利宾斯基规则筛选小分子

#=======================================================

#=======================================================

rm(list=ls())

library(ChemmineR)
library(BioMedR)

dt <- data.frame(name=c(1:1604), smie =c(1:1604))

sdfset <- read.SDFset("drug_fda.sdf")

for (i in 1:1604) {
  
  smiles <- sdf2smiles(sdfset[i]) 
  smiles <- smiles@smilist
  dt$smie[i] <- smiles
  
}

dt$smie <- as.character( dt$smie)




setwd("D:\\SCIwork\\F41\\IFI44")

mols = readMolFromSDF("drug_fda.sdf")

dat = extrDrugRuleOfFive(mols)

head(dat)

dat$name <- rownames(dat)


data_rule <- merge(dat, dt, by="name")

write.csv(data_rule, file = "data_rule.csv")

data_rule <-  subset(data_rule, data_rule$LipinskiFailures == 0 )
# 
# write.csv(data_rule, file = "data_rule1.csv")


drug <- read.csv("fda.csv", header = T)

names(drug)[2] <- 'smie'

data_rule <- merge(drug,data_rule,  by="smie")


vs <- read.csv("virtualscreening.csv", header = T)

vs <- subset(vs, select = c("Ligand"  ,    "Binding.Energy"))

names(vs)[1] <- 'zinc_id'

comdata <- merge(vs, data_rule, by="zinc_id")

write.csv(comdata, file = "comdata.csv")