fix for obo files

R/ermineR.R

@@ -47,7 +47,7 @@ ermineR = function(annotation = NULL,
     geneReplicates = match.arg(geneReplicates)
     stats = match.arg(stats)
     # set ermineJ home so users won't have to
-    ermineJHome = system.file("ermineJ-3.1.2",package = 'ermineR')
+    ermineJHome = system.file("ermineJ-3.2",package = 'ermineR')
     Sys.setenv(ERMINEJ_HOME = ermineJHome)
 
     # find that java home at all costs
@@ -95,21 +95,22 @@ ermineR = function(annotation = NULL,
 
     # get gene set descriptions -------------
     if(is.null(geneSetDescription) | nullAnnot){
-        geneSetDescription = system.file('go-minimal.xml',package = 'ermineR') 
+        geneSetDescription = system.file('go-minimal.obo',package = 'ermineR') 
     } else if(geneSetDescription == 'Latest_GO'){
-        temp = tempfile(fileext = '.xml')
+        temp = tempfile()
         goToday(temp)
         geneSetDescription = temp
     }else if(!file.exists(geneSetDescription)){
         message('Attempting to download gene set description from link')
-        temp = tempfile(fileext = 'xml.gz')
+        temp = tempfile()
         download.file(url = geneSetDescription,destfile = temp,quiet= TRUE)
         geneSetDescription = temp
     } # and else, geneSetDescription is a local file
 
     assertthat::is.string(geneSetDescription) # geneSetDescription is mandatory
     arguments$geneSetDescription = paste('--classFile',shQuote(geneSetDescription))
 
+
     # get scores and score columns-------------
     if(test %in% c('ORA','GSR','ROC')){
         # get hitlist if provided instead of scores
@@ -335,7 +336,7 @@ ermineR = function(annotation = NULL,
     #     warning('Something went wrong and I have no idea what. Returning response')
     #     return(response)
     # }
-    
+
     if(return){
         out = readErmineJOutput(output)
         out$details$call = call

R/ontology.R

@@ -3,17 +3,16 @@
 #' 
 #' Downloads latest gene ontology term information (not gene annotations)
 #'
-#' @param path File path. Without gz extension
+#' @param path File path
 #' @param overwrite If TRUE, overwrites existing file
 #'
 #' @export
 goToday = function(path,overwrite = FALSE){
     if(exists(path) & !overwrite){
         stop('File exists, not downloading')
     }
-    utils::download.file('http://archive.geneontology.org/latest-termdb/go_daily-termdb.rdf-xml.gz',
-                         destfile = paste0(path,'.gz'),quiet= TRUE)
-    R.utils::gunzip(paste0(path,'.gz'),overwrite = overwrite)    
+    utils::download.file('http://purl.obolibrary.org/obo/go.obo',
+                         destfile = paste0(path),quiet= TRUE)
 }
 
 #' getGoDates
@@ -26,6 +25,8 @@ getGoDates = function(){
     files = 
         RCurl::getURL('ftp://ftp.geneontology.org/pub/go/godatabase/archive/termdb/',dirlistonly = TRUE,ftp.use.epsv=TRUE)
 
+    files = RCurl::getURL('http://release.geneontology.org/')
+
     # dates = files %>% strsplit('a href') %>% {.[[1]]} %>% {.[grepl(x = .,pattern = '[0-9]+?-[0-9]+?-[0-9]+(?=/)',perl = TRUE)]} %>% 
     #     stringr::str_extract( '[0-9]+?-[0-9]+?-[0-9]+(?=/)')
     files %<>% strsplit('\n') %>% {.[[1]]} %>% {.[grepl(pattern = '[0-9]+?-[0-9]+?-[0-9]+', .)]}

