Package newly created but working

.Rbuildignore

@@ -0,0 +1,2 @@
+^.*\.Rproj$
+^\.Rproj\.user$

.Rproj.user/503CA0F5/console06/C707850D

@@ -0,0 +1,2 @@
+bash: setenv: command not found
+]0;~/Box Sync/One2One[?1034h130-229-10-198-dhcp:One2One ns9$ 130-229-10-198-dhcp:One2One ns9$ 

.Rproj.user/503CA0F5/console06/INDEX001

@@ -0,0 +1 @@
+[{"allow_restart":true,"alt_buffer":false,"autoclose":0,"buffered_output":"","caption":"Terminal 1","channel_id":"4424","channel_mode":1,"child_procs":false,"cols":233,"cwd":"~/Box Sync/One2One","exit_code":null,"handle":"C707850D","interaction_mode":2,"max_output_lines":1000,"restarted":false,"rows":23,"shell_type":7,"show_on_output":false,"terminal_sequence":1,"title":"~/Box Sync/One2One","track_env":true,"zombie":false}]

.Rproj.user/503CA0F5/cpp-definition-cache

@@ -0,0 +1,2 @@
+[
+]

.Rproj.user/503CA0F5/pcs/files-pane.pper

@@ -0,0 +1,9 @@
+{
+    "path" : "~/Box Sync/One2One",
+    "sortOrder" : [
+        {
+            "ascending" : true,
+            "columnIndex" : 2
+        }
+    ]
+}

.Rproj.user/503CA0F5/pcs/source-pane.pper

@@ -0,0 +1,3 @@
+{
+    "activeTab" : 1
+}

.Rproj.user/503CA0F5/pcs/windowlayoutstate.pper

@@ -0,0 +1,14 @@
+{
+    "left" : {
+        "panelheight" : 1302,
+        "splitterpos" : 442,
+        "topwindowstate" : "NORMAL",
+        "windowheight" : 1340
+    },
+    "right" : {
+        "panelheight" : 1302,
+        "splitterpos" : 804,
+        "topwindowstate" : "NORMAL",
+        "windowheight" : 1340
+    }
+}

.Rproj.user/503CA0F5/pcs/workbench-pane.pper

@@ -0,0 +1,6 @@
+{
+    "TabSet1" : 3,
+    "TabSet2" : 0,
+    "TabZoom" : {
+    }
+}

.Rproj.user/503CA0F5/persistent-state

@@ -0,0 +1,8 @@
+build-last-errors="[]"
+build-last-errors-base-dir="~/Box Sync/One2One/"
+build-last-outputs="[{\"output\":\"==> R CMD INSTALL --no-multiarch --with-keep.source One2One\\n\\n\",\"type\":0},{\"output\":\"\\n\",\"type\":1},{\"output\":\"Attaching package: ‘dplyr’\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"The following objects are masked from ‘package:base’:\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"    intersect, setdiff, setequal, union\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"Attaching package: ‘reshape’\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"The following object is masked from ‘package:dplyr’:\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"    rename\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"\",\"type\":1},{\"output\":\"* installing to library ‘/Users/ns9/Library/R/3.4/library’\\n\",\"type\":1},{\"output\":\"* installing *source* package ‘One2One’ ...\\n\",\"type\":1},{\"output\":\"** R\\n\",\"type\":1},{\"output\":\"** data\\n\",\"type\":1},{\"output\":\"*** moving datasets to lazyload DB\\n\",\"type\":1},{\"output\":\"\",\"type\":1},{\"output\":\"** preparing package for lazy loading\\n\",\"type\":1},{\"output\":\"** help\\n\",\"type\":1},{\"output\":\"*** installing help indices\\n\",\"type\":1},{\"output\":\"\",\"type\":1},{\"output\":\"** building package indices\\n\",\"type\":1},{\"output\":\"** installing vignettes\\n\",\"type\":1},{\"output\":\"** testing if installed package can be loaded\\n\",\"type\":1},{\"output\":\"\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"Attaching package: ‘dplyr’\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"The following objects are masked from ‘package:base’:\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"    intersect, setdiff, setequal, union\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"Attaching package: ‘reshape’\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"The following object is masked from ‘package:dplyr’:\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"    rename\\n\",\"type\":1},{\"output\":\"\\n\",\"type\":1},{\"output\":\"\",\"type\":1},{\"output\":\"* DONE (One2One)\\n\",\"type\":1},{\"output\":\"\",\"type\":1}]"
+compile_pdf_state="{\"errors\":[],\"output\":\"\",\"running\":false,\"tab_visible\":false,\"target_file\":\"\"}"
+files.monitored-path=""
+find-in-files-state="{\"handle\":\"\",\"input\":\"\",\"path\":\"\",\"regex\":false,\"results\":{\"file\":[],\"line\":[],\"lineValue\":[],\"matchOff\":[],\"matchOn\":[]},\"running\":false}"
+imageDirtyState="1"
+saveActionState="-1"

