diff --git a/IsolateCanonicalVariant.R b/IsolateCanonicalVariant.R
index 328699dcbec9bce019a806f800f1ec746d9f38ef..8813f2ec8c3835ee51f6d8cf8129c673179bbdd2 100644
--- a/IsolateCanonicalVariant.R
+++ b/IsolateCanonicalVariant.R
@@ -1,33 +1,35 @@
+# Installing dependencies
+dependencies <- c("stringi", "doParallel")
+missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
+if(length(missing_packages)) install.packages(missing_packages)
+rm(missing_packages,dependencies)
+
+IsolateCanonicalVariant <- function (AAchangeAnnotations){
# #<---------------------------->
-# # Please include this section when distributing and/or using this code.
-# # Please read and abide by the terms of the included LICENSE
+# # You must include this section when:
+# # Distributing, Using and/or Modifying this code.
+# # Please read and abide by the terms of the included LICENSE.
+# # Copyright 2020, Deepankar Chakroborty, All rights reserved.
# #
# # 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:
# # From a given vector of annotations for a particular DNA change
# # this function selects the canonical variant (if present)
# # by cross referencing the MANE Select and RefSeq Select sets.
-# #
-# # Logic flow:
+
+# # LOGIC FLOW:
# # - If there is only one annotation; that is selected
# # - If canonical transcript is not found in MANE Select + RefSeq select
# # or a matching transcript ID is not found in the annotation then;
# # The mutation with to the the highest position (residue number) is selected.
# # - If a match for canonical isoform is found then;
# # that particular mutation is selected
-# #
-# #<---------------------------->
-
-# Installing dependencies
-dependencies <- c("stringi", "doParallel")
-missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
-if(length(missing_packages)) install.packages(missing_packages)
-rm(missing_packages,dependencies)
-
-IsolateCanonicalVariant <- function (AAchangeAnnotations){
+
# importing resources
library(doParallel)
refseq <- readRDS(url("https://gitlab.utu.fi/deecha/shared_scripts/-/raw/master/asset/RefSeqSelect_Gene_Transcript.RDS"),"rb")
diff --git a/MutSiteFind.R b/MutSiteFind.R
index 709b666c8a28a7562383642b166d2fa125a7016c..70ccda65f2c48e5b0ec60b4a2d52871e21e89372 100644
--- a/MutSiteFind.R
+++ b/MutSiteFind.R
@@ -1,25 +1,30 @@
+# Installing missing dependencies
+dependencies <- c("stringi")
+missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
+if(length(missing_packages)) install.packages(missing_packages)
+rm(missing_packages,dependencies)
+
+MutSiteFind <- function(MutationColumn){
# #<---------------------------->
-# # Please include this section when distributing and/or using this code.
-# # Please read and abide by the terms of the included LICENSE
+# # You must include this section when:
+# # Distributing, Using and/or Modifying this code.
+# # Please read and abide by the terms of the included LICENSE.
+# # Copyright 2020, Deepankar Chakroborty, All rights reserved.
# #
# # 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)
-# #
-# #<---------------------------->
+# # In case of indels, it doesn't return the range!!
+# # (i.e. returns only the start position)
-dependencies <- c("stringi")
-missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
-if(length(missing_packages)) install.packages(missing_packages)
-rm(missing_packages,dependencies)
-MutSiteFind <- function(MutationColumn){
return(unlist(x = stringi::stri_extract_first_regex(str = MutationColumn,pattern = "[[:digit:]]+"), use.names = F))
}
diff --git a/ggplotBreaks.R b/ggplotBreaks.R
index bbac9fce99ee4171f982abc0a69b5f50f8e9806c..48121acd46498838980ca0000b3e1b07d7eb705e 100644
--- a/ggplotBreaks.R
+++ b/ggplotBreaks.R
@@ -1,11 +1,16 @@
+ggplotBreaks <- function(range,tick,skip.steps=0){
# #<---------------------------->
-# # Please include this section when distributing and/or using this code.
-# # Please read and abide by the terms of the included LICENSE
+# # You must include this section when:
+# # Distributing, Using and/or Modifying this code.
+# # Please read and abide by the terms of the included LICENSE.
+# # Copyright 2020, Deepankar Chakroborty, All rights reserved.
# #
# # 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:
# # Returns a list of vectors containing breaks and labels
# # for a continuous variable mapped to one of the axes for use with ggplot2
@@ -20,12 +25,8 @@
# # 0 10 20 30 40 50 60 70 80 90 100 110 120 130 140 150
# #
# # $labels
-# # "0" " " "20" " " "40" " " "60" " " "80" " " "100" " "
-# # "120" " " "140" " "
-# #
-# #<---------------------------->
+# # "0" " " "20" " " "40" " " "60" " " "80" " " "100" " " "120" " " "140" " "
-ggplotBreaks <- function(range,tick,skip.steps=0){
if (length(range) != 2){
stop("Correct format for: range = c(min_value,max_value)")
}
diff --git a/unparalogMutations.R b/unparalogMutations.R
index d4795631c720724c956494e6be60d9adc5abb305..ddf3ff588b21dacb4ff7dc58713e11ada0c44339 100644
--- a/unparalogMutations.R
+++ b/unparalogMutations.R
@@ -1,20 +1,30 @@
+# Installing missing dependencies
+dependencies <- c("stringi", "progress")
+missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
+if(length(missing_packages)) install.packages(missing_packages)
+rm(missing_packages,dependencies)
+
+unparalog <- function(DATA, paralog_separator = ";", annotation_separator = ",", GeneColName , AnnotationColName ){
# #<---------------------------->
-# # Please include this section when distributing and/or using this code.
-# # Please read and abide by the terms of the included LICENSE
+# # You must include this section when:
+# # Distributing, Using and/or Modifying this code.
+# # Please read and abide by the terms of the included LICENSE.
+# # Copyright 2020, Deepankar Chakroborty, All rights reserved.
# #
# # 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:
# # In the gene column in your SNV annotation if you see something like:
# # e.g. PRAMEF7;PRAMEF8 OR PRAMEF7,PRAMEF8
# # then your mutations annotations have gene paralogs.
# # This script aims to de-couple those paralogs into individual their rows.
# #
-# ------------------------
-
-### Info on what to pass as the function parameters:
+
+# # INFO on what to pass as the function parameters:
# Assign correct paralog_separator found in the gene column of your SNV annotations # e.g. if the Gene column has entries like PRAMEF7;PRAMEF8
# then the paralog_separator is ";"
# or set it to whatever separator is used by your SNV annotation software.
@@ -28,14 +38,7 @@
# AnnotationColName = Column name in the SNV annotation table where the Amino acid changes are listed
# <--------------->
-
-# Installing missing dependencies
-dependencies <- c("stringi", "progress")
-missing_packages <- dependencies[!(dependencies %in% installed.packages()[, "Package"])]
-if(length(missing_packages)) install.packages(missing_packages)
-rm(missing_packages,dependencies)
-
-unparalog <- function(DATA, paralog_separator = ";", annotation_separator = ",", GeneColName , AnnotationColName ){
+
# 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))