Preprint
Knowledge Graphs

DrugBank 6.0: the DrugBank Knowledgebase for 2024

Craig Knox, Mike Wilson, Christen M. Klinger, Mark Franklin, Eponine Oler(University of Alberta), Alexander E. Wilson, Allison Pon, Jordan J. Cox, Na Eun Chin, Seth A Strawbridge, Marysol García-Patiño, Ray Kruger(University of Alberta), Aadhavya Sivakumaran(University of Alberta), Selena Sanford(University of Alberta), Rahil Doshi(University of Alberta), Nitya Khetarpal(University of Alberta), Omolola Fatokun(University of Alberta), Daphnee Doucet(University of Alberta), Ashley Zubkowski(University of Alberta), Dorsa Yahya Rayat(University of Alberta), Hayley Jackson(University of Alberta), Karxena Harford(University of Alberta), Afia Anjum(University of Alberta), Mahi Zakir(University of Alberta), Fei Wang(University of Alberta), Siyang Tian(University of Alberta), Brian Lee(University of Alberta), Jaanus Liigand(University of Alberta), Harrison Peters(University of Alberta), Ruo Qi Wang, Tue Nguyen, Denise So, Matthew Sharp, Rodolfo da Silva, C. Gabriel, J.D. Scantlebury, Marissa Jasinski, David S. Ackerman, Timothy Jewison, Tanvir Sajed(University of Alberta), Vasuk Gautam(University of Alberta), David S. Wishart(University of Alberta)
October 16, 2023Nucleic Acids Research1,598 citations
PDFDOI

1.6k

Citations

93

Influential Citations

Nucleic Acids Research

Venue

2023

Year

Abstract

First released in 2006, DrugBank (https://go.drugbank.com) has grown to become the 'gold standard' knowledge resource for drug, drug-target and related pharmaceutical information. DrugBank is widely used across many diverse biomedical research and clinical applications, and averages more than 30 million views/year. Since its last update in 2018, we have been actively enhancing the quantity and quality of the drug data in this knowledgebase. In this latest release (DrugBank 6.0), the number of FDA approved drugs has grown from 2646 to 4563 (a 72% increase), the number of investigational drugs has grown from 3394 to 6231 (a 38% increase), the number of drug-drug interactions increased from 365 984 to 1 413 413 (a 300% increase), and the number of drug-food interactions expanded from 1195 to 2475 (a 200% increase). In addition to this notable expansion in database size, we have added thousands of new, colorful, richly annotated pathways depicting drug mechanisms and drug metabolism. Likewise, existing datasets have been significantly improved and expanded, by adding more information on drug indications, drug-drug interactions, drug-food interactions and many other relevant data types for 11 891 drugs. We have also added experimental and predicted MS/MS spectra, 1D/2D-NMR spectra, CCS (collision cross section), RT (retention time) and RI (retention index) data for 9464 of DrugBank's 11 710 small molecule drugs. These and other improvements should make DrugBank 6.0 even more useful to a much wider research audience ranging from medicinal chemists to metabolomics specialists to pharmacologists.

Analysis

Why This Paper Matters

DrugBank 6.0 represents a major update to the most widely used drug knowledgebase, which is critical for AI practitioners in drug discovery and bioinformatics. With over 30 million annual views, DrugBank serves as the foundational data source for training machine learning models on drug-target interactions, drug-drug interactions, and drug metabolism. The 300% increase in drug-drug interactions and addition of spectral data (MS/MS, NMR, CCS, RT, RI) for nearly 10,000 small molecules directly enables more accurate predictive models and multi-modal AI systems.

For AI researchers, this paper matters because it provides a richer, more complete dataset that can be used to train models for tasks like drug repurposing, adverse event prediction, and metabolomics. The inclusion of experimental and predicted spectral data opens new avenues for integrating cheminformatics with deep learning, particularly for small molecule property prediction and identification.

Technical Contributions

  • Massive data expansion: 72% more FDA-approved drugs, 38% more investigational drugs, and 300% more drug-drug interactions.
  • Rich pathway annotations: Thousands of new, colorful, richly annotated drug mechanism and metabolism pathways.
  • Multi-modal spectral data: Experimental and predicted MS/MS, 1D/2D-NMR, CCS, RT, and RI data for 9,464 small molecule drugs.
  • Improved data quality: Enhanced drug indications, interactions, and other data types across all 11,891 drugs.
  • Open access: Freely available at https://go.drugbank.com, supporting reproducibility and community use.

Results

DrugBank 6.0 now contains 4,563 FDA-approved drugs (up from 2,646), 6,231 investigational drugs (up from 3,394), 1,413,413 drug-drug interactions (up from 365,984), and 2,475 drug-food interactions (up from 1,195). Spectral data covers 9,464 of 11,710 small molecule drugs. The knowledgebase averages over 30 million views per year, demonstrating its widespread adoption.

Significance

DrugBank 6.0 is a cornerstone resource for AI-driven drug discovery and bioinformatics. Its comprehensive, curated data enables training of models for drug-target interaction prediction, drug-drug interaction risk assessment, and metabolomics-based diagnostics. The addition of spectral data supports multi-modal AI approaches that combine chemical structure, interaction networks, and experimental measurements. This update will accelerate research in personalized medicine, drug repurposing, and pharmaceutical AI, making it an essential tool for both academic and industrial AI practitioners.

knowledge-graphsdrug-discoverybioinformaticspharmacologydata-integrationspectral-datapathways

Related Papers