plidflow: PLIDflow/scripts/pdbqtcorrector2step.R comparison

comparison PLIDflow/scripts/pdbqtcorrector2step.R @ 6:795e11fac81b draft default tip

Included new tools for standardization

author	bitlab
date	Wed, 22 Apr 2020 06:12:00 -0400
parents	6fcfa4756040
children

comparison

equal deleted inserted replaced

-:97f12f7cc852
+:795e11fac81b
+#pdbqtcorrector2step.R prepare the out PDBQT file from pdbqtcorrector.R to run Vina
+#!/usr/bin/env Rscript
+args = commandArgs(trailingOnly=TRUE)
+if(length(args) < 2){
+stop("USE: Rscript pdbqtcorrector.R <receptor_name> <galaxy_file_pdbqt> <receptor_types>")
+}
+#Argument definition
+receptor_name <- args[1]
+receptor_types_file_out <- args[3]
+#Scan file
+original_file <- scan(args[1], what = character(), quiet = TRUE, na.strings = "NULLAJSKAJSFL")
+#13FEB2019
+#In order to avoid col 1 and col 2 fussion, split by characters all words. Then paste characters fron col 1 in a word, and those for col 2, rest columns change by " "
+buscador <-  c()
+for(of in 1:length(original_file)){
+buscador <-  c(buscador,strsplit(original_file[of], ""))
+}
+fix_row_1 <- 0
+for(off in 1:length(buscador)){
+if(buscador[[off]][1] == "A"){
+if(length(buscador[[off]]) >= 3){
+if(buscador[[off]][2] == "T"){
+if(buscador[[off]][3] == "O"){
+if(buscador[[off]][4] == "M"){
+fix_row_1 <- fix_row_1 + 1
+buscador[[off]][1] <- paste(buscador[[off]][1], buscador[[off]][2], buscador[[off]][3], buscador[[off]][4], sep = "")
+if(length(buscador[[off]]) == 4){
+for(off1 in 2:length(buscador[[off]])){
+buscador[[off]][off1] <- ""
+}
+for(qu in 1:(length(buscador[[off]])-1)){
+buscador[[off]] <- buscador[[off]][-length(buscador[[off]])]
+}
+}
+if(length(buscador[[off]]) > 4){
+var_aux <- c()
+for(off1 in 5:length(buscador[[off]])){
+var_aux <- c(var_aux, paste(buscador[[off]][off1]))
+}
+termino <- var_aux[1]
+for(ofu in 2:length(var_aux)){
+termino <- paste(termino, var_aux[ofu], sep = "")
+}
+buscador[[off]][2] <- termino
+for(off1 in 3:length(buscador[[off]])){
+buscador[[off]][off1] <- ""
+}
+for(qu in 2:(length(buscador[[off]])-1)){
+buscador[[off]] <- buscador[[off]][-length(buscador[[off]])]
+}
+}
+}
+}
+}
+}
+}
+}
+#print(fix_row_1)
+fix_row_2 <- 0
+for(off in 1:length(buscador)){
+if(buscador[[off]][1] == "H"){
+if(length(buscador[[off]]) >= 3){
+if(buscador[[off]][2] == "E"){
+if(buscador[[off]][3] == "T"){
+if(buscador[[off]][4] == "A"){
+if(buscador[[off]][5] == "T"){
+if(buscador[[off]][6] == "M"){
+fix_row_2 <- fix_row_2 + 1
+buscador[[off]][1] <- paste(buscador[[off]][1], buscador[[off]][2], buscador[[off]][3], buscador[[off]][4], buscador[[off]][5], buscador[[off]][6], sep = "")
+if(length(buscador[[off]]) == 6){
+for(off1 in 2:length(buscador[[off]])){
+buscador[[off]][off1] <- ""
+}
+for(qu in 1:(length(buscador[[off]])-1)){
+buscador[[off]] <- buscador[[off]][-length(buscador[[off]])]
+}
+}
+if(length(buscador[[off]]) > 6){
+var_aux <- c()
+for(off1 in 7:length(buscador[[off]])){
+var_aux <- c(var_aux, paste(buscador[[off]][off1]))
+}
+termino <- var_aux[1]
+for(ofu in 2:length(var_aux)){
+termino <- paste(termino, var_aux[ofu], sep = "")
+}
+buscador[[off]][2] <- termino
+for(off1 in 3:length(buscador[[off]])){
+buscador[[off]][off1] <- ""
+}
+for(qu in 2:(length(buscador[[off]])-1)){
+buscador[[off]] <- buscador[[off]][-length(buscador[[off]])]
+}
+}
+}
+}
+}
+}
+}
+}
