From 8f44640c52ccd1503fb3888a892a50c12e55ea31 Mon Sep 17 00:00:00 2001
From: dchakro <35454738+dchakro@users.noreply.github.com>
Date: Wed, 16 Dec 2020 19:45:17 +0200
Subject: [PATCH] Annovar functions

---
 Annovar/AnnovarMutCodeFind.R | 50 ++++++++++++++++++++++++++++++++++++
 Annovar/Annovar_cDNA_Find.R  | 48 ++++++++++++++++++++++++++++++++++
 2 files changed, 98 insertions(+)
 create mode 100644 Annovar/AnnovarMutCodeFind.R
 create mode 100644 Annovar/Annovar_cDNA_Find.R

diff --git a/Annovar/AnnovarMutCodeFind.R b/Annovar/AnnovarMutCodeFind.R
new file mode 100644
index 0000000..4ea1e29
--- /dev/null
+++ b/Annovar/AnnovarMutCodeFind.R
@@ -0,0 +1,50 @@
+annovarMutCodeFind=function(MutationColumn,isoform){
+# #<---------------------------->
+# # 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://github.com/dchakro)
+# #  Website: https://www.dchakro.com
+# #  Report issues: https://github.com/dchakro/shared_Rscripts/issues
+# #  License: https://github.com/dchakro/shared_Rscripts/blob/master/LICENSE
+# #<---------------------------->
+
+# # PURPOSE:
+# # This function takes a mutation info column from ANNOVAR output 
+# # and selects the protein change based on the isoform provided.
+# # More about annovar: https://en.wikipedia.org/wiki/ANNOVAR
+
+# # INPUT:
+# # MutationColumn = Mutation column from ANNOVAR output 
+# #                  (usually called: "AAChange.refGene")
+# # isoform = the GenBank Identifier, you can find it from the the ANNOVAR mutation info column.
+# # Default Isoform codes:
+# # EGFR  = NM_005228
+# # ERBB2 = NM_004448
+# # ERBB3 = NM_001982
+# # ERBB4 (Jm-A, Cyt-1) =  NM_005235
+# # ERBB4 (Jm-A, Cyt-2) =  NM_001042599
+
+# # Example usage:
+# # annovarMutCodeFind(MutationColumn = yourData$AAChange.refGene,
+# #  isoform = "NM_005228")
+
+  MutationList=c("List of mutations")
+  for(i in seq(1:length(MutationColumn))){
+    MutInfo=MutationColumn[i]
+    l=sort(unique(unlist(strsplit(MutInfo,","))))
+    l2=l[grep(isoform,l)]
+    l2.s=unique(unlist(strsplit(l2,":")))
+    l3=l2.s[grep("^p",l2.s)]
+    l3=gsub("p.","",l3)
+    l3=gsub("X","*",l3)
+    MUTATION=l3
+    if(length(MUTATION)==0) MUTATION=" "
+    MutationList=c(MutationList,MUTATION)
+  }
+  return(MutationList[-1])
+}
+
+annovarMutCodeFind(MutationColumn = Mutation.Table$AAChange.refGene,isoform = "NM_001982")
diff --git a/Annovar/Annovar_cDNA_Find.R b/Annovar/Annovar_cDNA_Find.R
new file mode 100644
index 0000000..064cf60
--- /dev/null
+++ b/Annovar/Annovar_cDNA_Find.R
@@ -0,0 +1,48 @@
+annovar_cDNA_Find=function(MutationColumn,isoform){
+# #<---------------------------->
+# # 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://github.com/dchakro)
+# #  Website: https://www.dchakro.com
+# #  Report issues: https://github.com/dchakro/shared_Rscripts/issues
+# #  License: https://github.com/dchakro/shared_Rscripts/blob/master/LICENSE
+# #<---------------------------->
+
+# # PURPOSE:
+# # This function takes a mutation info column from ANNOVAR output 
+# # and selects the cDNA change based on the isoform provided.
+# # More about annovar: https://en.wikipedia.org/wiki/ANNOVAR
+
+# # INPUT:
+# # MutationColumn = Mutation column from ANNOVAR output 
+# #                  (usually called: "AAChange.refGene")
+# # isoform = the GenBank Identifier, you can find it from the the ANNOVAR mutation info column.
+# # Default Isoform codes:
+# # EGFR  = NM_005228
+# # ERBB2 = NM_004448
+# # ERBB3 = NM_001982
+# # ERBB4 (Jm-A, Cyt-1) =  NM_005235
+# # ERBB4 (Jm-A, Cyt-2) =  NM_001042599
+
+# # Example usage:
+# # annovar_cDNA_Find(MutationColumn = yourData$AAChange.refGene,
+# #  isoform = "NM_005228")
+  MutationList=c("List of mutations")
+  for(i in seq(1:length(MutationColumn))){
+    MutInfo=MutationColumn[i]
+    l=sort(unique(unlist(strsplit(MutInfo,","))))
+    l2=l[grep(isoform,l)]
+    l2.s=unique(unlist(strsplit(l2,":")))
+    l3=l2.s[grep("^c",l2.s)]
+    l3=gsub("c.","",l3)
+    #l3=gsub("X","*",l3)
+    MUTATION=l3
+    if(length(MUTATION)==0) MUTATION=" "
+    MutationList=c(MutationList,MUTATION)
+  }
+  return(MutationList[-1])
+}
+