Devel_1_1_1 (#6)

grlloyd · web-flow · commit 552898cc5100 · 2021-02-23T10:55:17.000Z
* fix for #4 ensure imported data is numeric * add helper functions * add structToolbox vignette * add HDF5Array to suggests for MultiAssayExperiment * add some output items to study context * update vignettes
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -6,3 +6,4 @@
 ^doc$
 ^Meta$
 ^data-raw$
+^\.github$
diff --git a/.github/workflows/check-bioc.yml b/.github/workflows/check-bioc.yml
@@ -38,7 +38,7 @@ env:
   run_covr: 'true'
   run_pkgdown: 'false'
   has_RUnit: 'false'
-  cache-version: 'cache-v1'
+  cache-version: 'cache-v2'
 
 jobs:
   build-check:
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -27,6 +27,7 @@ Collate:
     'generics.R'
     'class_def.R'
     'constants.R'
+    'helper_fcns.R'
     'metabolomicsWorkbenchR.R'
 Imports: 
     data.table,
@@ -41,8 +42,13 @@ Suggests:
     BiocStyle,
     covr,
     knitr,
+    HDF5Array,
     rmarkdown,
-    testthat
+    structToolbox,
+    testthat,
+    pmp,
+    grid,
+    png
 VignetteBuilder: 
     knitr
 biocViews: Software, Metabolomics
diff --git a/NAMESPACE b/NAMESPACE
@@ -3,7 +3,10 @@
 export(check_pattern)
 export(check_puts)
 export(context)
+export(context_inputs)
+export(context_outputs)
 export(do_query)
+export(input_example)
 export(input_item)
 export(is_valid)
 export(output_item)
diff --git a/R/class_def.R b/R/class_def.R
@@ -93,7 +93,6 @@ setMethod(f = 'show',
     }
 )
 
-
 #' @rdname is_valid
 #' @export
 setMethod(f = 'is_valid',
@@ -880,24 +879,21 @@ setMethod(f = 'do_query',
         df = do_query(context$name,input_item$name,input_value,'untarg_data')
         fq = do_query('study','analysis_id',input_value,'untarg_factors')
         
-        X=as.data.frame(t(df))
-        
-        nf=ncol(fq)-1
-        
-        SM=as.data.frame(t(X[seq_len(nf),]))
-        X=X[nf+seq_len(nrow(X)),]
-        
-        VM=data.frame(feature_id=rownames(X))
+        fq=fq[,-1]
+
+        SM=as.data.frame(df[,colnames(fq)])
+        df[,colnames(fq)]=NULL
         
-        rownames(X)=seq_len(nrow(X))
+        df=as.data.frame(t(df))
+        VM=data.frame(feature_id=rownames(df))
         
         M = list(
             'data_source' = 'Metabolomics Workbench (untargeted)',
             'analysis_id' = input_value
         )
         
         SE = SummarizedExperiment(
-            assays = X,
+            assays = df,
             rowData = VM,
             colData = SM,
             metadata = M
diff --git a/R/constants.R b/R/constants.R
@@ -57,7 +57,8 @@ context$study = mw_context(
     output_items = c('summary','factors','analysis','metabolites','mwtab',
         'source','species','disease','number_of_metabolites','data','datatable',
         'untarg_studies','untarg_factors','untarg_data','metabolite_info',
-        'SummarizedExperiment')
+        'SummarizedExperiment','untarg_SummarizedExperiment','DatasetExperiment',
+        'untarg_DatasetExperiment')
 )
 
