Buck9195/shared_Rscripts
1
0
Fork 0
mirror of https://github.com/dchakro/shared_Rscripts.git synced 2026-05-17 09:12:16 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Squashed commit of the following:

Browse source 
commit 631eef6e8b
Author: Deepankar Chakroborty <deepankar.chakroborty@utu.fi>
Date:   Wed Jul 29 14:41:00 2020 +0300

    Switch to stringi to improve performance.

commit 99a6589b9b
Author: Deepankar Chakroborty <deepankar.chakroborty@utu.fi>
Date:   Wed Jul 29 14:39:44 2020 +0300

    Include MutSiteFind.R and improved installing dependencies

    unparalogMutations checks & installs dependencies only when it is sourced, and not everytime the function was called (as previously).

commit a044ac9f09
Author: Deepankar Chakroborty <deepankar.chakroborty@utu.fi>
Date:   Wed Jul 29 14:19:03 2020 +0300

    updated 20200714

commit cd79464c4e
Author: Deepankar Chakroborty <deepankar.chakroborty@utu.fi>
Date:   Wed Jul 29 13:12:47 2020 +0300

    Squashed commit of the following:

    commit 23f5db8f0f
    Author: Deepankar Chakroborty <deepankar.chakroborty@utu.fi>
    Date:   Wed Jul 29 13:12:26 2020 +0300

        Changed to Apache License 2.0

    commit 21ad1ee706
    Author: Deepankar Chakroborty <deepankar.chakroborty@utu.fi>
    Date:   Wed Jul 29 13:12:05 2020 +0300

        Update info section
This commit is contained in:
Deepankar Chakroborty 2020-07-29 14:43:39 +03:00
parent 23f5db8f0f
commit 4c3b85200c
3 changed files with 32 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

25
MutSiteFind.R Normal file
View file

@ -0,0 +1,25 @@
# #<---------------------------->
# # Please include this section when distributing and/or using this code.
# # Please read and abide by the terms of the included LICENSE
# #
# # Author : Deepankar Chakroborty (https://gitlab.utu.fi/deecha)
# # Report issues: https://gitlab.utu.fi/deecha/shared_scripts/-/issues
# # License: https://gitlab.utu.fi/deecha/shared_scripts/-/blob/master/LICENSE
# #
# # PURPOSE:
# # For a given vector of amino acid changes like A123T, V256F, E746_A750del
# # this function returns c(123, 256, 746) as amino acid positions of
# # the mutated residue.
# # In case of indels, it doesn't return the range!! (returns only the start position)
# #
# #<---------------------------->
dependencies <- c("stringi")
missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
if(length(missing_packages)) install.packages(missing_packages)
MutSiteFind <- function(MutationColumn){
return(unlist(x = stringi::stri_extract_first_regex(str = MutationColumn,pattern = "[[:digit:]]+"), use.names = F))
}

BIN
asset/RefSeqSelect_Gene_Transcript.RDS Normal file
View file

Binary file not shown.

14
unparalogMutations.R
View file

@ -1,6 +1,6 @@
# #<---------------------------->
# # Please include this when distributing and/or using this code.
# # I hope you will read and respect the terms of the included LICENSE
# # Please include this section when distributing and/or using this code.
# # Please read and abide by the terms of the included LICENSE
# #
# # Author : Deepankar Chakroborty (https://gitlab.utu.fi/deecha)
# # Report issues: https://gitlab.utu.fi/deecha/shared_scripts/-/issues
@ -29,12 +29,12 @@
# <--------------->
# Installing missing dependencies
dependencies <- c("stringi", "progress")
missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
if(length(missing_packages)) install.packages(missing_packages)
unparalog <- function(DATA, paralog_separator = ";", annotation_separator = ",", GeneColName , AnnotationColName ){
# Installing missing dependencies
dependencies <- c("stringi", "progress")
missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
if(length(missing_packages)) install.packages(missing_packages)
# Sanity checks
check_paralog_sep <- !any(stringi::stri_detect_fixed(str = DATA$Gene.refGene,pattern = paralog_separator))
check_annotation_sep <- !any(stringi::stri_detect_fixed(str = DATA$AAChange.refGene, pattern = annotation_separator))