+}
+}
+#print(fix_row_2)
+fix_row_3 <- 0
+for(off in 1:length(buscador)){
+if(buscador[[off]][1] == "T"){
+if(length(buscador[[off]]) >= 3){
+if(buscador[[off]][2] == "E"){
+if(buscador[[off]][3] == "R"){
+fix_row_3 <- fix_row_3 + 1
+}
+}
+}
+}
+}
+#print(fix_row_3)
+final_row <-  fix_row_1 + fix_row_2 + fix_row_3
+#counter <- final_row
+#print(counter)
+# At this point roots "ATOM", "HETATM" and "TER" are isolated in case fusion. This step component differrent for those are pasted
+for(off in 1:length(buscador)){
+if(as.character(buscador[[off]][1]) != "ATOM" && buscador[[off]][1] != "HETATM"){
+#print(off)
+pegado <- buscador[[off]][1]
+for(fus in 2:length(buscador[[off]])){
+if(length(buscador[[off]]) > 1){
+pegado <- paste(pegado, buscador[[off]][fus], sep = "")
+buscador[[off]][1] <- pegado
+}
+}
+if(length(buscador[[off]]) > 1){
+for(qu in 1:(length(buscador[[off]])-1)){
+buscador[[off]] <- buscador[[off]][-length(buscador[[off]])]
+}
+}
+}
+}
+# strsplit applied to the original_file return a list format. In this steps it is for changing list for vector format for buscador varible
+total_original_file <- c()
+for(si in 1:length(buscador)){
+total_original_file <- c(total_original_file, buscador[[si]])
+}
+#13feb2019
+original_file <- total_original_file
+#Starts pdbqtcorrector
+#Calculate first root word and "TER"
+for(e in 1:length(original_file)){
+if(original_file[e] == "ATOM" || original_file[e] == "HETATM" || original_file[e] == "TER"){
+k <- e
+break
+}
+}
+#Calculate the row number for table which conteins aligned x,y,z coordenates
+counter <- 0
+for(c in e:length(original_file)){
+if(original_file[c] == "ATOM" || original_file[c] == "HETATM" || original_file[c] == "TER"){
+counter <- counter + 1
+}
+}
+#Table to be fills in named tabla_ordenados
+tabla_ordenados <- matrix(1, nrow = (counter), ncol = 13)
+#Calculate TER times and make a vector
+ele_ter_vector <- 1
+ter_vector <- c()
+k_position <- c()
+#ter_pos <- 0 #21sep2018
+for(o in 1:(length(original_file))){
+if(original_file[o] =="TER"){
+k_position <- c(k_position, o)
+ter_pos <- o #21sep
+for(g in o:(o+4)){
+ter_vector <- c(ter_vector,original_file[g] )
+}
+}
+}
+#Fill in the tabla_ordenados with values scaned until counter-1 since last row (ter) has diferent length and this could give you back an error
+for(i in 1:(counter-1)){
+for(j in 1:13){
+tabla_ordenados[i,j] <- original_file[k]
+if(tabla_ordenados[i,13]=="ATOM" || tabla_ordenados[i,13]== "HETATM"|| tabla_ordenados[i,13]=="TER"){
+corte <- c()
+for(v in 4:12){
+corte <- c(corte,tabla_ordenados[i,v])
+}
+coo_corte <- 1
+tabla_ordenados[i,4] <- ""
+for(m in 5:13){
+tabla_ordenados[i,m] <- corte[coo_corte]
+coo_corte <- coo_corte + 1
+}
+k <- k-1
+}
+# #################02julio2019################################
+if(tabla_ordenados[i,12]=="ATOM" || tabla_ordenados[i,12]== "HETATM"|| tabla_ordenados[i,12]=="TER"){
+#print("ENTERING")
+#stop()
+corte_2 <- c()
+for(iv in 5:11){
+corte_2 <- c(corte_2,tabla_ordenados[i,iv])
+}
+#print(corte_2)
+first_number <- substr(corte_2[5], 1, 4)
+second_number <- substr(corte_2[5], 5, 1000)
+coo_corte_2 <- 1
+tabla_ordenados[i,5] <- ""
+tabla_ordenados[i,12] <- ""
+tabla_ordenados[i,13] <- ""
+for(im in 6:13){
+tabla_ordenados[i,im] <- corte_2[coo_corte_2]
+coo_corte_2 <- coo_corte_2 + 1
+}
+k <- k-2
+tabla_ordenados[i,12] <- corte_2[6]
