"))
#We then determine the number of samples to create a figure with the good number of columns
x = len(my_samples) - 1
if( (x%2) == 0):
Nbcols = 2
#We define also the number of rows
Nbrows = x/Nbcols
else:
Nbcols = 3
#We define also the number of rows
Nbrows = x/Nbcols + 1
k = 1
#Definition of the subplot distances
plt.subplots_adjust(hspace=0.4)
#For each line of the samples
for my_line in my_samples:
#We not treat empty lines
if(my_line[0] == ''):
continue
my_line = compute_percents(my_line)
#Needed empty variables to treat several lines
my_names_for_pie = list()
my_values_for_pie = list()
my_colors_list = list()
my_lowers_values = float()
#We study each element in the line of the sample
for j in range(len(my_line)):
#We catch the name of the sample
if (0<=str(my_line[j]).find("Taxo_")):
#We catch the simplified name of the sample
my_pie_name = found_file_name(my_line[j])
#We avoid to treat the last element of the line
elif my_line[j] == '':
continue
#If it's an element
else:
#We verify that at least one read was detected
if (float(my_line[j]) > 0):
if (float(my_line[j]) < 1):
my_lowers_values += float(my_line[j])
else:
#We catch the name of the detected taxonomic elements
my_names_for_pie.append(taxo[j])
my_colors_list.append(my_colors[taxo[j]])
#And also their corresponding values
my_values_for_pie.append(my_line[j])
#Finally, we add the lowers in the same group for the graphics
my_names_for_pie.append("Low Groups")
#Thier corresponding color
my_colors_list.append(my_colors['Low Groups'])
#And also their corresponding value
my_values_for_pie.append(my_lowers_values)
#We create the subplot for each plot
plt.subplot(Nbrows,Nbcols,k)
#We use these elements to store them
plt.pie(my_values_for_pie, colors=my_colors_list, autopct='%1.1f%%', pctdistance=1.2, shadow=True)
#We also define the font properties using the FontProperties from the class font_manager
#This give an object properties that can directly been given to the legend object.
prop = fm.FontProperties(size=7)
plt.title(my_pie_name)
plt.tight_layout()
#We finally do this function to adapt the graphics to its size
#plt.grid(True)
k = k + 1
plt.legend(my_names_for_pie, prop = prop)
#We finally save the figure in various formats
plt.savefig('../Summary_files/Taxo_pie_results.png')
plt.savefig('../Summary_files/Taxo_pie_results.emf')
plt.savefig('../Summary_files/Taxo_pie_results.pdf') |