 context$compound = mw_context(
diff --git a/R/helper_fcns.R b/R/helper_fcns.R
@@ -0,0 +1,83 @@
+#' Valid inputs
+#' 
+#' Get a list of valid input_items for a context.
+#' 
+#' @param context The name of a valid context (character)
+#' @return A list of input item names for a context
+#' @examples
+#' # list of input items for the "study" context
+#' context_inputs("study")
+#' @export
+context_inputs = function(context) {
+    if (!is.character(context)) {
+        stop('"context" must be of type "character"')
+    }
+    
+    name_valid = context %in% names(metabolomicsWorkbenchR::context)
+    if (!name_valid) {
+        stop(paste0('"',context,'" is not a recognised context. Use ',
+            'names(context) for a list of valid contexts'))
+    }
+    
+    return(metabolomicsWorkbenchR::context[[context]]$input_items)
+}
+
+#' Valid outputs
+#' 
+#' Get a list of valid output_items for a context.
+#' 
+#' @param context The name of a valid context (character)
+#' @return A list of output item names for a context
+#' @examples
+#' # list of output items for the "study" context
+#' context_outputs("study")
+#' @export
+context_outputs = function(context) {
+    if (!is.character(context)) {
+        stop('"context" must be of type "character"')
+    }
+    
+    name_valid = context %in% names(metabolomicsWorkbenchR::context)
+    if (!name_valid) {
+        stop(paste0('"',context,'" is not a recognised context. Use ',
+            'names(context) for a list of valid contexts'))
+    }
+    
+    x=metabolomicsWorkbenchR::context[[context]]$output_items
+    w=which(x=='all')
+    if (length(w)>0){
+        x=x[-w]
+    }
+    return(x)
+}
+
+#' Valid input_value for input_item
+#' 
+#' Displays a valid input_value for an input_item and returns an example that
+#' matches the required input pattern.
+#' 
+#' @param input_item The name of a valid input_item (character)
+#' @return An example input value matching the pattern required for the chosen
+#' input item.
+#' @examples
+#' # example input_value for input item "study_id" 
+#' input_example('study_id')
+#' @export
+input_example = function(input_item) {
+    if (!is.character(input_item)) {
+        stop('"input_item" must be of type "character"')
+    }
+    
+    name_valid = input_item %in% names(metabolomicsWorkbenchR::input_item)
+    if (!name_valid) {
+        stop(paste0('"',input_item,'" is not a recognised input_item. Use ',
+            'names(input_item) for a list of valid input items'))
+    }
+    
+    show(metabolomicsWorkbenchR::input_item[[input_item]])
+    
+    return(
+        invisible(metabolomicsWorkbenchR::input_item[[input_item]]$example[1]))
+}
+
+
diff --git a/R/parse_fcns.R b/R/parse_fcns.R
@@ -154,8 +154,13 @@ parse_untarg_data=function(response,output_item,input_value) {
     
     # add the factors into back into the table
     w=which(colnames(out)=='group')
+    # convert to numeric
+    temp=lapply(out[(w+1):ncol(out)],as.numeric)
+    temp=as.data.frame(temp)
+    rownames(temp)=rownames(out)
+    colnames(temp)=colnames(out[(w+1):ncol(out)])
     # exclude group
-    out=cbind(out[seq_len(w-1)],m,out[(w+1):ncol(out)])
+    out=cbind(out[seq_len(w-1)],m,temp)
     
     out$group=NULL
     return(out)
@@ -176,8 +181,13 @@ parse_datatable=function(response,output_item,input_value) {
     
     # add the factors into back into the table
     w=which(colnames(out)=='Class')
+    # convert to numeric
+    temp=lapply(out[(w+1):ncol(out)],as.numeric)
+    temp=as.data.frame(temp)
+    rownames(temp)=rownames(out)
+    colnames(temp)=colnames(out[(w+1):ncol(out)])
     # exclude group
-    out=cbind(out[seq_len(w-1)],m,out[(w+1):ncol(out)])
+    out=cbind(out[seq_len(w-1)],m,temp)
     out$Class=NULL
     attributes(out)=c(attributes(out),list('number_of_factors'=ncol(m)))
     
diff --git a/man/context_inputs.Rd b/man/context_inputs.Rd
diff --git a/man/context_outputs.Rd b/man/context_outputs.Rd
diff --git a/man/input_example.Rd b/man/input_example.Rd
diff --git a/tests/testthat/test-classdef.R b/tests/testthat/test-classdef.R
@@ -6,7 +6,8 @@ test_that("context creation works as expected", {
         output_items = c('summary','factors','analysis','metabolites','mwtab',
             'source','species','disease','number_of_metabolites','data','datatable',
             'untarg_studies','untarg_factors','untarg_data','metabolite_info',
-            'SummarizedExperiment')
+            'SummarizedExperiment','untarg_SummarizedExperiment',
+            'DatasetExperiment','untarg_DatasetExperiment')
     )
     