.Rproj.user/503CA0F5/rmd-outputs

@@ -0,0 +1,5 @@
+/var/folders/qk/f3p79d9523j3kjt3qkrcn0k0000csj/T//RtmpDvBPYI/preview-ac89254985f9.html
+/var/folders/qk/f3p79d9523j3kjt3qkrcn0k0000csj/T//RtmpDvBPYI/preview-aca3478a6aa3.html
+/private/var/folders/qk/f3p79d9523j3kjt3qkrcn0k0000csj/T/RtmpDvBPYI/preview-aaaecd300f1.dir/introduction.html
+/private/var/folders/qk/f3p79d9523j3kjt3qkrcn0k0000csj/T/RtmpDvBPYI/preview-aaae70e2d4ca.dir/introduction.html
+/private/var/folders/qk/f3p79d9523j3kjt3qkrcn0k0000csj/T/RtmpDvBPYI/preview-aaae3c0053ac.dir/introduction.html

.Rproj.user/503CA0F5/saved_source_markers

@@ -0,0 +1 @@
+{"active_set":"","sets":[]}

.Rproj.user/503CA0F5/sources/prop/111BEC64

@@ -0,0 +1,2 @@
+{
+}

.Rproj.user/503CA0F5/sources/prop/2CDB7A0E

@@ -0,0 +1,5 @@
+{
+    "cursorPosition" : "0,0",
+    "scrollLine" : "0",
+    "tempName" : "Untitled1"
+}

.Rproj.user/503CA0F5/sources/prop/369E48E6

@@ -0,0 +1,4 @@
+{
+    "cursorPosition" : "17,0",
+    "scrollLine" : "0"
+}

.Rproj.user/503CA0F5/sources/prop/4B5F1197

@@ -0,0 +1,5 @@
+{
+    "cursorPosition" : "7,32",
+    "scrollLine" : "0",
+    "tempName" : "Untitled1"
+}

.Rproj.user/503CA0F5/sources/prop/65C16CFC

@@ -0,0 +1,4 @@
+{
+    "cursorPosition" : "9,84",
+    "scrollLine" : "0"
+}

.Rproj.user/503CA0F5/sources/prop/6677BA5D

@@ -0,0 +1,4 @@
+{
+    "cursorPosition" : "19,0",
+    "scrollLine" : "0"
+}

.Rproj.user/503CA0F5/sources/prop/758A0F0B

@@ -0,0 +1,4 @@
+{
+    "cursorPosition" : "11,0",
+    "scrollLine" : "0"
+}

.Rproj.user/503CA0F5/sources/prop/96B2425D

@@ -0,0 +1,5 @@
+{
+    "cursorPosition" : "16,90",
+    "scrollLine" : "0",
+    "tempName" : "Untitled1"
+}

.Rproj.user/503CA0F5/sources/prop/D0B6B8F6

@@ -0,0 +1,5 @@
+{
+    "cursorPosition" : "0,0",
+    "scrollLine" : "0",
+    "tempName" : "Untitled1"
+}

