v2.2.1

.Rbuildignore

@@ -15,3 +15,5 @@
 ^doc$
 ^Meta$
 ^CRAN-SUBMISSION$
+^paper\.md$
+^paper\.bib$

.github/workflows/draft-pdf.yml

@@ -0,0 +1,28 @@
+name: Draft PDF
+on:
+  push:
+    paths:
+      - paper.md
+      - paper.bib
+
+jobs:
+  paper:
+    runs-on: ubuntu-latest
+    name: Paper Draft
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Build draft PDF
+        uses: openjournals/openjournals-draft-action@master
+        with:
+          journal: joss
+          # This should be the path to the paper within your repo.
+          paper-path: paper.md
+      - name: Upload
+        uses: actions/upload-artifact@v4
+        with:
+          name: paper
+          # This is the output path where Pandoc will write the compiled
+          # PDF. Note, this should be the same directory as the input
+          # paper.md
+          path: paper.pdf

.github/workflows/rhub.yaml

@@ -0,0 +1,95 @@
+# R-hub's generic GitHub Actions workflow file. It's canonical location is at
+# https://github.com/r-hub/actions/blob/v1/workflows/rhub.yaml
+# You can update this file to a newer version using the rhub2 package:
+#
+# rhub::rhub_setup()
+#
+# It is unlikely that you need to modify this file manually.
+
+name: R-hub
+run-name: "${{ github.event.inputs.id }}: ${{ github.event.inputs.name || format('Manually run by {0}', github.triggering_actor) }}"
+
+on:
+  workflow_dispatch:
+    inputs:
+      config:
+        description: 'A comma separated list of R-hub platforms to use.'
+        type: string
+        default: 'linux,windows,macos'
+      name:
+        description: 'Run name. You can leave this empty now.'
+        type: string
+      id:
+        description: 'Unique ID. You can leave this empty now.'
+        type: string
+
+jobs:
+
+  setup:
+    runs-on: ubuntu-latest
+    outputs:
+      containers: ${{ steps.rhub-setup.outputs.containers }}
+      platforms: ${{ steps.rhub-setup.outputs.platforms }}
+
+    steps:
+    # NO NEED TO CHECKOUT HERE
+    - uses: r-hub/actions/setup@v1
+      with:
+        config: ${{ github.event.inputs.config }}
+      id: rhub-setup
+
+  linux-containers:
+    needs: setup
+    if: ${{ needs.setup.outputs.containers != '[]' }}
+    runs-on: ubuntu-latest
+    name: ${{ matrix.config.label }}
+    strategy:
+      fail-fast: false
+      matrix:
+        config: ${{ fromJson(needs.setup.outputs.containers) }}
+    container:
+      image: ${{ matrix.config.container }}
+
+    steps:
+      - uses: r-hub/actions/checkout@v1
+      - uses: r-hub/actions/platform-info@v1
+        with:
+          token: ${{ secrets.RHUB_TOKEN }}
+          job-config: ${{ matrix.config.job-config }}
+      - uses: r-hub/actions/setup-deps@v1
+        with:
+          token: ${{ secrets.RHUB_TOKEN }}
+          job-config: ${{ matrix.config.job-config }}
+      - uses: r-hub/actions/run-check@v1
+        with:
+          token: ${{ secrets.RHUB_TOKEN }}
+          job-config: ${{ matrix.config.job-config }}
+
+  other-platforms:
+    needs: setup
+    if: ${{ needs.setup.outputs.platforms != '[]' }}
+    runs-on: ${{ matrix.config.os }}
+    name: ${{ matrix.config.label }}
+    strategy:
+      fail-fast: false
+      matrix:
+        config: ${{ fromJson(needs.setup.outputs.platforms) }}
+
+    steps:
+      - uses: r-hub/actions/checkout@v1
+      - uses: r-hub/actions/setup-r@v1
+        with:
+          job-config: ${{ matrix.config.job-config }}
+          token: ${{ secrets.RHUB_TOKEN }}
+      - uses: r-hub/actions/platform-info@v1
+        with:
+          token: ${{ secrets.RHUB_TOKEN }}
+          job-config: ${{ matrix.config.job-config }}
+      - uses: r-hub/actions/setup-deps@v1
+        with:
+          job-config: ${{ matrix.config.job-config }}
+          token: ${{ secrets.RHUB_TOKEN }}
+      - uses: r-hub/actions/run-check@v1
+        with:
+          job-config: ${{ matrix.config.job-config }}
+          token: ${{ secrets.RHUB_TOKEN }}

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: dbparser
 Title: Drugs Databases Parser
-Version: 2.0.3
+Version: 2.2.1
 Authors@R:
     c(
     person("Mohammed", "Ali", email = "moh_fcis@yahoo.com", role = c("aut", "cre")),
@@ -12,13 +12,15 @@ Description: This tool is for parsing public drug databases such as 'DrugBank' X
 License: MIT + file LICENSE
 Encoding: UTF-8
 Imports:
+    data.table,
     dplyr,
     progress,
     purrr,
     tibble,
     tools,
+    utils,
     XML
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.3
 Suggests:
     canvasXpress,
     knitr,

