Created
November 30, 2012 17:25
-
-
Save karelfiser/4177161 to your computer and use it in GitHub Desktop.
find_kinase_consensus_in_proteins
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
## Find a kinase (here ABL1) consensus sequence in protein sequences using R. | |
proteins <- c("P00519", "P46109", "P61769") # ABL1, CRKL, B2M | |
for (ii in proteins) { | |
prot_url <- paste("http://www.uniprot.org/uniprot/", ii, ".fasta", sep="") # url of protein fasta | |
protein_fasta <- scan(file=url(prot_url), what="character", sep="\t") # read the protein fasta | |
protein_seq <- paste(protein_fasta[2:length(protein_fasta)], collapse="") # amino acid sequence only | |
# print(protein_seq) | |
for (ik in which(strsplit(protein_seq, '')[[1]]=='Y')) { | |
tyr_context <- substr(protein_seq, ik-1, ik+3) | |
# print(tyr_context) | |
# search for ABL1 specific sequence: I/V/L-Y-X-X-P/F: | |
x <- grep(pattern = "[IVL]Y..[PF]", x = tyr_context, value = TRUE) | |
if (length(x)!=0) { | |
print(paste(ii, ": ", x, sep="")) | |
} | |
} | |
} | |
# Homework: | |
# 1) Try to search through protein_seq directly (don't use strsplit by Y). | |
# 2) Find other Tyr or Ser/Thr kinases target sequences. | |
# 3) Convert Uniprot ids to gene symbols. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment