Mercurial > repos > bitlab > plidflow

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

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Included new tools for standardization
author bitlab
date Wed, 22 Apr 2020 06:12:00 -0400
parents 6fcfa4756040
children
comparison
equal deleted inserted replaced
5:97f12f7cc852 6:795e11fac81b
1 #clusterfilemaker.R makes a file containg geometric center coordenates for FILL_Xout1.pdb files. X represents envelopes size from 10 to 100
2
3 #!/usr/bin/env Rscript
4 args = commandArgs(trailingOnly=TRUE)
5
6 if(length(args) < 1){
7 stop("USE: Rscript clusterfilemaker.R <session_id>")
8 }
9
10 #Select the directory where all files are being stored
11
12 session_id <- args[1]
13
14 print(session_id)
15
16 setwd(session_id)
17
18 #Scan dataset containig FILL_<point>out1.pdb with point from 10 to 500
19 fill_outs_1 <- scan("templatefillouts1.txt", what = character(), quiet = TRUE)
20
21 #Write the head for the file later created which contains the middle point from FILL_<point>out1.pdb with point from 10 to 500
22 cabecera_fillfile <- paste("npts", sep = ";")
23 cabecera <- c("x","y","z")
24
25 for(i in 1:3){
26 cabecera_fillfile <- paste(cabecera_fillfile, cabecera[i], sep=";")
27 }
28 write(cabecera_fillfile, file="fillouts1file.txt", append= TRUE)
29
30 #Loop to read the files FILL_<point>out1.pdb and calculate the middle point
31 num_points <- 0
32 start_env <- 10 # to fit the first envelope size. In case to change envelope size, only modify this parameter
33 jp <- 10 #jump between envelopes size. In case modify jump between envelopes size, only modify this parameter
34 #In case modify start envelope size and jump, only modify start_env and jp parameters in the script nothing in following steps
35
36
37
38
39
40 num_points <- (start_env - jp)
41 for(f in 1:length(fill_outs_1)){
42 # print(paste("Testing file ", fill_outs_1[f]))
43 if(file_test("-f", fill_outs_1[f])){
44 archivo <- scan(fill_outs_1[f], what = character(), quiet = TRUE)
45 }else{
46 next
47 }
48
49 #Make a table with only x, y, z coordenates for C atoms only
50 salto <- 0
51 for(i in 1:(length(archivo)-2)){
52 if(archivo[i] == "ATOM" && ( archivo[i+2] == "C" || archivo[i+2] == "O" || archivo[i+2] == "H" )){
53 salto <- salto + 1
54 }
55 }
56 tablaC <- matrix(1, nrow = salto, ncol = 4)
57
58 #Names for columns
59 ##First column correspond to position for atoms C. This column will be created when the C atom positions will be know
60 ###Write the name for columns and rows
61 colnames(tablaC) <- c("C Position","X", "Y", "z")
62 rownames(tablaC) <- 1:salto
63
64 #Calculate the number of C atoms and to write theirs coordenates x,y,z in the tablaC
65 salto <- 0
66 posicionC <- c()
67 for(i in 1:(length(archivo)-2)){
68 if(archivo[i] == "ATOM" && ( archivo[i+2] == "C" || archivo[i+2] == "O" || archivo[i+2] == "H" )){
69 salto <- salto + 1
70 posicionC <- c(posicionC, archivo[i+1])
71 tablaC[salto,2] <- as.numeric(archivo[i+5])
72 tablaC[salto,3] <- as.numeric(archivo[i+6])
73 tablaC[salto,4] <- as.numeric(archivo[i+7])
74 }
75 }
76
77 #Write the C atoms positions in column 1 of the table tablaC
78 for(i in 1:salto){
79 tablaC[i,1] <- as.numeric(posicionC[i])
80 }
81
82 #Calculate middle point for the FILL_<point>out1.pdb given
83 pto_x_medio <- (max(tablaC[,2]) + min(tablaC[,2]))/2
84 pto_y_medio <- (max(tablaC[,3]) + min(tablaC[,3]))/2
85 pto_z_medio <- (max(tablaC[,4]) + min(tablaC[,4]))/2
86
87 #Write a plain text called fillouts1file.txt which contain in the first column number of point
88 #for the envelope according to AutoLigand program. Columns 2,3,4 for coordenates x, y ,z
89 #for the middle points for FILL_<point>out1.pdb from 10 to 500 points
90 num_points <- num_points + jp
91 write(paste(num_points,pto_x_medio, pto_y_medio, pto_z_medio, sep=";"),file="fillouts1file.txt", append= TRUE)
92 }
93
94
95
96
97
98
99
100
101