.Rproj.user/503CA0F5/sources/prop/DF9713E5

@@ -0,0 +1,4 @@
+{
+    "cursorPosition" : "3,22",
+    "scrollLine" : "0"
+}

.Rproj.user/503CA0F5/sources/prop/E5A941A8

@@ -0,0 +1,4 @@
+{
+    "cursorPosition" : "15,0",
+    "scrollLine" : "0"
+}

.Rproj.user/503CA0F5/sources/prop/F05B7023

@@ -0,0 +1,4 @@
+{
+    "cursorPosition" : "201,13",
+    "scrollLine" : "169"
+}

.Rproj.user/503CA0F5/sources/prop/INDEX

@@ -0,0 +1,12 @@
+~%2FBox%20Sync%2FOne2One%2FR%2Fanalyse.orthology.r="D0B6B8F6"
+~%2FBox%20Sync%2FOne2One%2FR%2Fcheck.species.r="2CDB7A0E"
+~%2FBox%20Sync%2FOne2One%2FR%2Fdata.r="65C16CFC"
+~%2FBox%20Sync%2FOne2One%2FR%2Fget.symbol.from.homologID.r="96B2425D"
+~%2FBox%20Sync%2FOne2One%2FR%2Fhello.R="111BEC64"
+~%2FBox%20Sync%2FOne2One%2FR%2Fload.homologs.r="4B5F1197"
+~%2FBox%20Sync%2FOne2One%2FReadme.Rmd="758A0F0B"
+~%2FBox%20Sync%2FOne2One%2Fvignettes%2Fintroduction.Rmd="DF9713E5"
+~%2FDatasets%20that%20are%20too%20large%20to%20store%20elsewhere%2FDisease%20Transcriptomes%2FALS%2FRegenerate_Human_Bootstrap_Plots.r="E5A941A8"
+~%2FDatasets%20that%20are%20too%20large%20to%20store%20elsewhere%2FSOD1%20Spinal%20Cord%20(GSE18597)%2FRegenerating_Bootstrap_Plots.r="6677BA5D"
+~%2FDatasets%20that%20are%20too%20large%20to%20store%20elsewhere%2FSOD1%20Spinal%20Cord%20(GSE18597)%2Fgenerate.bootstrap.plots.for.transcriptome_SOD1.r="F05B7023"
+~%2FGoogle%20Drive%2FDiseaseEnrichment%2Fget.vertebrate.homologs.r="369E48E6"

.Rproj.user/503CA0F5/sources/s-3AD1AF90/25C317CE

@@ -0,0 +1,23 @@
+{
+    "collab_server" : "",
+    "contents" : "",
+    "created" : 1516132633447.000,
+    "dirty" : false,
+    "encoding" : "UTF-8",
+    "folds" : "",
+    "hash" : "0",
+    "id" : "25C317CE",
+    "lastKnownWriteTime" : 1516202508,
+    "last_content_update" : 1516202508625,
+    "path" : "~/Box Sync/One2One/R/analyse.orthology.r",
+    "project_path" : "R/analyse.orthology.r",
+    "properties" : {
+        "cursorPosition" : "0,0",
+        "scrollLine" : "0",
+        "tempName" : "Untitled1"
+    },
+    "relative_order" : 6,
+    "source_on_save" : false,
+    "source_window" : "",
+    "type" : "r_source"
+}

