Progress batman
From CSBLwiki
(Difference between revisions)
(→How to get residue correlation matrix) |
|||
| Line 12: | Line 12: | ||
==ADDA algorithm== | ==ADDA algorithm== | ||
===How to get residue correlation matrix=== | ===How to get residue correlation matrix=== | ||
| - | <pre> | + | <pre style col="blue"> |
# set working directory | # set working directory | ||
setwd("/Users/igchoi/Downloads/") | setwd("/Users/igchoi/Downloads/") | ||
| + | |||
# read blast table | # read blast table | ||
tmp = read.table("sample.tab",sep="\t") | tmp = read.table("sample.tab",sep="\t") | ||
| - | # dimension | + | |
| + | # check dimension of table | ||
dim(tmp) | dim(tmp) | ||
| - | # | + | |
| + | # change simpler GI number (skip this if you don't understand) | ||
tmp[,1] = sapply(as.vector(tmp[,1]), function(x) { | tmp[,1] = sapply(as.vector(tmp[,1]), function(x) { | ||
y = strsplit(x,"\\|"); return(unlist(y)[2]) }) | y = strsplit(x,"\\|"); return(unlist(y)[2]) }) | ||
tmp[,2] = sapply(as.vector(tmp[,2]), function(x) { | tmp[,2] = sapply(as.vector(tmp[,2]), function(x) { | ||
y = strsplit(x,"\\|"); return(unlist(y)[2]) }) | y = strsplit(x,"\\|"); return(unlist(y)[2]) }) | ||
| - | # | + | |
| + | # check the result | ||
tmp[1:5,] | tmp[1:5,] | ||
| - | # V7 | + | |
| - | # query = 590 residues | + | # aligned region: V7 V8, V9 V10 |
| - | count.que = matrix(0,nrow(tmp),590) | + | # query length = 590 residues |
| + | count.que = matrix(0,nrow(tmp),590) # <- build empty 'aligned' matrix | ||
for(i in 1:nrow(tmp)) { | for(i in 1:nrow(tmp)) { | ||
res = unlist(tmp[i,7:8]) | res = unlist(tmp[i,7:8]) | ||
| Line 34: | Line 39: | ||
count.que[i,c(res[1]:res[2])] = 1 | count.que[i,c(res[1]:res[2])] = 1 | ||
} | } | ||
| + | |||
| + | # check aligned region (blue colored regions are aligned with other proteins - central region) | ||
image(t(count.que),col=c("white","blue")) | image(t(count.que),col=c("white","blue")) | ||
| - | # count number of neighbors occurring both position i and j | + | |
| - | corr = matrix(0,590,590) | + | # count number of neighbors occurring both position i and j (using 'aligned' matrix) |
| + | corr = matrix(0,590,590) # <- set empty correlation matrix (590 x 590) | ||
| + | |||
for (i in 1:ncol(count.que)) { | for (i in 1:ncol(count.que)) { | ||
for (j in i:ncol(count.que)) { | for (j in i:ncol(count.que)) { | ||
| Line 45: | Line 54: | ||
} | } | ||
} | } | ||
| + | |||
| + | # range of number of neighbors (among 52 hits) | ||
range(corr) | range(corr) | ||
| + | |||
| + | # check highly correlated region in the correlation matrix | ||
image(corr,col=topo.colors(10)) | image(corr,col=topo.colors(10)) | ||
| + | |||
</pre> | </pre> | ||
Revision as of 13:01, 14 February 2011
Contents |
2011
- Reference: PDF download
Error fetching PMID 12706730:
- Error fetching PMID 12706730:
Schedule
ADDA algorithm
How to get residue correlation matrix
# set working directory
setwd("/Users/igchoi/Downloads/")
# read blast table
tmp = read.table("sample.tab",sep="\t")
# check dimension of table
dim(tmp)
# change simpler GI number (skip this if you don't understand)
tmp[,1] = sapply(as.vector(tmp[,1]), function(x) {
y = strsplit(x,"\\|"); return(unlist(y)[2]) })
tmp[,2] = sapply(as.vector(tmp[,2]), function(x) {
y = strsplit(x,"\\|"); return(unlist(y)[2]) })
# check the result
tmp[1:5,]
# aligned region: V7 V8, V9 V10
# query length = 590 residues
count.que = matrix(0,nrow(tmp),590) # <- build empty 'aligned' matrix
for(i in 1:nrow(tmp)) {
res = unlist(tmp[i,7:8])
print(res)
count.que[i,c(res[1]:res[2])] = 1
}
# check aligned region (blue colored regions are aligned with other proteins - central region)
image(t(count.que),col=c("white","blue"))
# count number of neighbors occurring both position i and j (using 'aligned' matrix)
corr = matrix(0,590,590) # <- set empty correlation matrix (590 x 590)
for (i in 1:ncol(count.que)) {
for (j in i:ncol(count.que)) {
print(paste(i,j))
chk = count.que[,i]+count.que[,j]
cnt = length(which(chk==2))
corr[i,j] = cnt
}
}
# range of number of neighbors (among 52 hits)
range(corr)
# check highly correlated region in the correlation matrix
image(corr,col=topo.colors(10))