inst/ermineJ-3.1.2/bin/ermineJ.bat → inst/ermineJ-3.2/bin/ermineJ.bat

@@ -1,120 +1,120 @@
-@echo off
-@REM enable echoing my setting ERMINEJ_BATCH_ECHO to 'on'
-@if "%ERMINEJ_BATCH_ECHO%" == "on"  echo %ERMINEJ_BATCH_ECHO%
-
-echo Starting ErmineJ ...
-
-@REM Execute a user defined script before this one
-if exist "%HOME%\ermineJrc_pre.bat" call "%HOME%\ermineJrc_pre.bat"
-
-@REM set local scope for the variables with windows NT shell
-if "%OS%"=="Windows_NT" @setlocal
-
-@REM ==== START VALIDATION ====
-if not "%JAVA_HOME%" == "" goto OkJHome
-
-echo.
-echo ERROR: JAVA_HOME not found in your environment.
-echo Please set the JAVA_HOME variable in your environment to match the
-echo location of your Java installation
-echo.
-goto end
-
-:OkJHome
-if exist "%JAVA_HOME%" goto chkMHome
-
-echo.
-echo ERROR: JAVA_HOME is set to an invalid directory.
-echo JAVA_HOME = %JAVA_HOME%
-echo Please set the JAVA_HOME variable in your environment to match the
-echo location of your Java installation
-echo.
-goto end
-
-:chkMHome
-if not "%ERMINEJ_HOME%" == "" goto valMHome
-
-echo.
-echo ERROR: ERMINEJ_HOME not found in your environment.
-echo Please set the ERMINEJ_HOME variable in your environment to match the
-echo location of the ermineJ installation
-echo.
-goto end
-
-:valMHome
-if exist "%ERMINEJ_HOME%\bin\ermineJ.bat" goto init
-
-echo.
-echo ERROR: ERMINEJ_HOME is set to an invalid directory or does not contain the bin\ermineJ.bat script
-echo ERMINEJ_HOME = %ERMINEJ_HOME%
-echo Please set the ERMINEJ_HOME variable in your environment to match the
-echo location of the ermineJ installation
-echo.
-goto end
-@REM ==== END VALIDATION ====
-
-:init
-@REM Decide how to startup depending on the version of windows
-
-@REM -- 4NT shell
-if "%eval[2+2]" == "4" goto 4NTArgs
-
-@REM -- Regular WinNT shell
-set ERMINEJ_CMD_LINE_ARGS=%*
-goto endInit
-
-@REM The 4NT Shell from jp software
-:4NTArgs
-set ERMINEJ_CMD_LINE_ARGS=%$
-goto endInit
-
-@REM Reaching here means variables are defined and arguments have been captured
-:endInit
-if "%ERMINEJ_OPTS%"=="" SET ERMINEJ_OPTS="-Xmx3g"
-SET ERMINEJ_JAVA_EXE="%JAVA_HOME%\bin\java.exe"
-
-if exist %ERMINEJ_JAVA_EXE%  goto run
-echo.
-echo ERROR: ERMINEJ_JAVA_EXE is set to an invalid path.
-echo ERMINEJ_JAVA_EXE = %ERMINEJ_JAVA_EXE%
-echo Please set the JAVA_HOME variable in your environment to match the
-echo location of the java installation
-echo.
-goto end
-
-:run
-SET ERMINEJ_CLASSPATH="%ERMINEJ_HOME%\lib\forehead.jar"
-SET ERMINEJ_MAIN_CLASS="com.werken.forehead.Forehead"
-SET ERMINEJ_ENDORSED="%JAVA_HOME%\lib\endorsed;%ERMINEJ_HOME%\lib"
-if not "%ERMINEJ_HOME_LOCAL%" == "" goto StartMHL
-
-@REM Start ERMINEJ without ERMINEJ_HOME_LOCAL override
-%ERMINEJ_JAVA_EXE% -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
-@REM %ERMINEJ_JAVA_EXE% -Dorg.xml.sax.driver=org.apache.xerces.parsers.SAXParser -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
-goto :end
-
-@REM Start ERMINEJ with ERMINEJ_HOME_LOCAL override
-:StartMHL
-%ERMINEJ_JAVA_EXE% -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-DermineJ.home.local=%ERMINEJ_HOME_LOCAL%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
-@REM %ERMINEJ_JAVA_EXE% -Dorg.xml.sax.driver=org.apache.xerces.parsers.SAXParser -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-DermineJ.home.local=%ERMINEJ_HOME_LOCAL%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
-
-:end
-@REM set local scope for the variables with windows NT shell
-if "%OS%"=="Windows_NT" goto endNT
-
-@REM For old DOS remove the set variables from ENV - we assume they were not set
-@REM before we started - at least we don't leave any baggage around
-set ERMINEJ_JAVA_EXE=
-set ERMINEJ_CLASSPATH=
-set ERMINEJ_MAIN_CLASS=
-set ERMINEJ_CMD_LINE_ARGS=
-goto postExec
-
-:endNT
-@endlocal
-
-:postExec
-@REM if exist "%HOME%\ermineJrc_post.bat" call "%HOME%\ermineJrc_post.bat"
-@REM pause the batch file if ERMINEJ_BATCH_PAUSE is set to 'on'
-@REM if "%ERMINEJ_BATCH_PAUSE%" == "on" pause
-
+@echo off
