pyCirclize: Python中的圆形可视化

概述

pyCirclize是一个基于matplotlib实现的圆形可视化Python包。该包的开发目的是在Python中轻松且美观地绘制圆形图表，如Circos图和和弦图。此外，还实现了生物信息学领域有用的基因组和系统发育树可视化方法。 pyCirclize受到circlize和pyCircos的启发。更详细的文档可在此处获取。

图1 pyCirclize示例图库

安装

安装需要Python 3.8或更高版本。

安装PyPI包：

pip install pycirclize

安装conda-forge包：

conda install -c conda-forge pycirclize

API使用

API使用在文档的以下各节中进行了描述。

代码示例

1. Circos图

from pycirclize import Circos
import numpy as np
np.random.seed(0)

# 初始化Circos扇区
sectors = {"A": 10, "B": 15, "C": 12, "D": 20, "E": 15}
circos = Circos(sectors, space=5)

for sector in circos.sectors:
    # 绘制扇区名称
    sector.text(f"扇区: {sector.name}", r=110, size=15)
    # 创建x位置和随机y值
    x = np.arange(sector.start, sector.end) + 0.5
    y = np.random.randint(0, 100, len(x))
    # 绘制线条
    track1 = sector.add_track((80, 100), r_pad_ratio=0.1)
    track1.xticks_by_interval(interval=1)
    track1.axis()
    track1.line(x, y)
    # 绘制散点
    track2 = sector.add_track((55, 75), r_pad_ratio=0.1)
    track2.axis()
    track2.scatter(x, y)
    # 绘制条形图
    track3 = sector.add_track((30, 50), r_pad_ratio=0.1)
    track3.axis()
    track3.bar(x, y)

# 绘制连接
circos.link(("A", 0, 3), ("B", 15, 12))
circos.link(("B", 0, 3), ("C", 7, 11), color="skyblue")
circos.link(("C", 2, 5), ("E", 15, 12), color="chocolate", direction=1)
circos.link(("D", 3, 5), ("D", 18, 15), color="lime", ec="black", lw=0.5, hatch="//", direction=2)
circos.link(("D", 8, 10), ("E", 2, 8), color="violet", ec="red", lw=1.0, ls="dashed")

circos.savefig("example01.png")

2. Circos图（基因组学）

from pycirclize import Circos
from pycirclize.utils import fetch_genbank_by_accid
from pycirclize.parser import Genbank

# 下载`NC_002483` E.coli质粒GenBank文件
gbk_fetch_data = fetch_genbank_by_accid("NC_002483")
gbk = Genbank(gbk_fetch_data)

# 使用基因组大小初始化Circos实例
circos = Circos(sectors={gbk.name: gbk.range_size})
circos.text(f"大肠杆菌K-12 质粒F\n\n{gbk.name}", size=14)
circos.rect(r_lim=(90, 100), fc="lightgrey", ec="none", alpha=0.5)
sector = circos.sectors[0]

# 绘制正向链CDS
f_cds_track = sector.add_track((95, 100))
f_cds_feats = gbk.extract_features("CDS", target_strand=1)
f_cds_track.genomic_features(f_cds_feats, plotstyle="arrow", fc="salmon", lw=0.5)

# 绘制反向链CDS
r_cds_track = sector.add_track((90, 95))
r_cds_feats = gbk.extract_features("CDS", target_strand=-1)
r_cds_track.genomic_features(r_cds_feats, plotstyle="arrow", fc="skyblue", lw=0.5)

# 如果存在，绘制'gene'限定符标签
labels, label_pos_list = [], []
for feat in gbk.extract_features("CDS"):
    start = int(feat.location.start)
    end = int(feat.location.end)
    label_pos = (start + end) / 2
    gene_name = feat.qualifiers.get("gene", [None])[0]
    if gene_name is not None:
        labels.append(gene_name)
        label_pos_list.append(label_pos)
f_cds_track.xticks(label_pos_list, labels, label_size=6, label_orientation="vertical")

