获得kegg通路中所有基因的名称，并将他们合并去重

获取kegg基因名称，Entry号是hsa04010

r语言：

library("KEGGREST")

path_way<-'hsa04010'

keggGet(path_way)

gs<-keggGet(path_way)

#获取通路中gene信息

gs[[1]]$GENE

#查找所有基因

genes<-unlist(lapply(gs[[1]]$GENE,function(x) strsplit(x,';')))

genelist <- genes[1:length(genes)%%3 ==2]

genelist <- data.frame(genelist)  

#把结果写入表格中

# 设置路径

path <- "~/Desktop/paper/data/pathway/"

# 将列表输出为CSV文件

write.csv(genelist, file = paste0(path, "genelist.csv"), row.names = FALSE) 

获得csv文件后使用python进行合并和去重

import pandas as pd
df1 = pd.read_csv('/Users/yaodashuai/Desktop/paper/data/pathway/cell_cycle.csv')
df2 = pd.read_csv('/Users/yaodashuai/Desktop/paper/data/pathway/RTK-RAS.csv')
df3 = pd.read_csv('/Users/yaodashuai/Desktop/paper/data/pathway/p53.csv')
df4 = pd.read_csv('/Users/yaodashuai/Desktop/paper/data/pathway/pi3k.csv')
# 将四个数据框的第一列连接起来
merged_column = pd.concat([df1.iloc[:, 0], df2.iloc[:, 0], df3.iloc[:, 0], df4.iloc[:, 0]], ignore_index=True)

# 将合并后的数据保存到一个新的CSV文件
df_merged = pd.DataFrame(merged_column, columns=['genelist'])
df_merged.to_csv('/Users/yaodashuai/Desktop/paper/data/pathway/merged.csv', index=False)

# 读取合并后的数据
merged_genes = pd.read_csv('/Users/yaodashuai/Desktop/paper/data/pathway/merged.csv')

# 对基因进行去重
unique_genes = merged_genes['genelist'].drop_duplicates()

# 创建带有去重基因的DataFrame
df_unique = pd.DataFrame(unique_genes, columns=['genelist'])

# 保存去重后的数据到一个新的CSV文件
df_unique.to_csv('/Users/yaodashuai/Desktop/paper/data/pathway/quchong_data.csv', index=False)

# 读取gene列表
path_genes = pd.read_csv('/Users/yaodashuai/Desktop/paper/data/pathway/quchong_data.csv')

# 提取基因名称列
gene_names = path_genes.iloc[:, 0]  # 假设基因名称在第一列

# 读取基因表达谱数据
gene_expression_data = pd.read_csv('/Users/yaodashuai/Desktop/paper/data/data_log/ov.csv')

# 根据基因名称筛选pathway的表达数据
differential_expression_data = gene_expression_data[gene_expression_data.iloc[:, 0].isin(gene_names)]
# 假设基因表达谱中的基因名称也在第一列

# 将DEGs的表达数据保存为新的CSV文件
differential_expression_data.to_csv('/Users/yaodashuai/Desktop/paper/data/test/pathway.csv', index=False)