+@REM enable echoing my setting ERMINEJ_BATCH_ECHO to 'on'
+@if "%ERMINEJ_BATCH_ECHO%" == "on"  echo %ERMINEJ_BATCH_ECHO%
+
+echo Starting ErmineJ ...
+
+@REM Execute a user defined script before this one
+if exist "%HOME%\ermineJrc_pre.bat" call "%HOME%\ermineJrc_pre.bat"
+
+@REM set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" @setlocal
+
+@REM ==== START VALIDATION ====
+if not "%JAVA_HOME%" == "" goto OkJHome
+
+echo.
+echo ERROR: JAVA_HOME not found in your environment.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation
+echo.
+goto end
+
+:OkJHome
+if exist "%JAVA_HOME%" goto chkMHome
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory.
+echo JAVA_HOME = %JAVA_HOME%
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation
+echo.
+goto end
+
+:chkMHome
+if not "%ERMINEJ_HOME%" == "" goto valMHome
+
+echo.
+echo ERROR: ERMINEJ_HOME not found in your environment.
+echo Please set the ERMINEJ_HOME variable in your environment to match the
+echo location of the ermineJ installation
+echo.
+goto end
+
+:valMHome
+if exist "%ERMINEJ_HOME%\bin\ermineJ.bat" goto init
+
+echo.
+echo ERROR: ERMINEJ_HOME is set to an invalid directory or does not contain the bin\ermineJ.bat script
+echo ERMINEJ_HOME = %ERMINEJ_HOME%
+echo Please set the ERMINEJ_HOME variable in your environment to match the
+echo location of the ermineJ installation
+echo.
+goto end
+@REM ==== END VALIDATION ====
+
+:init
+@REM Decide how to startup depending on the version of windows
+
+@REM -- 4NT shell
+if "%eval[2+2]" == "4" goto 4NTArgs
+
+@REM -- Regular WinNT shell
+set ERMINEJ_CMD_LINE_ARGS=%*
+goto endInit
+
+@REM The 4NT Shell from jp software
+:4NTArgs
+set ERMINEJ_CMD_LINE_ARGS=%$
+goto endInit
+
+@REM Reaching here means variables are defined and arguments have been captured
+:endInit
+if "%ERMINEJ_OPTS%"=="" SET ERMINEJ_OPTS="-Xmx3g"
+SET ERMINEJ_JAVA_EXE="%JAVA_HOME%\bin\java.exe"
+
+if exist %ERMINEJ_JAVA_EXE%  goto run
+echo.
+echo ERROR: ERMINEJ_JAVA_EXE is set to an invalid path.
+echo ERMINEJ_JAVA_EXE = %ERMINEJ_JAVA_EXE%
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of the java installation
+echo.
+goto end
+
+:run
+SET ERMINEJ_CLASSPATH="%ERMINEJ_HOME%\lib\forehead.jar"
+SET ERMINEJ_MAIN_CLASS="com.werken.forehead.Forehead"
+SET ERMINEJ_ENDORSED="%JAVA_HOME%\lib\endorsed;%ERMINEJ_HOME%\lib"
+if not "%ERMINEJ_HOME_LOCAL%" == "" goto StartMHL
+
+@REM Start ERMINEJ without ERMINEJ_HOME_LOCAL override
+%ERMINEJ_JAVA_EXE% -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
+@REM %ERMINEJ_JAVA_EXE% -Dorg.xml.sax.driver=org.apache.xerces.parsers.SAXParser -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
+goto :end
+
+@REM Start ERMINEJ with ERMINEJ_HOME_LOCAL override
+:StartMHL
+%ERMINEJ_JAVA_EXE% -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-DermineJ.home.local=%ERMINEJ_HOME_LOCAL%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
+@REM %ERMINEJ_JAVA_EXE% -Dorg.xml.sax.driver=org.apache.xerces.parsers.SAXParser -Djavax.xml.parsers.SAXParserFactory=org.apache.xerces.jaxp.SAXParserFactoryImpl -Djavax.xml.parsers.DocumentBuilderFactory=org.apache.xerces.jaxp.DocumentBuilderFactoryImpl "-DermineJ.home=%ERMINEJ_HOME%" "-DermineJ.home.local=%ERMINEJ_HOME_LOCAL%" "-Dtools.jar=%JAVA_HOME%\lib\tools.jar" "-Dforehead.conf.file=%ERMINEJ_HOME%\bin\forehead.conf" -Djava.endorsed.dirs=%ERMINEJ_ENDORSED% %ERMINEJ_OPTS% -classpath %ERMINEJ_CLASSPATH% %ERMINEJ_MAIN_CLASS% %ERMINEJ_CMD_LINE_ARGS%
+
+:end
+@REM set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" goto endNT
+
+@REM For old DOS remove the set variables from ENV - we assume they were not set
+@REM before we started - at least we don't leave any baggage around
+set ERMINEJ_JAVA_EXE=
+set ERMINEJ_CLASSPATH=
+set ERMINEJ_MAIN_CLASS=
+set ERMINEJ_CMD_LINE_ARGS=
+goto postExec
+
+:endNT
+@endlocal
+
+:postExec
+@REM if exist "%HOME%\ermineJrc_post.bat" call "%HOME%\ermineJrc_post.bat"
+@REM pause the batch file if ERMINEJ_BATCH_PAUSE is set to 'on'
+@REM if "%ERMINEJ_BATCH_PAUSE%" == "on" pause
+