NAMESPACE

@@ -1,10 +1,17 @@
 # Generated by roxygen2: do not edit by hand
 
+export(add_database_info)
 export(cett_nodes_options)
 export(drug_node_options)
+export(merge_drugbank_onsides)
+export(merge_drugbank_twosides)
 export(parseDrugBank)
+export(parseOnSIDES)
+export(parseTWOSIDES)
 export(references_node_options)
 export(show_dvobject_metadata)
+export(subset_drugbank_dvobject)
+export(subset_onsides_dvobject)
 import(dplyr)
 importFrom(XML,xmlApply)
 importFrom(XML,xmlChildren)
@@ -16,7 +23,17 @@ importFrom(XML,xmlSize)
 importFrom(XML,xmlToDataFrame)
 importFrom(XML,xmlToList)
 importFrom(XML,xmlValue)
+importFrom(data.table,fread)
+importFrom(dplyr,.data)
+importFrom(dplyr,distinct)
+importFrom(dplyr,filter)
+importFrom(dplyr,left_join)
+importFrom(dplyr,mutate)
+importFrom(dplyr,pull)
+importFrom(dplyr,rename)
+importFrom(dplyr,select)
 importFrom(progress,progress_bar)
+importFrom(purrr,"%||%")
 importFrom(purrr,'%>%')
 importFrom(purrr,is_empty)
 importFrom(purrr,is_null)
@@ -26,5 +43,6 @@ importFrom(tibble,as_tibble)
 importFrom(tibble,as_tibble_row)
 importFrom(tibble,tibble)
 importFrom(tibble,tibble_row)
+importFrom(utils,object.size)
 importFrom(utils,stack)
 importFrom(utils,unzip)

NEWS.md

@@ -1,3 +1,58 @@
+# dbparser
+
+# dbparser 2.2.1
+
+This is a major feature release focused on expanding `dbparser`'s capabilities into real-world pharmacovigilance and drug-drug interaction analysis. The integration engine has been formalized around a "Hub and Spoke" model, with DrugBank acting as the central hub.
+
+## NEW FEATURES
+
+*   **New Parser: `parseOnSIDES()`**
+    *   Parses the relational CSV files from the OnSIDES database, a modern resource for adverse drug events extracted from FDA labels.
+    *   Returns a `dvobject` containing the 7 core relational tables and an optional `high_confidence` summary table.
+
+*   **New Parser: `parseTWOSIDES()`**
+    *   Parses the TWOSIDES database, the leading resource for drug-drug interaction (DDI) adverse event signals from real-world data.
+    *   Returns a `dvobject` containing the `drug_drug_interactions` table.
+    *   The parser correctly handles known column name misspellings in the source data (e.g., `drug_1_rxnorn_id`).
+
+*   **New Integration Function: `merge_drugbank_onsides()`**
+    *   Merges a DrugBank `dvobject` with an OnSIDES `dvobject`.
+    *   Automatically creates an enriched `integrated_data` list, linking OnSIDES data to DrugBank IDs via RxNorm CUIs.
+    *   The function is **chainable**, meaning it can be used in a `%>%` pipeline after other merge functions.
+
+*   **New Integration Function: `merge_drugbank_twosides()`**
+    *   Merges a DrugBank `dvobject` with a TWOSIDES `dvobject`.
+    *   Performs a "double join" to enrich both drugs in an interaction pair with their DrugBank IDs and names.
+    *   Uses a robust "union" logic to keep interactions even if only one of the two drugs is present in the input DrugBank object.
+    *   The function is also **chainable**.
+*   **Subset a DrugBank dvobject function: `subset_drugbank_dvobject()`**
+    * Intelligently filters a DrugBank dvobject to retain only the data associated with a specified list of drugbank_ids. It correctly handles the deep,
+multi-level nested structure of the entire object, including the complex relationships within the `cett` list.
+*   **Subset an OnSIDES dvobject function: `subset_onsides_dvobject()`**
+    * Intelligently filters an OnSIDES dvobject by cascading filters through the
+relational tables, ensuring the final subset is self-consistent.
+*   **Adding metadata to existing `dvobject` objects using function: `add_database_info()`**
+*   **Major enhancements to function `show_dvobject_metadata()`**
+    * Displays information about passed dbobject object including basic info, 
+    database metadata, and all data.frames contained within nested lists.
+
+* Run `vignette("dbparser_2_2", package = "dbparser")` for more info
+
+## DOCUMENTATION
+
+*   **New Vignette: "Integrated Pharmacovigilance"**
+    *   A comprehensive new tutorial demonstrating a full, three-way integration of DrugBank, OnSIDES, and TWOSIDES.
+    *   Includes a complete scientific case study analyzing single-drug vs. polypharmacy risks.
+    *   Introduces a reproducible example workflow using a pre-computed RDS data object hosted externally to keep the package lightweight.
+    *   Run `vignette("drugbank_nside", package = "dbparser")` for more info
+*  Updated existing vignette and package Readme with enhanced examples
+
+## BUG FIXES & MINOR IMPROVEMENTS
+
+*   Several minor fixes are done
+
+---
+
 # dbparser 2.0.3
 
 ## Enhancements

R/drugbank_parser.R

@@ -80,7 +80,13 @@ parseDrugBank <- function(db_path,
     message("Completed loading DrugBank DB into memory")
     message("...........................................")
     pkg_env$root <- XML::xmlRoot(parsed_db)
-    dvobject     <- add_drugbank_info(dvobject  = dvobject)
+    dvobject     <- add_database_info(dvobject         = dvobject,
+                                      db_version       = XML::xmlGetAttr(
+                                        node = pkg_env$root,
+                                        name = "version"),
+                                      db_exported_date = XML::xmlGetAttr(
+                                        node = pkg_env$root,
+                                        name = "exported-on"))
     message("parsing drugs elements")
 
     dvobject[["drugs"]] <- parse_drug_nodes(drug_options)