+tabla_ordenados[i,10] <- first_number
+tabla_ordenados[i,11] <- second_number
+}
+#################02julio2019################################
+k <- k + 1
+}
+if(tabla_ordenados[i,1]=="TER"){
+k <- k - 8
+}
+}
+#Fill in TER row until last one
+star_ter <- 2
+mmm <- 1
+for(ii in 1:counter){
+if(tabla_ordenados[ii,1]=="TER"){
+k <- k_position[mmm] + 4
+mmm <- mmm + 1
+y <- 2
+for(l in star_ter:(star_ter+3)){
+if(y%%3==0 && y!=6){
+tabla_ordenados[ii,y] <- ""
+y <- y + 1
+tabla_ordenados[ii,y] <- ter_vector[l]
+}
+tabla_ordenados[ii,y] <- ter_vector[l]
+y <- y +1
+}
+star_ter <- star_ter + 5
+for(b in 7:13){
+tabla_ordenados[ii,b] <- ""
+}
+}
+}
+##Fill if last row is not TER root
+if(ter_pos < (length(original_file)-14)){
+tpnt <- 0
+ntn <- length(original_file) - 12
+for(jnt in 1:13){
+tabla_ordenados[nrow(tabla_ordenados),jnt] <- original_file[ntn]
+ntn <- ntn + 1
+}
+}
+##Fill in last row with TER row values ##
+#ajustcel4 <-0
+if(ter_pos > (length(original_file)-14)){
+for(rtv in 1:length(ter_vector)){
+ajustcel4 <- rtv #14nov2018
+if(is.na(ter_vector[rtv])){
+ajustcel4 <- rtv - 1
+}
+}
+ter_vector_numeric <- strsplit(ter_vector[ajustcel4], "")
+last_ter <- length(ter_vector)-4
+if(length(ter_vector_numeric[[1]]) != 1){
+if(length(ter_vector) < 5){
+for(jj in 1:6){
+tabla_ordenados[counter,jj] <- ter_vector[last_ter]
+if(jj%%3==0 && jj !=6 || jj == 4){    #he incluido el jj == 4
+tabla_ordenados[counter, jj] <- ""
+last_ter <- last_ter - 1
+}
+last_ter <- last_ter + 1
+}
+for(jj in 7:13){
+tabla_ordenados[counter, jj] <- ""
+}
+}
+if(length(ter_vector) >= 5){
+for(jj in 1:7){
+tabla_ordenados[counter,jj] <- ter_vector[last_ter]
+if(jj%%3==0 && jj !=6){    #he incluido el jj == 4
+tabla_ordenados[counter, jj] <- ""
+last_ter <- last_ter -1
+}
+last_ter <- last_ter + 1
+}
+for(jj in 8:13){
+tabla_ordenados[counter, jj] <- ""
+}
+}
+}
+if(length(ter_vector_numeric[[1]]) == 1){
+if(length(ter_vector) <= 5){
+for(jj in 1:6){
+tabla_ordenados[counter,jj] <- ter_vector[last_ter]
+if(jj%%3==0 && jj !=6 ){    #he incluido el jj == 4
+tabla_ordenados[counter, jj] <- ""
+last_ter <- last_ter - 1
+}
+last_ter <- last_ter + 1
+}
+for(jj in 7:13){
+tabla_ordenados[counter, jj] <- ""
+}
+}
+if(length(ter_vector) > 5){
+for(jj in 1:7){
+tabla_ordenados[counter,jj] <- ter_vector[last_ter]
+if(jj%%3==0 && jj !=6){    #he incluido el jj == 4
+tabla_ordenados[counter, jj] <- ""
+last_ter <- last_ter -1
+}
+last_ter <- last_ter + 1
+}
+for(jj in 8:13){
+tabla_ordenados[counter, jj] <- ""
+}
+}
+}
+}
+#View(tabla_ordenados)
+#19octubre2018
+#listacol11 <- matrix(0, nrow = nrow(tabla_ordenados), ncol = 1)
+twopoint <- c()
+for(dc11 in  1:nrow(tabla_ordenados)){
+listacol11 <-strsplit(tabla_ordenados[dc11,11], "")
+if(length(listacol11[[1]]) != 0){
+num_poin <- 0
+for(findpoint in 1:length(listacol11[[1]])){
+if(listacol11[[1]][findpoint] == "."){
+num_poin <- num_poin + 1
+}
+}
+if(num_poin == 2){
+twopoint <- c(twopoint, dc11)
+unopto0 <- listacol11[[1]][1]
+dospto0 <- listacol11[[1]][5]
+for(div1pto in 2:4){
+unopto0 <- paste(unopto0, listacol11[[1]][div1pto], sep = "")
+}
+for(div2pto in 6:length(listacol11[[1]])){
+dospto0 <- paste(dospto0, listacol11[[1]][div2pto], sep = "")
+}
+#19oct2018 Voy a guardar cada fila en un vector para luego pegarlo
+vec_guarfilas <- c()
+for(vgf in 1:10){
+if(tabla_ordenados[dc11,vgf] != ""){
