tcmsp中药靶点基因一键提取R语言程序

 快速提取TCMSP - Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform

 搜索的中药成分对应的基因靶点R程序，可同时提取多味药物对应的基因靶点。

library(rvest)
library(httr)
library(jsonlite)
library(dplyr)
library(data.table)
library(tidyverse)

# 需要把下一行双引号里的文本替换成文“本段程序”所在目录的路径，并把‘\’,改成‘\\’
setwd("E:\\code\\R")

obThresholdValue = 30
dlThresholdValue = 0.18

# 填写药名称（可填写多个）
names <- c(
  'Aiye'
)

# 填写药对应的链接，与上面填写的药名称顺序一致
urls <- c(
    'https://tcmsp-e.com/tcmspsearch.php?qr=Folium%20Artemisiae%20Argyi&qsr=herb_en_name&token=a321854fbffcb9d42104d5c55dd71c15'
)

all_drug_target <- tibble(Drug=NA,MOL_ID=NA,molecule_name=NA,target_name=NA)

num <- 1
for (url in urls) {
  name <- names[num]
  print(name)
  num <- num + 1
  web <- read_html(GET(url,encoding="UTF-8", config(ssl_verifypeer = FALSE)))

  tcmsp <- web %>% html_elements("script") %>% html_text()
  test1 <- str_extract_all(tcmsp,"data:\\s\\[.*\\]")
  test2 <- unlist(test1[12])

  drug_m <- str_replace(test2[1], "data:","") %>% fromJSON(simplifyVector = TRUE) %>% mutate(across(c(ob, dl), as.numeric)) %>% filter(ob >= obThresholdValue & dl >= dlThresholdValue)
  drug_t <- str_replace(test2[2], "data:","") %>% fromJSON(simplifyVector = TRUE) %>% semi_join(drug_m, by = "MOL_ID") %>% tibble() %>% add_column(Drug = name, .before = 'molecule_ID') %>% select(Drug, MOL_ID, molecule_name, target_name)
  all_drug_target <- all_drug_target %>% add_row(drug_t)
}

all_drug_target <- all_drug_target %>% filter(!is.na(Drug) & !is.na(MOL_ID) & !is.na(molecule_name) & !is.na(target_name)) %>% distinct(target_name, molecule_name, Drug, MOL_ID, .keep_all = TRUE)

write.table(all_drug_target, file="AllDrugTarget.txt", sep="\t", row.names=FALSE, quote = FALSE)