我有以下工作代码。
from matplotlib import pyplot as plt
import numpy as np
from matplotlib_venn import venn3, venn3_circles
Gastric_tumor_promoters = set(['DPEP1', 'CDC42BPA', 'GNG4', 'RAPGEFL1', 'MYH7B', 'SLC13A3', 'PHACTR3', 'SMPX', 'NELL2', 'PNMAL1', 'KRT23', 'PCP4', 'LOX', 'CDC42BPA'])
Ovarian_tumor_promoters = set(['ABLIM1','CDC42BPA','VSNL1','LOX','PCP4','SLC13A3'])
Gastric_tumor_suppressors = set(['PLCB4', 'VSNL1', 'TOX3', 'VAV3'])
#Ovarian_tumor_suppressors = set(['VAV3', 'FREM2', 'MYH7B', 'RAPGEFL1', 'SMPX', 'TOX3'])
venn3([Gastric_tumor_promoters,Ovarian_tumor_promoters, Gastric_tumor_suppressors], ('GCPromoters', 'OCPromoters', 'GCSuppressors'))
venn3([Gastric_tumor_promoters,Ovarian_tumor_promoters, Gastric_tumor_suppressors], ('GCPromoters', 'OCPromoters', 'GCSuppressors'))
plt.show()
如何在这3个圈子中显示每个组的内容?颜色alpha为0.6。圆圈必须更大才能容纳所有符号。
答案 0 :(得分:4)
我不确定是否有一种简单的方法可以自动完成任何可能的组合组合。如果您准备在特定示例中进行一些手动调整,请从以下内容开始:
A = set(['DPEP1', 'CDC42BPA', 'GNG4', 'RAPGEFL1', 'MYH7B', 'SLC13A3', 'PHACTR3', 'SMPX', 'NELL2', 'PNMAL1', 'KRT23', 'PCP4', 'LOX', 'CDC42BPA'])
B = set(['ABLIM1','CDC42BPA','VSNL1','LOX','PCP4','SLC13A3'])
C = set(['PLCB4', 'VSNL1', 'TOX3', 'VAV3'])
v = venn3([A,B,C], ('GCPromoters', 'OCPromoters', 'GCSuppressors'))
v.get_label_by_id('100').set_text('\n'.join(A-B-C))
v.get_label_by_id('110').set_text('\n'.join(A&B-C))
v.get_label_by_id('011').set_text('\n'.join(B&C-A))
v.get_label_by_id('001').set_text('\n'.join(C-A-B))
v.get_label_by_id('010').set_text('')
plt.annotate(',\n'.join(B-A-C), xy=v.get_label_by_id('010').get_position() +
np.array([0, 0.2]), xytext=(-20,40), ha='center',
textcoords='offset points',
bbox=dict(boxstyle='round,pad=0.5', fc='gray', alpha=0.1),
arrowprops=dict(arrowstyle='->',
connectionstyle='arc',color='gray'))
请注意,像v.get_label_by_id('001')
这样的方法会返回matplotlib Text
对象,您可以根据自己的喜好自由配置它们(例如,您可以通过调用set_fontsize(8)
等来更改字体大小)。
答案 1 :(得分:0)
这是一个使整个过程自动化的示例。它会创建一个临时词典,其中包含venn所需的id作为键以及该id的所有参与集的交集。
如果您不希望对标签进行排序,请删除倒数第二行中的sorted()调用。
import math
from matplotlib import pyplot as plt
from matplotlib_venn import venn2, venn3
import numpy as np
# Convert number to indices into binary
# e.g. 5 -> '101' > [2, 0]
def bits2indices(b):
l = []
if b == 0:
return l
for i in reversed(range(0, int(math.log(b, 2)) + 1)):
if b & (1 << i):
l.append(i)
return l
# Make dictionary containing venn id's and set intersections
# e.g. d = {'100': {'c', 'b', 'a'}, '010': {'c', 'd', 'e'}, ... }
def set2dict(s):
d = {}
for i in range(1, 2**len(s)):
# Make venn id strings
key = bin(i)[2:].zfill(len(s))
key = key[::-1]
ind = bits2indices(i)
# Get the participating sets for this id
participating_sets = [s[x] for x in ind]
# Get the intersections of those sets
inter = set.intersection(*participating_sets)
d[key] = inter
return d
# Define some sets
a = set(['a', 'b', 'c'])
b = set(['c', 'd', 'e'])
c = set(['e', 'f', 'a'])
s = [a, b, c]
# Create dictionary from sets
d = set2dict(s)
# Plot it
h = venn3(s, ('A', 'B', 'C'))
for k, v in d.items():
l = h.get_label_by_id(k)
if l:
l.set_text('\n'.join(sorted(v)))
plt.show()
/编辑 对不起,我刚刚发现以上代码并未删除重复的标签,因此是错误的。 venn表示的元素数和标签数不同。这是一个新版本,可从其他路口删除错误的重复项。我想有一种更聪明,更实用的方法来执行此操作,而不是遍历所有路口两次……
import math, itertools
from matplotlib import pyplot as plt
from matplotlib_venn import venn2, venn3
import numpy as np
# Generate list index for itertools combinations
def gen_index(n):
x = -1
while True:
while True:
x = x + 1
if bin(x).count('1') == n:
break
yield x
# Generate all combinations of intersections
def make_intersections(sets):
l = [None] * 2**len(sets)
for i in range(1, len(sets) + 1):
ind = gen_index(i)
for subset in itertools.combinations(sets, i):
inter = set.intersection(*subset)
l[next(ind)] = inter
return l
# Get weird reversed binary string id for venn
def number2venn_id(x, n_fill):
id = bin(x)[2:].zfill(n_fill)
id = id[::-1]
return id
# Iterate over all combinations and remove duplicates from intersections with
# more sets
def sets2dict(sets):
l = make_intersections(sets)
d = {}
for i in range(1, len(l)):
d[number2venn_id(i, len(sets))] = l[i]
for j in range(1, len(l)):
if bin(j).count('1') < bin(i).count('1'):
l[j] = l[j] - l[i]
d[number2venn_id(j, len(sets))] = l[j] - l[i]
return d
# Define some sets
a = set(['a', 'b', 'c', 'f'])
b = set(['c', 'd', 'e'])
c = set(['e', 'f', 'a'])
sets = [a, b, c]
d = sets2dict(sets)
# Plot it
h = venn3(sets, ('A', 'B', 'C'))
for k, v in d.items():
l = h.get_label_by_id(k)
if l:
l.set_fontsize(12)
l.set_text('\n'.join(sorted(v)))
# Original for comparison
f = plt.figure(2)
venn3(sets, ('A', 'B', 'C'))
plt.show()