+vec_guarfilas <- c(vec_guarfilas, tabla_ordenados[dc11,vgf])
+}
+}
+vec_guarfilas[10] <- unopto0
+vec_guarfilas[11] <- dospto0
+vec_guarfilas[12] <- tabla_ordenados[dc11,12]
+vec_guarfilas[13] <- tabla_ordenados[dc11,13]
+#print(vec_guarfilas)
+for(mvc in 1:13){
+tabla_ordenados[dc11,mvc] <- vec_guarfilas[mvc]
+}
+}
+}
+}
+#View(tabla_ordenados)
+#acaba 19octubre2018
+#Make a table containing for each cell the number of characters for each for the tabla_ordenados
+tabla_ordenados_numcarac <- matrix(1, nrow = nrow(tabla_ordenados), ncol = ncol(tabla_ordenados))
+for(i in 1:nrow(tabla_ordenados)){
+for(j in 1:ncol(tabla_ordenados)){
+caracteres <- strsplit(tabla_ordenados[i,j], "")
+num_carac <- 0
+# if(tabla_ordenados[i,j] == ""){
+#   num_carac <- ""
+# }
+#if(tabla_ordenados[i,j] != ""){
+for(k in 1:length(caracteres[[1]])){
+num_carac <- num_carac + 1
+}
+tabla_ordenados_numcarac[i,j] <- num_carac
+#}
+}
+}
+#View(tabla_ordenados_numcarac) #27mar2019
+#################03julio2019###################3     ##
+for(i in 1:nrow(tabla_ordenados)){
+if(tabla_ordenados_numcarac[i,4] == 2 && tabla_ordenados_numcarac[i,5] == 3){
+cambio_posicion5 <- tabla_ordenados[i,5]
+tabla_ordenados[i,5] <- ""
+tabla_ordenados_numcarac[i,5] <- 2
+tabla_ordenados[i,4] <- cambio_posicion5
+tabla_ordenados_numcarac[i,4] <- 3
+}
+}
+for(i in 1:nrow(tabla_ordenados)){
+if(tabla_ordenados_numcarac[i,5] == 2 && tabla_ordenados_numcarac[i,6] == 5){
+Aaposicion5 <- substr(tabla_ordenados[i,6], 1, 1)
+cambio_posicion5 <- substr(tabla_ordenados[i,6], 2, 5)
+tabla_ordenados[i,5] <- Aaposicion5
+tabla_ordenados_numcarac[i,5] <- 1
+tabla_ordenados[i,6] <- cambio_posicion5
+tabla_ordenados_numcarac[i,6] <- 4
+}
+}
+for(i in 1:nrow(tabla_ordenados)){
+if(tabla_ordenados[i, 3] < 6 && tabla_ordenados[i, 4] == ""){
+tabla_ordenados[i, 4] <- "XX"
+}
+}
+#################03julio2019###################3     ##
+# &&&&& 03sep2019 &&&&&&&&&&&&
+if(tabla_ordenados_numcarac[counter,5] >= 5){
+ter_5_col <- substr(tabla_ordenados[counter, 5], 1, 1)
+ter_6_col <- substr(tabla_ordenados[counter, 5], 2, 1000)
+tabla_ordenados[counter, 5] <- ter_5_col
+tabla_ordenados[counter, 6] <- ter_6_col
+}
+# &&&&& 03sep2019 &&&&&&&&&&&&
+####····̣# &&&&& 30oct2019 &&&&&&&&&&&&
+for(ac3 in 1:counter){
+if(tabla_ordenados_numcarac[ac3,3] >= 7){
+ter_3_col <- substr(tabla_ordenados[ac3, 3], 1, 4)
+ter_4_col <- substr(tabla_ordenados[ac3, 3], 5, 1000)
+tabla_ordenados[ac3, 3] <- ter_3_col
+tabla_ordenados[ac3, 4] <- ter_4_col
+tabla_ordenados_numcarac[ac3, 3] <- 4
+tabla_ordenados_numcarac[ac3, 4] <- 3
+}
+}
+####····̣# &&&&& 30oct2019 &&&&&&&&&&&&
+#:;:;:;:;:;:;:;:;________09septiembre2019. Remove line with "Na" in column 13 in tabla_ordenados and tabla_ordenados_numcarac
+# quitar_fila <- 0
+# for(ena in 1:counter){
+#   if(tabla_ordenados[ena,13] == "Na"){
+#     print(ena)
+#     tabla_ordenados_numcarac <- tabla_ordenados_numcarac[-ena,]
+#     ena <- ena - 1
+#     quitar_fila <- quitar_fila + 1
+#     counter <- counter - quitar_fila
+#
+#   }
+# }
+#
+# tabla_ordenados <- subset(tabla_ordenados, tabla_ordenados[,13] != "Na")
+#:;:;:;:;:;:;:;:;________09septiembre2019
+#View(tabla_ordenados)
+#View(tabla_ordenados_numcarac)
+#Fit spaces for write()
+#Fit spaces for write()
+#Pairwise 1col-2col con 1col == "ATOM"
+for(i in 1:nrow(tabla_ordenados)){
