Add Vignette and functions for Chembl

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: AnnotationGx
 Title: AnnotationGx: A package for building, updating and querying an
     annotation database for pharmaco-genomic data
-Version: 0.0.0.9080
+Version: 0.0.0.9081
 Authors@R: c(
     person("Jermiah", "Joseph", role = c("aut", "cre"),
         email = "[email protected]"),
@@ -32,7 +32,10 @@ Suggests:
     covr,
     readxl,
     knitr,
-    rmarkdown
+    rmarkdown,
+    BiocStyle,
+    RefManageR,
+    sessioninfo
 Config/testthat/edition: 3
 Config/testthat/parallel: true
 Config/testthat/start-first: watcher, parallel*

NAMESPACE

@@ -1,8 +1,10 @@
 # Generated by roxygen2: do not edit by hand
 
 export(annotatePubchemCompound)
+export(getChemblFilterTypes)
 export(getChemblMechanism)
 export(getChemblResourceFields)
+export(getChemblResources)
 export(getOncotreeMainTypes)
 export(getOncotreeTumorTypes)
 export(getOncotreeVersions)
@@ -14,6 +16,7 @@ export(getUnichemSources)
 export(mapCID2Properties)
 export(mapCell2Accession)
 export(mapCompound2CID)
+export(queryChemblAPI)
 export(queryUnichem)
 export(standardize_names)
 import(BiocParallel)

R/chembl.R

@@ -78,16 +78,39 @@
 
   # Add the query parameters
   query <- list()
-  query[["format"]] <- format
   fld <- paste0(field, "__", filter_type)
   query[[fld]] <- value
+  query[["format"]] <- format
   url$query <- query
 
   final_url <- httr2::url_build(url)
   final_url |> .build_request()
 }
 
 
+#' Query the ChEMBL API
+#'
+#' This function queries the ChEMBL API using the specified parameters and returns the response in JSON format.
+#'
+#' @param resource The resource to query in the ChEMBL API.
+#' @param field The field to filter on in the ChEMBL API.
+#' @param filter_type The type of filter to apply in the ChEMBL API.
+#' @param value The value to filter on in the ChEMBL API.
+#' @param format The format of the response (default is "json").
+#'
+#' @return The response from the ChEMBL API in JSON format.
+#'
+#' @examples
+#' queryChemblAPI("mechanism", "molecule_chembl_id", "in", "CHEMBL1413")
+#'
+#' @export
+queryChemblAPI <- function(resource, field, filter_type, value, format = "json") {
+  .build_chembl_request(resource, field, filter_type, value, format) |> 
+    .perform_request() |> 
+    .parse_resp_json()
+}
+
+
 #' Get ChEMBL Mechanism
 #'
 #' This function retrieves information about the mechanism of action for a given ChEMBL ID.
@@ -162,3 +185,31 @@ getChemblResourceFields <- function(resource) {
   checkmate::assert_choice(resource, .chembl_resources())
   .chembl_resource_schema(resource)[["fields"]] |> names()
 }
+
+#' getChemblResources function
+#'
+#' This function retrieves the Chembl resources.
+#'
+#' @return A list of Chembl resources.
+#'
+#' @examples
+#' getChemblResources()
+#'
+#' @export
+getChemblResources <- function(){
+  .chembl_resources()
+}
+
+#' Get the Chembl filter types
+#'
+#' This function retrieves the Chembl filter types.
+#'
+#' @return A list of Chembl filter types.
+#'
+#' @examples
+#' getChemblFilterTypes()
+#'
+#' @export
+getChemblFilterTypes <- function(){
+  .chembl_filter_types()
+}

tests/testthat/test_chembl.R

@@ -11,10 +11,10 @@ test_that("build_chembl_request constructs the correct URL", {
   format <- "json"
 
   # Call the function
-  url <- .build_chembl_request(resource, field, filter_type, value, format)
+  url <- AnnotationGx:::.build_chembl_request(resource, field, filter_type, value, format)
 
   # Check the constructed URL
-  expected_url <- "https://www.ebi.ac.uk/chembl/api/data/target?format=json&target_chembl_id__exact=CHEMBL2144069"
+  expected_url <-"https://www.ebi.ac.uk/chembl/api/data/target?target_chembl_id__exact=CHEMBL2144069&format=json"
   expect_equal(url$url, expected_url)
 })
 
@@ -35,7 +35,7 @@ test_that("getChemblMechanism works", {
 
   url <- getChemblMechanism(chembl_id, returnURL = T)
   expect_list(url)
-  expect_equal(url[[1]], "https://www.ebi.ac.uk/chembl/api/data/mechanism?format=json&molecule_chembl_id__in=CHEMBL1413")
+  expect_equal(url[[1]], "https://www.ebi.ac.uk/chembl/api/data/mechanism?molecule_chembl_id__in=CHEMBL1413&format=json")
 })
 