.Rproj.user/503CA0F5/sources/s-3AD1AF90/25C317CE-contents

@@ -0,0 +1,93 @@
+#' Analyse orthology between two species
+#'
+#' Returns a table of 1:1 orthologs along with gene sets (in Homologene ID format) detailing how genes differ between the two species
+#'
+#' @param species1 String with the name of the first species, i.e. "mouse"
+#' @param species2 String with the name of the second species, i.e. "human"
+#' @param allHomologs Output of load.homologs() function
+#'
+#' @return List. The most important thing is orthologs_one2one.
+#'
+#' @examples
+#' ortholog_data = analyse.orthology("human","mouse")
+#'
+#' @export
+analyse.orthology <- function(species1="mouse",species2="human",allHomologs=allHomologs){
+    library(dplyr)
+    library(magrittr)
+    #species1 = "mouse"
+    #species2 = "human"
+
+    species1 = check.species(requestedSpecies=species1,allSpecies=allHomologs$`Common Organism Name`)
+    species2 = check.species(requestedSpecies=species2,allSpecies=allHomologs$`Common Organism Name`)
+
+    species1_srt = gsub(",.*","",species1)
+    species2_srt = gsub(",.*","",species2)
+
+    hom_vert = allHomologs[allHomologs$`Common Organism Name` %in% c(species1,species2),c("HomoloGene ID","Common Organism Name","Symbol")] %>% unique
+    species1_hom  = hom_vert[hom_vert$`Common Organism Name`==species1,] %>% dplyr::rename(species1.symbol=Symbol)
+    species2_hom  = hom_vert[hom_vert$`Common Organism Name`==species2,] %>% dplyr::rename(species2.symbol=Symbol)
+    colnames(species1_hom)[3]=sprintf("%s.symbol",species1_srt)
+    colnames(species2_hom)[3]=sprintf("%s.symbol",species2_srt)
+    allHomologsInSpecies = merge(species1_hom[,c(1,3)],species2_hom[,c(1,3)],by="HomoloGene ID",all=TRUE)
+
+    species1_allGenes = unique(species1_hom$`HomoloGene ID`)
+    species2_allGenes = unique(species2_hom$`HomoloGene ID`)
+    total_numS1genes = length(species1_allGenes)
+    total_numS2genes = length(species2_allGenes)
+    print(sprintf("Full dataset contains %s genes from %s",total_numS1genes,species1_srt))
+    print(sprintf("Full dataset contains %s genes from %s",total_numS2genes,species2_srt))
+
+    # Keep only genes which are expressed in both species
+    shared_genes = intersect(species1_hom$`HomoloGene ID`,species2_hom$`HomoloGene ID`)
+    species1_sharedHom = species1_hom[species1_hom$`HomoloGene ID` %in% shared_genes,]
+    species2_sharedHom = species2_hom[species2_hom$`HomoloGene ID` %in% shared_genes,]
+
+    # Find genes which were deleted in one species
+    species1_present_species2_deleted = setdiff(species1_allGenes,shared_genes)
+    species2_present_species1_deleted = setdiff(species2_allGenes,shared_genes)
+    print(sprintf("%s genes which are present in %s are deleted in %s",length(species1_present_species2_deleted),species1_srt,species2_srt))
+    print(sprintf("%s genes which are present in %s are deleted in %s",length(species2_present_species1_deleted),species2_srt,species1_srt))
+
+    # Get frequency of genes being duplicated
+    species1_freq = data.frame(table(species1_hom$`HomoloGene ID`)) %>% dplyr::rename(HomoloGene.ID=Var1)
+    species2_freq = data.frame(table(species2_hom$`HomoloGene ID`)) %>% dplyr::rename(HomoloGene.ID=Var1)
+    species1_freq = species1_freq[order(species1_freq$Freq,decreasing = TRUE),]
+    species2_freq = species2_freq[order(species2_freq$Freq,decreasing = TRUE),]
+    species1_duplicated_homoloID = as.character(species1_freq[species1_freq$Freq>1,]$HomoloGene.ID)
+    species2_duplicated_homoloID = as.character(species2_freq[species2_freq$Freq>1,]$HomoloGene.ID)
+    print(sprintf("%s genes are duplicated in %s",length(species1_duplicated_homoloID),species1_srt))
+    print(sprintf("%s genes are duplicated in %s",length(species2_duplicated_homoloID),species2_srt))
+
+    # Drop genes that have more than one entry per species
+    species1_onceOnly = species1_freq %>% dplyr::filter(Freq==1) %>% .[,"HomoloGene.ID"] %>% as.character()
+    species2_onceOnly = species2_freq %>% dplyr::filter(Freq==1) %>% .[,"HomoloGene.ID"] %>% as.character()
+    oncePerSpecies = intersect(species1_onceOnly,species2_onceOnly)
+    species1_121 = species1_sharedHom[species1_sharedHom$`HomoloGene ID` %in% oncePerSpecies,]
+    species2_121 = species2_sharedHom[species2_sharedHom$`HomoloGene ID` %in% oncePerSpecies,]
+    colnames(species1_121)[3]=sprintf("%s.symbol",species1_srt)
+    colnames(species2_121)[3]=sprintf("%s.symbol",species2_srt)
+
+    # Which genes are duplicated in one species, but not the other
+    species1_onceOnly_species2_dup = intersect(species1_onceOnly,species2_duplicated_homoloID)
+    species2_onceOnly_species1_dup = intersect(species2_onceOnly,species1_duplicated_homoloID)
+    species2_dup_species1_dup = intersect(species2_duplicated_homoloID,species1_duplicated_homoloID)
+
+    # Get merged listing of 1:1 homologs
+    merged_homologs = merge(species1_121[,c(1,3)],species2_121[,c(1,3)],by="HomoloGene ID")
+    print(sprintf("%s are shared 1:1 between the two species",dim(merged_homologs)[1]))
+
+    # Prepare results
+    allRes = list()
+    allRes$orthologs_all     = allHomologsInSpecies
+    allRes$orthologs_one2one = merged_homologs
+    allRes$species1_allGenes = species1_allGenes
+    allRes$species2_allGenes = species2_allGenes
+    allRes$shared_genes      = shared_genes
+    allRes$species1_present_species2_deleted = species1_present_species2_deleted
+    allRes$species2_present_species1_deleted = species2_present_species1_deleted
+    allRes$species1_onceOnly_species2_dup    = species1_onceOnly_species2_dup
+    allRes$species2_onceOnly_species1_dup    = species2_onceOnly_species1_dup
+    allRes$species2_dup_species1_dup         = species2_dup_species1_dup
+    return(allRes)
+}