+linea <- c()
+if(tabla_ordenados_numcarac[i,1] == 4){
+num_espacios <- 6
+ajuste <- 0
+for(a in 1:(tabla_ordenados_numcarac[i,2])){
+if(a != tabla_ordenados_numcarac[i,2]){
+ajuste <- ajuste + 1
+}
+if(a == tabla_ordenados_numcarac[i,2]){
+espacios <- rep(" ", num_espacios-ajuste)
+linea <- c(espacios, tabla_ordenados[i,2])
+break
+}
+}
+}
+#1col == HETATM INI
+if(tabla_ordenados_numcarac[i,1] == 6){
+num_espacios <- 4
+ajuste <- 0
+for(a in 1:(tabla_ordenados_numcarac[i,2])){
+if(a != tabla_ordenados_numcarac[i,2]){
+ajuste <- ajuste + 1
+}
+if(a == tabla_ordenados_numcarac[i,2]){
+espacios <- rep(" ", num_espacios-ajuste)
+linea <- c(espacios, tabla_ordenados[i,2])
+###21feb2019
+if(tabla_ordenados_numcarac[i,2] == 5){
+espacios <- rep(" ", (num_espacios-ajuste) + 1)
+linea <- c(espacios, tabla_ordenados[i,2])
+}
+###21feb2019
+break
+}
+}
+}
+#1col == HETATM FIN
+##1col == TER INICIO
+if(tabla_ordenados_numcarac[i,1] == 3){
+num_espacios <- 7
+ajuste <- 0
+for(a in 1:(tabla_ordenados_numcarac[i,2])){
+if(a != tabla_ordenados_numcarac[i,2]){
+ajuste <- ajuste + 1
+espacios <- rep(" ", num_espacios-ajuste)
+}
+if(a == tabla_ordenados_numcarac[i,2]){
+espacios <- rep(" ", num_espacios-ajuste)
+linea <- c(espacios, tabla_ordenados[i,2])
+break
+}
+}
+}
+##1col == TER FIN
+##Pairwise 2col-3col
+linea2 <- c()
+for(b in 1:(tabla_ordenados_numcarac[i,3])){
+if(b < 4){
+espacios2 <- rep(" ", 2)
+}
+if(b >= 4){
+if(tabla_ordenados[i,4] == ""){
+espacios2 <- rep(" ", 2)
+}
+if(tabla_ordenados[i,4]!= ""){
+espacios2 <- rep(" ", 1)
+}
+}
+}
+if(tabla_ordenados_numcarac[i,3] >= 8){
+e_espacios2 <- length(espacios2)-1
+espacios2 <- rep(" ",e_espacios2)
+}
+linea2 <- c(linea, espacios2, tabla_ordenados[i,3])
+###21feb2019
+if(tabla_ordenados_numcarac[i,1] == 6 && tabla_ordenados_numcarac[i,2] == 5){
+espacios2 <- espacios2[-length(espacios2)]
+linea2 <- c(linea, espacios2, tabla_ordenados[i,3])
+}
+###21feb2019
+###Pairwise 3col-4col
+linea3 <- c()
+for(c in 1:(tabla_ordenados_numcarac[i,4])){
+#28nov
+if(c == 2){
+if(tabla_ordenados_numcarac[i,1] == 6 && tabla_ordenados_numcarac[i,3] == 1){
+espacios3 <- rep(" ", 2)
+}
+if(tabla_ordenados_numcarac[i,1] == 6 && tabla_ordenados_numcarac[i,3] == 2){
+espacios3 <- rep(" ", 1)
+}
+if(tabla_ordenados_numcarac[i,1] == 6 && tabla_ordenados_numcarac[i,3] == 2 && tabla_ordenados_numcarac[i,5] == 1){
+espacios3 <- rep(" ", 3)
+}
+#########21junio2019
+if(tabla_ordenados_numcarac[i,1] == 4 &&  tabla_ordenados_numcarac[i,3] == 1 && tabla_ordenados_numcarac[i,6] == 5){
+espacios3 <- rep(" ", 2)
+}
+if(tabla_ordenados_numcarac[i,1] == 4 &&  tabla_ordenados_numcarac[i,3] == 2 && tabla_ordenados_numcarac[i,6] == 5){
+espacios3 <- rep(" ", 1)
+}
+########21junio2019
+}
+#28nov. Hace falta corregir para el resto de HETATM
+if(c == 3){
+if(b == 1){
+espacios3 <- rep(" ", 3)
+}
+if(b == 2){
+espacios3 <- rep(" ", 2)
+}
+if(b >= 3){
+espacios3 <- rep(" ", 1)
+}
+}
+if(c == 4){
+if(b == 1){
+espacios3 <- rep(" ", 2)
+}
+if(b >= 2){
+espacios3 <- rep(" ", 1)
+}
+}
+#27mar2019 ######################################
+if(c == 5){
+if(b >= 2){
+espacios3 <- rep("", 1)
+}
+}
+#27mar2019 ######################################
+}
+linea3 <- c(linea2, espacios3, tabla_ordenados[i,4])
+####03julio2019####################### #####################