 
@@ -55,3 +55,41 @@ test_that("getChemblResourceFields works", {
     "site_id", "target_chembl_id", "variant_sequence"
   ))
 })
+
+test_that("queryChemblAPI constructs the correct URL and returns parsed JSON response", {
+  # Set up test data
+  resource <- "mechanism"
+  field <- "mechanism_of_action"
+  filter_type <- "icontains"
+  value <- "Muscarinic acetylcholine receptor"
+  format <- "json"
+  expected_url <- "https://www.ebi.ac.uk/chembl/api/data/mechanism?mechanism_of_action__icontains=Muscarinic%20acetylcholine%20receptor&format=json"
+
+  request <- AnnotationGx:::.build_chembl_request(resource, field, filter_type, value, format)
+  expect_equal(request$url, expected_url)
+
+  # Call the function
+  response <- queryChemblAPI(resource, field, filter_type, value, format)
+
+  expect_class(response, "list")
+
+  expect_length(response, 2)
+})
+
+test_that("getChemblFilterTypes works", {
+  result <- getChemblFilterTypes()
+
+  expect_class(result, "character")
+  expect_length(result, 19)
+
+  expect_true("in" %in% result)
+})
+
+test_that("getChemblResources works", {
+  result <- getChemblResources()
+
+  expect_class(result, "character")
+  expect_length(result, 32)
+
+  expect_true("activity" %in% result)
+})

vignettes/ChEMBL.Rmd

@@ -0,0 +1,134 @@
+---
+title: "Querying ChEMBL Database"
+author: 
+  - name: Jermiah Joseph, Shahzada Muhammad Shameel Farooq, and Christopher Eeles
+output: 
+  BiocStyle::html_document:
+    self_contained: yes
+    toc: true
+    toc_float: true
+    toc_depth: 2
+    code_folding: show
+date: "`r doc_date()`"
+package: "`r pkg_ver('AnnotationGx')`"
+vignette: >
+  %\VignetteIndexEntry{Querying ChEMBL Database}
+  %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteEncoding{UTF-8}  
+---
+
+
+```{r setup, include = FALSE}
+knitr::opts_chunk$set(
+    collapse = TRUE,
+    comment = "#>",
+    crop = NULL ## Related to https://stat.ethz.ch/pipermail/bioc-devel/2020-April/016656.html
+)
+```
+
+
+# Introduction to ChEMBL API
+
+**WARNING: This vignette is a work in progress. If you have questions or would
+like to see more features, please open an issue at 
+[bhklab/AnnotationGx](https://github.com/bhklab/AnnotationGx)**
+
+The ChEMBL database contains information on bioactive drug-like small molecules.
+The information includes 2-D structures, calculated properties; logP, Molecular
+Weight, Lipinski Parameters, and abstracted bioactivities; binding
+constants and ADMET data. The data is curated from primary scientific literature.
+The ChEMBL API allows for the data to be made available for retrieval in a
+programmatic fashion. We can use the API to query CHEMBL ID of a compound, retrieve
+all molecule mechanisms of action, query compound_record resource and molecule
+resource from the ChEMBL database.
+
+
+## Setup
+
+```{r setup agx}
+library(AnnotationGx)
+```
+
+
+
+## Retrieve molecule mechanisms of action from ChEMBL {#chembl-mechanisms}
+
+Given a ChEMBL ID, we can retrieve the molecule mechanisms of action from the
+ChEMBL database using the `getChemblMechanism()` function. 
+
+**
+NOTE: This is a specialized function that queries the API for the *mechanism* resource only.
+To query other resources, please see the [Custom Queries](#custom-queries) section.
+**
+
+
+
+``` {r run one query}
+mechs <- getChemblMechanism("CHEMBL1413")
+mechs
+```
+
+In the above example, multiple mechanisms of action are returned. 
+
+
+## Custom Queries {#custom-queries}
+
+The ChEMBL API allows for a wide range of queries. We have specialized one function,
+but are open to incorporating more. Please open an issue at [bhklab/AnnotationGx](https://github.com/bhklab/AnnotationGx)
+with an idea of a specialized function that meets a use case. 
+
+A query to the API follows the following format:
+```
+https://www.ebi.ac.uk/chembl/api/data/[resource]?[field]__[filter_type]=[value]&format=[format]
+```
+More information can be found at the [API Documentation](https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-**services******)
+
+In summary, the requirements for a query are:
+
+1. The `resource` to be queried
+2. The reource `field` to be queried
+3. The `filter_type` to be used
+4. The `value` to be used for the filter
+5. (optional) The `format` of the returned data (default is JSON)
+
+For example, the query for the example in [the above section](#chembl-mechanisms) would be:
+"https://www.ebi.ac.uk/chembl/api/data/mechanism?molecule_chembl_id__in=CHEMBL1413&format=json"
+where:
+
+- `resource` is "mechanism"
+- `field` is "molecule_chembl_id"
+- `filter_type` is "in"
+- `value` is "CHEMBL1413"
+- `format` is "json"
+
+These parameters can be used in the `queryChemblAPI(resource, field, filter_type, value, format = "json")`
+function to query the ChEMBL API.
+
+**NOTE: unlike the `getChemblMechanism()` function which returns a `data.table`, the `queryChemblAPI()` function 
+returns the raw data unformatted**
+
+``` {r run custom query}
+queryChemblAPI("mechanism", "molecule_chembl_id", "in", "CHEMBL1413")
+```
+
+The `getChemblResources()` function returns a list of possible 
+resources that can be queried:
+
+``` {r query resources}
+getChemblResources() 
+```
+
+
+The `getChemblResourceFields(resource)` function returns a list of possible
+fields that can be queried for a given resource:
+``` {r query resource fields}
+getChemblResourceFields("mechanism")
+
+```
+
+
+The `getChemblFilterTypes()` function returns a list of possible filter types.
+
+``` {r query filter types}
+getChemblFilterTypes()
+```