# 绘制刻度（间隔 = 10 Kb）
r_cds_track.xticks_by_interval(
    10000, outer=False, label_formatter=lambda v: f"{v/1000:.1f} Kb"
)

circos.savefig("example02.png")

3. 弦图

from pycirclize import Circos
import pandas as pd

# 创建矩阵数据框（3 x 6）
行名 = ["F1", "F2", "F3"]
列名 = ["T1", "T2", "T3", "T4", "T5", "T6"]
矩阵数据 = [
    [10, 16, 7, 7, 10, 8],
    [4, 9, 10, 12, 12, 7],
    [17, 13, 7, 4, 20, 4],
]
矩阵数据框 = pd.DataFrame(矩阵数据, index=行名, columns=列名)

# 从矩阵初始化Circos以绘制弦图
circos = Circos.initialize_from_matrix(
    矩阵数据框,
    space=5,
    cmap="tab10",
    label_kws=dict(size=12),
    link_kws=dict(ec="black", lw=0.5, direction=1),
)

circos.savefig("example03.png")

4. 系统发育树

from pycirclize import Circos
from pycirclize.utils import load_example_tree_file, ColorCycler
from matplotlib.lines import Line2D

# 从系统发育树初始化Circos
树文件 = load_example_tree_file("large_example.nwk")
circos, tv = Circos.initialize_from_tree(
    树文件,
    r_lim=(30, 100),
    leaf_label_size=5,
    line_kws=dict(color="lightgrey", lw=1.0),
)

# 定义用于树注释的组-物种字典
# 在此例中，设置最小物种列表以指定组的最近共同祖先节点
组名到物种列表 = dict(
    单孔目=["Tachyglossus_aculeatus", "Ornithorhynchus_anatinus"],
    有袋目=["Monodelphis_domestica", "Vombatus_ursinus"],
    貧齒目=["Choloepus_didactylus", "Dasypus_novemcinctus"],
    非洲獸目=["Trichechus_manatus", "Chrysochloris_asiatica"],
    真猿类=["Galeopterus_variegatus", "Theropithecus_gelada"],
    啮齿目=["Oryctolagus_cuniculus", "Microtus_oregoni"],
    真獸類=["Talpa_occidentalis", "Mirounga_leonina"],
)

# 设置树线颜色和标签颜色
ColorCycler.set_cmap("tab10")
组名到颜色 = {name: ColorCycler() for name in 组名到物种列表.keys()}
for 组名, 物种列表 in 组名到物种列表.items():
    颜色 = 组名到颜色[组名]
    tv.set_node_line_props(物种列表, color=颜色, apply_label_color=True)

# 绘制图形并在中心设置图例
fig = circos.plotfig()
_ = circos.ax.legend(
    handles=[Line2D([], [], label=n, color=c) for n, c in 组名到颜色.items()],
    labelcolor=组名到颜色.values(),
    fontsize=6,
    loc="center",
    bbox_to_anchor=(0.5, 0.5),
)
fig.savefig("example04.png")

5. 雷达图

from pycirclize import Circos
import pandas as pd

# 创建RPG职业参数数据框（3个职业，7个参数）
df = pd.DataFrame(
    data=[
        [80, 80, 80, 80, 80, 80, 80],
        [90, 20, 95, 95, 30, 30, 80],
        [60, 90, 20, 20, 100, 90, 50],
    ],
    index=["英雄", "战士", "法师"],
    columns=["生命值", "魔法值", "攻击力", "防御力", "特攻", "特防", "速度"],
)

# 初始化Circos实例以绘制雷达图
circos = Circos.radar_chart(
    df,
    vmax=100,
    marker_size=6,
    grid_interval_ratio=0.2,
)

# 绘制图形并在右上角设置图例
fig = circos.plotfig()
_ = circos.ax.legend(loc="upper right", fontsize=10)
fig.savefig("example05.png")