.Rproj.user/503CA0F5/sources/s-3AD1AF90/39BAB851

@@ -0,0 +1,23 @@
+{
+    "collab_server" : "",
+    "contents" : "",
+    "created" : 1516203298776.000,
+    "dirty" : false,
+    "encoding" : "UTF-8",
+    "folds" : "",
+    "hash" : "0",
+    "id" : "39BAB851",
+    "lastKnownWriteTime" : 1516203522,
+    "last_content_update" : 1516203522633,
+    "path" : "~/Box Sync/One2One/R/get.symbol.from.homologID.r",
+    "project_path" : "R/get.symbol.from.homologID.r",
+    "properties" : {
+        "cursorPosition" : "16,90",
+        "scrollLine" : "0",
+        "tempName" : "Untitled1"
+    },
+    "relative_order" : 8,
+    "source_on_save" : false,
+    "source_window" : "",
+    "type" : "r_source"
+}

.Rproj.user/503CA0F5/sources/s-3AD1AF90/39BAB851-contents

@@ -0,0 +1,27 @@
+#' Get gene symbol from homologID
+#'
+#' Most outputs of this package are in the format of homolog IDs. To be useful they need to be converted to gene symbols. This functon does that.
+#'
+#' @param homoIDs The list of homolog IDs to be converted to gene symbols
+#' @param species1 String with the name of the first species, i.e. "mouse"
+#' @param species2 String with the name of the second species, i.e. "human"
+#' @param ortholog_data Output of analyse.orthology() function
+#' @param symbol_species The name of the species for which gene symbols should be returned. I.e. "mouse"
+#'
+#' @return List. The gene symbols equivilenet to homolog IDs in homoIDs
+#'
+#' @examples
+#' allHomologs = load.homologs()
+#' ortholog_data = analyse.orthology("human","mouse",allHomologs)
+#' homoIDs_bg     = ortholog_data$species2_allGenes
+#' symbols_bg = get.symbol.from.homologID(homoIDs_bg,"human","mouse",ortholog_data,"mouse")
+#'
+#' @export
+get.symbol.from.homologID <- function(homoIDs,species1,species2,ortholog_data,symbol_species){
+    # Which species do the symbols need to be returned from? I.e. MGI or HGNC symbols?
+    whichSpecies = which(c(species1,species2)==symbol_species)+1
+    if(length(whichSpecies)==0){stop("ERROR: symbol_species must be the same as either species1 or species2")}
+    # These are the gene symbols:
+    symbols = ortholog_data$orthologs_all[ortholog_data$orthologs_all$`HomoloGene ID` %in% homoIDs,whichSpecies]
+    return(unique(symbols))
+}