python 画基因图

Python是当下非常流行的编程语言之一，而在生物信息学领域，python也大有用途。例如，我们可使用python来画基因图。

# 导入需要使用的库
from reportlab.lib import colors
from reportlab.lib.units import cm
from Bio.Graphics import GenomeDiagram
from Bio import SeqIO
# 读取序列数据
record = SeqIO.read("NC_000964.gbk", "genbank")
# 创建基因图对象
gd_diagram = GenomeDiagram.Diagram("Escherichia coli str. K⑴2 substr. MG1655")
# 添加一个轴线
gd_track_for_features = gd_diagram.new_track(1, name="Annotated Features")
gd_feature_set = gd_track_for_features.new_set()
# 遍历特点
for feature in record.features:
if feature.type != "gene":
# 只绘制基因特点
continue
# 绘制基因的外围
color = colors.blue
start, end = feature.location.start, feature.location.end
gene_feature = gd_feature_set.add_feature(feature, sigil="ARROW", color=color, label=True, label_size=14, label_angle=0)
# 绘制内部注释
for site, name, color in [("TSS", "green", colors.green), ("promoter", "blue", colors.blue), ("RBS", "purple", colors.purple), ("CDS", "orange", colors.orange)]:
if site in feature.qualifiers:
site_feature = SeqFeature(FeatureLocation(feature.qualifiers[site][0]-start, feature.qualifiers[site][0]-start+1), strand=feature.strand)
gd_feature_set.add_feature(site_feature, sigil="OCTO", color=color, label=True, label_size=10, label_color=color, label_angle=0)
# 设置图象参数并生成输出
gd_diagram.draw(format="circular", circular=True, pagesize=(20*cm,20*cm), start=0, end=len(record), circle_core=0.5)
gd_diagram.write("ecoli_gene_map.pdf", "PDF")

上述代码可以用于读取NCBI数据库中的Escherichia coli str. K⑴2 substr. MG1655基因序列并画出基因图，其中利用了reportlab和Bio库中的一些函数和类来绘图。使用python画基因图可让我们更好地了解基因结构和功能，有助于进一步的生物信息学研究和分析。