如何在python中使用matplotlib创建曼哈顿情节？

Question

不幸的是，我自己没有找到解决方案。如何使用例如matplotlib / pandas在python中创建Manhattan plot。问题是在这些图中，x轴是离散的。

from pandas import DataFrame
from scipy.stats import uniform
from scipy.stats import randint
import numpy as np

# some sample data
df = DataFrame({'gene' : ['gene-%i' % i for i in np.arange(1000)],
'pvalue' : uniform.rvs(size=1000),
'chromosome' : ['ch-%i' % i for i in randint.rvs(0,12,size=1000)]})

# -log_10(pvalue)
df['minuslog10pvalue'] = -np.log10(df.pvalue)
df = df.sort_values('chromosome')

# How to plot gene vs. -log10(pvalue) and colour it by chromosome?

Answer 1

您可以使用以下内容：

from pandas import DataFrame
from scipy.stats import uniform
from scipy.stats import randint
import numpy as np
import matplotlib.pyplot as plt

# some sample data
df = DataFrame({'gene' : ['gene-%i' % i for i in np.arange(10000)],
'pvalue' : uniform.rvs(size=10000),
'chromosome' : ['ch-%i' % i for i in randint.rvs(0,12,size=10000)]})

# -log_10(pvalue)
df['minuslog10pvalue'] = -np.log10(df.pvalue)
df.chromosome = df.chromosome.astype('category')
df.chromosome = df.chromosome.cat.set_categories(['ch-%i' % i for i in range(12)], ordered=True)
df = df.sort_values('chromosome')

# How to plot gene vs. -log10(pvalue) and colour it by chromosome?
df['ind'] = range(len(df))
df_grouped = df.groupby(('chromosome'))

fig = plt.figure()
ax = fig.add_subplot(111)
colors = ['red','green','blue', 'yellow']
x_labels = []
x_labels_pos = []
for num, (name, group) in enumerate(df_grouped):
    group.plot(kind='scatter', x='ind', y='minuslog10pvalue',color=colors[num % len(colors)], ax=ax)
    x_labels.append(name)
    x_labels_pos.append((group['ind'].iloc[-1] - (group['ind'].iloc[-1] - group['ind'].iloc[0])/2))
ax.set_xticks(x_labels_pos)
ax.set_xticklabels(x_labels)
ax.set_xlim([0, len(df)])
ax.set_ylim([0, 3.5])
ax.set_xlabel('Chromosome')

我刚刚创建了一个额外的运行索引列，以控制x标签的位置。

Answer 2

import matplotlib.pyplot als plt
from numpy.random import randn, random_sample

g = random_sample(int(1e5))*10 # uniform random values between 0 and 10
p = abs(randn(int(1e5))) # abs of normally distributed data

"""
plot g vs p in groups with different colors
colors are cycled automatically by matplotlib
use another colormap or define own colors for a different cycle
"""
for i in range(1,11): 
    plt.plot(g[abs(g-i)<1], p[abs(g-i)<1], ls='', marker='.')

plt.show()

您还可以查看this script，它似乎为您的问题提供了完整的解决方案。

Answer 3

你也可以使用 seaborn，这让事情变得更容易和更可控。

import numpy as np
import pandas as pd
import seaborn as sns
from scipy.stats import uniform, randint

# Simulate DataFrame
df = pd.DataFrame({
'rsid'  : ['rs{}'.format(i) for i in np.arange(10000)],
'chrom' : [i for i in randint.rvs(1,23+1,size=10000)],
'pos'   : [i for i in randint.rvs(0,10**5,size=10000)],
'pval'  : uniform.rvs(size=10000)})
df['-logp'] = -np.log10(df.pval); df = df.sort_values(['chrom','pos'])
df.reset_index(inplace=True, drop=True); df['i'] = df.index

# Generate Manhattan plot: (#optional tweaks for relplot: linewidth=0, s=9)
plot = sns.relplot(data=df, x='i', y='-logp', aspect=3.7, 
                   hue='chrom', palette = 'bright', legend=None) 
chrom_df=df.groupby('chrom')['i'].median()
plot.ax.set_xlabel('chrom'); plot.ax.set_xticks(chrom_df);
plot.ax.set_xticklabels(chrom_df.index)
plot.fig.suptitle('Manhattan plot');

我在这里遇到了其他答案，当时我正在寻找一种使用 Python 制作精美曼哈顿图的方法，但最终使用了这种 seaborn 方法。你也可以看看这个笔记本（=不是我的）以获得更多灵感：

https://github.com/mojones/video_notebooks/blob/master/Manhattan%20plots%20in%20Python.ipynb