Drug Identifiers

The Drug Identifiers Package covers:

<p><br/></p>

- 16,558 drugs, their chemical structures OR sequences. Includes coverage of salt and ester drug product formulations.

- Chemical structures in multiple formats, including SDF, SMILES, & Inchi.
- External identifiers such as: ChEMBL, PubChem, RxCUI, PDB, GenBank, Uniprot, & Zinc.

<p><br/></p>

The data is meticulously organized, curated, and optimized for traditional and machine-learning applications to:

- ****Simplify data normalization**** from multiple sources with comprehensive lists of synonyms, brand names, code names, & other common identifiers.
- **Identify potential patterns**  by grouping drugs based on structural similarity, sequence similarity, type of drug, or chemical properties.
- **Enable efficient information** retrieval and analysis for data consumers by enabling lookups by multiple naming conventions and identifiers from multiple platforms.

DrugBank is the world’s first intelligent and comprehensive drug knowledge platform. Our goal is to augment human intelligence so that all medical information is used to its fullest potential ensuring that everyone has access to the best possible medical outcomes. With the help of artificial intelligence, our team of medical and scientific experts gather, author, verify, and structure all of the latest biomedical information into one knowledge platform. Our offerings include machine learning-ready dataset downloads that have been thoughtfully packaged to serve unique use cases.

<p><br/></p>

The following data modules are included in this package:

<p><br/></p>

- **Drugs**: This module provides a comprehensive list of all approved and investigational drugs. Each drug includes detailed molecular descriptions and relevant nomenclature and identifiers. The dataset includes coverage of small molecule drugs and biologics.

<p><br/></p>

- **References**: This module provides comprehensive citations, substantiating the facts mentioned within DrugBank.

---

The workflow to request this data is as follows:

- Click the “Get” button to try the data

- Click the “Request” button to request the complete package

- DrugBank will get in touch with you to describe how the data will be shared

搜集汇总

背景与挑战

背景概述

该数据集涵盖16,558种药物及其化学结构或序列，提供多种格式和外部标识符，旨在通过数据标准化、模式识别和高效检索支持机器学习和分析应用。数据源自DrugBank知识平台，包含药物和参考文献模块，需通过请求流程获取完整包。