+# if(tabla_ordenados_numcarac[i,3] == 3 && tabla_ordenados_numcarac[i,4] == 3 && tabla_ordenados_numcarac[i,5] == 2 && tabla_ordenados_numcarac[i,6] == 5){
+#   linea3 <- c(linea2, " ", tabla_ordenados[i,4])
+# }
+####03julio2019####################### #####################
+#TER
+if(tabla_ordenados_numcarac[i,1] == 3){
+num_espacios4 <- 8
+ajuste_t1 <- 0
+for(l in 1:tabla_ordenados_numcarac[i,4]){
+if(l != tabla_ordenados_numcarac[i,4]){
+ajuste_t1 <-ajuste_t1 + 1
+num_espacios4 <- 8 - ajuste_t1
+}
+if(l == tabla_ordenados_numcarac[i,4]){
+num_espacios4 <- 8 - ajuste_t1
+}
+}
+linea3 <- c(linea, rep(" ", num_espacios4), tabla_ordenados[i,4])
+}
+####Pairwise 4col-5col
+linea4 <- c()
+if(tabla_ordenados_numcarac[i,1] != 3){
+if(tabla_ordenados_numcarac[i,3] >= 7){
+linea4 <- c(linea3, tabla_ordenados[i,5])
+}
+if(tabla_ordenados_numcarac[i,3] < 7){
+linea4 <- c(linea3, " ", tabla_ordenados[i,5])
+###18oct2018
+if(tabla_ordenados_numcarac[i,3] >= 3 && tabla_ordenados[i,4] == ""){
+linea4 <- c(linea2, " ", tabla_ordenados[i,5])
+}
+###18oct2018
+}
+#------------29julio2019--------------------#
+if(isTRUE(tabla_ordenados[i,3] == "NA") && tabla_ordenados[i,4] == ""){
+linea4 <- c(linea2, rep(" ", 6), tabla_ordenados[i,5])
+}
+#------------29julio2019--------------------#
+}
+if(tabla_ordenados_numcarac[i,1] == 3){
+linea4 <- c(linea3, " ", tabla_ordenados[i,5])
+##
+if(tabla_ordenados[i,4] == ""){
+linea4 <- c(linea2,rep(" ", 4),tabla_ordenados[i,5])
+}
+##
+}
+#####Pairwise 5col-6col. NO espacios4
+if(tabla_ordenados_numcarac[i,1] != 3){
+linea5 <-c()
+for(d in 1:(tabla_ordenados_numcarac[i,6])){
+if(d == 1){
+espacios5 <- rep(" ", 3)
+}
+if(d == 2){
+espacios5 <- rep(" ", 2)
+}
+if(d >= 3){
+espacios5 <- rep(" ", 1)
+}
+##################21junio2109#############
+if(tabla_ordenados_numcarac[i,3] == 2 && tabla_ordenados_numcarac[i,5] == 2 && tabla_ordenados_numcarac[i,6] == 5){
+espacios5 <- rep(" ", 2)
+}
+##################21junio2109#############
+###########03julio################                 ############
+# if(tabla_ordenados_numcarac[i,3] == 1 && tabla_ordenados_numcarac[i,4] == 3 && tabla_ordenados_numcarac[i,5] == 2 && tabla_ordenados_numcarac[i,6] == 5){
+#
+#   espacios5 <- ""
+# }
+###########03julio################                 ############
+}
+linea5 <- c(linea4, espacios5, tabla_ordenados[i,6])
+}
+if(tabla_ordenados_numcarac[i,1] == 3){
+for(dd in 1:(tabla_ordenados_numcarac[i,6])){
+if(dd == 1){
+espacios55 <- rep(" ", 3)
+}
+#14nov
+if(dd == 1 && tabla_ordenados_numcarac[i,5] == 3){
+espacios55 <- rep(" ", 1)
+}
+#14nov
+if(dd == 2){
+espacios55 <- rep(" ", 2)
+}
+if(dd >= 3){
+espacios55 <- rep(" ", 1)
+}
+}
+linea5 <- c(linea4, espacios55, tabla_ordenados[i,6])
+#------------------05sep2019------------#
+if(tabla_ordenados_numcarac[i,6] == 1 && tabla_ordenados_numcarac[i,5] >= 5){
+espacios55 <- rep(" ", 1)
+linea5 <- c(linea4, espacios55, tabla_ordenados[i,6])
+}
+#------------------05sep2019------------#
+}
+######Pairwise 6col-7col
+linea6 <- c()
+if(tabla_ordenados_numcarac[i,7] == 5){
+espacios6 <- rep(" ", 7)
+linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+###################21junio2109#################
+if(tabla_ordenados_numcarac[i,3] == 4 && tabla_ordenados_numcarac[i,6] == 5){
+espacios6 <- rep(" ", 6)
+linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+}