inst/go-minimal.obo

@@ -0,0 +1,65 @@
+format-version: 1.2
+data-version: releases/2021-02-01
+subsetdef: chebi_ph7_3 "Rhea list of ChEBI terms representing the major species at pH 7.3."
+subsetdef: gocheck_do_not_annotate "Term not to be used for direct annotation"
+subsetdef: gocheck_do_not_manually_annotate "Term not to be used for direct manual annotation"
+subsetdef: goslim_agr "AGR slim"
+subsetdef: goslim_aspergillus "Aspergillus GO slim"
+subsetdef: goslim_candida "Candida GO slim"
+subsetdef: goslim_chembl "ChEMBL protein targets summary"
+subsetdef: goslim_drosophila "Drosophila GO slim"
+subsetdef: goslim_flybase_ribbon "FlyBase Drosophila GO ribbon slim"
+subsetdef: goslim_generic "Generic GO slim"
+subsetdef: goslim_metagenomics "Metagenomics GO slim"
+subsetdef: goslim_mouse "Mouse GO slim"
+subsetdef: goslim_pir "PIR GO slim"
+subsetdef: goslim_plant "Plant GO slim"
+subsetdef: goslim_pombe "Fission yeast GO slim"
+subsetdef: goslim_synapse "synapse GO slim"
+subsetdef: goslim_yeast "Yeast GO slim"
+synonymtypedef: syngo_official_label "label approved by the SynGO project"
+synonymtypedef: systematic_synonym "Systematic synonym" EXACT
+default-namespace: gene_ontology
+ontology: go
+property_value: http://purl.org/dc/elements/1.1/description "The Gene Ontology (GO) provides a framework and set of concepts for describing the functions of gene products from all organisms." xsd:string
+property_value: http://purl.org/dc/elements/1.1/title "Gene Ontology" xsd:string
+property_value: http://purl.org/dc/terms/license http://creativecommons.org/licenses/by/4.0/
+property_value: owl:versionInfo "2021-02-01" xsd:string
+
+[Term]
+id: GO:0003674
+name: molecular_function
+namespace: molecular_function
+alt_id: GO:0005554
+def: "A molecular process that can be carried out by the action of a single macromolecular machine, usually via direct physical interactions with other molecular entities. Function in this sense denotes an action, or activity, that a gene product (or a complex) performs. These actions are described from two distinct but related perspectives: (1) biochemical activity, and (2) role as a component in a larger system/process." [GOC:pdt]
+comment: Note that, in addition to forming the root of the molecular function ontology, this term is recommended for use for the annotation of gene products whose molecular function is unknown. When this term is used for annotation, it indicates that no information was available about the molecular function of the gene product annotated as of the date the annotation was made; the evidence code 'no data' (ND), is used to indicate this. Despite its name, this is not a type of 'function' in the sense typically defined by upper ontologies such as Basic Formal Ontology (BFO). It is instead a BFO:process carried out by a single gene product or complex.
+subset: goslim_aspergillus
+subset: goslim_candida
+subset: goslim_chembl
+subset: goslim_generic
+subset: goslim_metagenomics
+subset: goslim_pir
+subset: goslim_plant
+subset: goslim_yeast
+synonym: "molecular function" EXACT []
+
+[Term]
+id: GO:1
+name: one
+namespace: molecular_function
+def: "The maintenance of the structure and integrity of the mitochondrial genome; includes replication and segregation of the mitochondrial chromosome." [GOC:ai, GOC:vw]
+
+[Term]
+id: GO:2
+name: two
+namespace: molecular_function
+
+[Term]
+id: GO:11
+name: eleven
+namespace: molecular_function
+
+[Term]
+id: GO:31
+name: thirtyone
+namespace: molecular_function