     expect_equal(study,context$study)
diff --git a/tests/testthat/test-helpers.R b/tests/testthat/test-helpers.R
@@ -0,0 +1,32 @@
+test_that("list of context inputs returns correctly", {
+    
+    expect_identical(context_inputs("study")[1],"study_id")
+    
+    expect_error(context_inputs(123))
+    
+    expect_error(context_inputs("banana"))
+    
+}
+)
+
+test_that("list of context outputs returns correctly", {
+    
+    expect_identical(context_outputs("study")[1],"summary")
+    
+    expect_error(context_outputs(123))
+    
+    expect_error(context_outputs("banana"))
+    
+}
+)
+
+test_that("input example returns correctly", {
+    
+    expect_identical(input_example("study_id")[1],"ST000001")
+    
+    expect_error(input_example(123))
+    
+    expect_error(input_example("banana"))
+    
+}
+)
diff --git a/vignettes/Introduction_to_metabolomicsWorkbenchR.Rmd b/vignettes/Introduction_to_metabolomicsWorkbenchR.Rmd
@@ -1,5 +1,5 @@
 ---
-title: "Introduction_to_metabolomicsWorkbenchR"
+title: "Introduction to `metabolomicsWorkbenchR`"
 author:
 - name: Gavin R Lloyd
   affiliation: Phenome Centre Birmingham, University of Birmingham, UK
@@ -22,6 +22,7 @@ vignette: >
 
 ```{r echo = FALSE,include=FALSE}
 suppressPackageStartupMessages(library(metabolomicsWorkbenchR))
+library(grid)
 ```
 
 
@@ -88,6 +89,19 @@ df = do_query(
 )
 
 df[,1:3]
+```
+We can also request an image of the molecular structure:
+
+```{r}
+img = do_query(
+        context = 'compound',
+        input_item = 'regno',
+        input_value = '11',
+        output_item = 'png'
+      )
+
+grid.raster(img)
+
 ```
 
 Valid contexts, input items and output items can be listed using the `names` function:
@@ -97,8 +111,12 @@ Valid contexts, input items and output items can be listed using the `names` fun
 names(context) # context, input_item or output_item
 ```
 
-Valid inputs and outputs for a context can be displayed by accessing the list of context objects. Valid inputs for a particular output can also be displayed by accessing the list of output item objects. Use of `metabolmicsWorkbenchR` objects is detailed in a later section.
+Valid inputs and outputs for a context can be displayed by accessing the list of context objects. Valid inputs for a particular output can also be displayed by accessing the list of output item objects. Use of `metabolmicsWorkbenchR` objects is detailed in a later section. In addition, functions `context_inputs`, `context_outputs` and `input_example` are provided for convenience.
 
+```{r}
+# valid inputs for "study" context
+context_inputs('study')
+```
 More information about the different contexts can be found in the API documentation
 [(link)](https://www.metabolomicsworkbench.org/tools/MWRestAPIv1.0.pdf)
 
@@ -120,7 +138,7 @@ df[1:3,1:3]
 ```
 
 ## `output_item` "compound_exact", "protein_exact" and "gene_exact"
-These outputs refer to compound, protein and gene context API outputs that can be used with exact matching. This means that only exact matches to the input_value will be returned. For these outputs all available output fields will be returned.
+These outputs refer to compound, protein and gene context API outputs that can be used with exact matching. This means that only exact matches to the input_value will be returned. For these outputs all available output fields will be returned. These output items are used in place of the 'all' item specified in the API documentation.
 
 ```{r}
 df = do_query(
@@ -134,7 +152,7 @@ df[,1:3]
 ```
 
 ## `output_item` "protein_partial" and "gene_partial"
-These outputs refer to protein and gene contexts API outputs that can be used with partial matching. This means that all records with a partial match to the input_value will be returned. For these outputs all available output fields will be returned.
+These outputs refer to protein and gene contexts API outputs that can be used with partial matching. This means that all records with a partial match to the input_value will be returned. For these outputs all available output fields will be returned. 
 
 ```{r}
 df = do_query(
diff --git a/vignettes/example_using_structToolbox.Rmd b/vignettes/example_using_structToolbox.Rmd

Original file line number	Diff line number	Diff line change
`@@ -57,7 +57,8 @@ context$study = mw_context(`
`57`	`57`	`output_items = c('summary','factors','analysis','metabolites','mwtab',`
`58`	`58`	`'source','species','disease','number_of_metabolites','data','datatable',`
`59`	`59`	`'untarg_studies','untarg_factors','untarg_data','metabolite_info',`
`60`		`- 'SummarizedExperiment')`
	`60`	`+ 'SummarizedExperiment','untarg_SummarizedExperiment','DatasetExperiment',`
	`61`	`+ 'untarg_DatasetExperiment')`
`61`	`62`	`)`
`62`	`63`
`63`	`64`	`context$compound = mw_context(`