+###################21junio2109#################
+##    03julio2019   #########
+if(tabla_ordenados_numcarac[i,6] == 4 && tabla_ordenados_numcarac[i,6] == 4){
+espacios6 <- rep(" ", 6)
+linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+}
+##    03julio2019   #########
+}
+if(tabla_ordenados_numcarac[i,7] > 5){
+out_spaces <- tabla_ordenados_numcarac[i,7] - 5
+espacios6 <- rep(" ", (7-out_spaces))
+linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+###################21junio2109#################
+if(tabla_ordenados_numcarac[i,3] == 4 && tabla_ordenados_numcarac[i,6] == 5){
+out_spaces <- tabla_ordenados_numcarac[i,7] - 4
+espacios6 <- rep(" ", (7-out_spaces))
+linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+}
+###################21junio2109#################
+##    03julio2019   #########
+if(tabla_ordenados_numcarac[i,6] == 4 && tabla_ordenados_numcarac[i,6] == 4){
+out_spaces_2 <- tabla_ordenados_numcarac[i,7] - 4
+espacios6 <- rep(" ", (7-out_spaces_2))
+linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+}
+##    03julio2019   #########
+}
+######################################27mar2019
+#
+# if(tabla_ordenados_numcarac[i,4] == 5){
+#   espacios6 <- rep(" ",5)
+#   linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+# }
+#
+# if(tabla_ordenados_numcarac[i,4] > 5){
+#   espacios6 <- rep(" ",4)
+#   linea6 <-c(linea5, espacios6, tabla_ordenados[i,7])
+# }
+######################################27mar2019
+#######Pairwise 7col-8col
+linea7 <- c()
+ajuste3 <- 0
+if(tabla_ordenados_numcarac[i,8] == 5){
+espacios7 <- rep(" ", 3)
+linea7 <-c(linea6, espacios7, tabla_ordenados[i,8])
+}
+if(tabla_ordenados_numcarac[i,8] == 6){
+espacios7 <- rep(" ", 2)
+linea7 <-c(linea6, espacios7, tabla_ordenados[i,8])
+}
+if(tabla_ordenados_numcarac[i,8] > 6){
+espacios7 <- rep(" ", 1)
+linea7 <-c(linea6, espacios7, tabla_ordenados[i,8])
+}
+########Pairwise 8col-9col
+linea8 <- c()
+ajuste4 <- 0
+if(tabla_ordenados_numcarac[i,9] == 5){
+espacios8 <- rep(" ", 3)
+linea8 <-c(linea7, espacios8, tabla_ordenados[i,9])
+}
+if(tabla_ordenados_numcarac[i,9] == 6){
+espacios8 <- rep(" ", 2)
+linea8 <-c(linea7, espacios8, tabla_ordenados[i,9])
+}
+if(tabla_ordenados_numcarac[i,9] > 6){
+espacios8 <- rep(" ", 1)
+linea8 <-c(linea7, espacios8, tabla_ordenados[i,9])
+}
+#########Pairwise 9col-10col
+linea9 <- c()
+if(tabla_ordenados_numcarac[i,10] == 4){
+espacios9 <- rep(" ", 2)
+linea9 <- c(linea8, espacios9, tabla_ordenados[i,10])
+}
+if(tabla_ordenados_numcarac[i,10] > 4){
+espacios9 <- rep(" ", 1)
+linea9 <- c(linea8, espacios9, tabla_ordenados[i,10])
+}
+##########Pairwise 10col-11col
+# linea10 <- c()
+# if(tabla_ordenados_numcarac[i,11] == 4){
+#   espacios10 <- rep(" ", 2)
+#   linea10 <- c(linea9, espacios10, tabla_ordenados[i,11])
+# }
+# if(tabla_ordenados_numcarac[i,11] > 4){
+#   espacios10 <- rep(" ", 1)
+#   linea10 <- c(linea9, espacios10, tabla_ordenados[i,11])
+# }
+#22oct2018
+##########Pairwise 10col-11col
+linea10 <- c()
+if(tabla_ordenados_numcarac[i,11] == 4){
+espacios10 <- rep(" ", 3)
+linea10 <- c(linea9, espacios10, tabla_ordenados[i,11])
+}
+if(tabla_ordenados_numcarac[i,11] == 5){
+espacios10 <- rep(" ", 2)
+linea10 <- c(linea9, espacios10, tabla_ordenados[i,11])
+}
+if(tabla_ordenados_numcarac[i,11] > 5){
+espacios10 <- rep(" ", 1)
+linea10 <- c(linea9, espacios10, tabla_ordenados[i,11])
+}
+#22oct2018
+###########Pairwise 11col-12col
+linea11 <- c()
+if(tabla_ordenados_numcarac[i,12] == 5){
+espacios11 <- rep(" ", 5)
+linea11 <-c(linea10, espacios11, tabla_ordenados[i,12])
+}
+ajuste5 <- 0
+for(h in 6:tabla_ordenados_numcarac[i,12]){
+if(tabla_ordenados_numcarac[i,12] > 5){
+ajuste5 <- ajuste5 + 1
+espacios11 <- rep(" ", (5-ajuste5))
+##espacios11 <- rep(" ", (5-ajuste5))
+linea11 <-c(linea10, espacios11, tabla_ordenados[i,12])
+}
+}
+############Pairwise 12col-13col
+linea12 <- c(linea11," ", tabla_ordenados[i,13])
+#TER
+if(tabla_ordenados_numcarac[i,1] == 3){
+cabecera <- tabla_ordenados[i,1]
+for(w in 1:length(linea5)){
+cabecera <- paste(cabecera,linea5[w], sep = "")
+}
+#write(cabecera, file = "1z95_wo_198andwater_ph7_MOD.pdbqt", append = TRUE)
+write(cabecera, file = args[2], append = TRUE)
+}
+#!= TER
+if(tabla_ordenados_numcarac[i,1] != 3){
+cabecera <- tabla_ordenados[i,1]
+for(w in 1:length(linea12)){
+cabecera <- paste(cabecera,linea12[w], sep = "")
+}
+#write(cabecera, file = "1z95_wo_198andwater_ph7_MOD.pdbqt", append = TRUE)
+write(cabecera, file = args[2], append = TRUE)
+}
+}
+#21junio2019
+# #### Make file receptor_atm_types.txt to be paste in the GPF file ###
+prereceptor_atmtypes <- c()
+for(i in 1:nrow(tabla_ordenados)){
+if(tabla_ordenados[i,13] != ""){
+prereceptor_atmtypes <- c(prereceptor_atmtypes, tabla_ordenados[i,13])
+}
+}
+#
+receptor_atmtypes <- unique(prereceptor_atmtypes)
+#
+filtered_receptor <- c()
+for(i in 1:length(receptor_atmtypes)){
+	#print(receptor_atmtypes[i])
+	#print(is.na(as.numeric(receptor_atmtypes[i])))
+	if(suppressWarnings(is.na(as.numeric(receptor_atmtypes[i])))){
+		filtered_receptor <- c(filtered_receptor, receptor_atmtypes[i])
+	}
+}
+receptor_atmtypes <- filtered_receptor
+cabeceratm <- receptor_atmtypes[1]
+for(rat in 2:length(receptor_atmtypes)){
+cabeceratm <- paste(cabeceratm, receptor_atmtypes[rat], sep = " ")
+}
+write(cabeceratm, file = receptor_types_file_out, append = FALSE)
+#21junio2019
+# #::::::::06sep2019:::::::::::::::::#
+#
+# #Make the file receptor_types_file_out.txt removing duplicates and Na
+# #21junio2019
+#
+# #
+# prereceptor_atmtypes <- c()
+# for(i in 1:nrow(tabla_ordenados)){
+#   if(tabla_ordenados[i,13] != ""){
+#     prereceptor_atmtypes <- c(prereceptor_atmtypes, tabla_ordenados[i,13])
+#   }
+# }
+# #
+# # #print(prereceptor_atmtypes)
+# #
+# receptor_atmtypes <- unique(prereceptor_atmtypes)
+# #21junio2019
+#
+# quitar <- 0
+# for(i in 1:length(receptor_atmtypes)){
+#   if(isTRUE(receptor_atmtypes[i] == "Na")){
+#     quitar <- i
+#     break
+#   }
+# }
+#
+# if(quitar == 0){
+#   cabeceratm <- receptor_atmtypes[1]
+#   for(rat in 2:length(receptor_atmtypes)){
+#     cabeceratm <- paste(cabeceratm, receptor_atmtypes[rat], sep = " ")
+#   }
+#
+#   write(cabeceratm, file = "receptor_types_file_out.txt", append = FALSE)
+# }
+#
+# if(quitar != 0){
+#   receptor_atmtypes <- receptor_atmtypes[-quitar]
+#   cabeceratm_types <- receptor_atmtypes[1]
+#   for(at_t in 2:length(receptor_atmtypes)){
+#    cabeceratm_types <- paste(cabeceratm_types, receptor_atmtypes[at_t], sep = " ")
+#   }
+#   write(cabeceratm_types, file = "receptor_types_file_out.txt", append = FALSE)
+# }

Mercurial > repos > bitlab > plidflow

comparison PLIDflow/scripts/pdbqtcorrector2step.R @ 6:795e11fac81b draft default tip