This data package contains medical datasets that have been used to build the Drugs@FDA. The information is classified by health information, regulatory information and advanced search. This data package contains the necessary technical information (excluding programming scripts) to reproduce the online version of Drugs@FDA. The data package is best to use with a database program.

This dataset provides a comprehensive, structured overview of hundreds of commonly used pharmaceutical drugs, listed alphabetically by generic name. It serves as a valuable resource for healthcare students, professionals, data analysts, and anyone interested in pharmacology.

Compiled from reputable sources like the FDA Prescribing Information, Lexicomp, and Micromedex, each entry includes detailed information on drug properties, safety, and usage. This dataset is ideal for educational purposes, data analysis projects, and as a reference for building healthcare applications.

Key Features (Columns):

Generic Name: The common name of the drug.

Drug Class: The pharmacological category (e.g., SSRI, Beta-Blocker, Statin).

Indications: The medical conditions the drug is used to treat.

Dosage Form: The physical form of the drug (e.g., Tablet, Capsule, Injection, Cream).

Strength: The potency of the drug (e.g., 500 mg, 0.1%).

Route of Administration: How the drug is administered (e.g., Oral, Topical, Intravenous).

Side Effects: Common adverse reactions associated with the drug.

Contraindications: Conditions or factors that serve as a reason to not use the drug.

Interaction warnings & Precautions: Important information on how the drug interacts with others and key safety measures.

Storage Conditions: Recommended storage instructions (e.g., Room Temperature, Refrigerate).

Reference: The primary source(s) of the information.

Availability: Whether the drug is typically available by prescription or over-the-counter (OTC).

Potential Use Cases:

Educational Tool: For students of medicine, pharmacy, and nursing to learn about drug properties.

Data Analysis & Visualization: Analyze the distribution of drug classes, common side effects, or storage requirements.

Drug Interaction Checker (Basic Foundation): Use as a base dataset to build a simple drug interaction screening tool.

Clinical Reference Application: Populate a mobile or web app with essential drug information.

Natural Language Processing (NLP): Train models to extract drug information from text or to classify drugs based on their descriptions.

File(s):

drugs_from_a_to_z.csv (The Excel data converted to a CSV for broader compatibility)

Acknowledgements:

This dataset synthesizes information from publicly available drug monographs and prescribing information from sources including the U.S. Food and Drug Administration (FDA), Lexicomp, and Micromedex.

This data package contains complete information on all approved, marketed, canceled and dormant products for human, veterinary, disinfectant and radiopharmaceutical use in New Zealand, Germany, United Kingdom (UK) and Canada.

Information about FDA-approved brand name and generic prescription and over-the-counter human drugs and biological therapeutic products. Drugs@FDA includes most of the drug products approved since 1939. The majority of patient information, labels, approval letters, reviews, and other information are available for drug products approved since 1998.

Drug Labels and Side Effects Dataset

Dataset Overview

This comprehensive pharmaceutical synthetic dataset contains 1,393 records of synthetic drug information with 15 columns, designed for data science projects focusing on healthcare analytics, drug safety analysis, and pharmaceutical research. The dataset simulates real-world pharmaceutical data with appropriate variety and realistic constraints for machine learning applications.

Dataset Specifications

Column Specifications

Categorical Features

Numerical Features

*Intentionally stored as mixed types for data cleaning practice

Key Statistics

Manufacturer Distribution

Drug Class Distribution

Side Effect Severity

Potential Use Cases

1. Machine Learning Applications

• Drug Approval Prediction: Predict approval likelihood based on drug characteristics
• Price Prediction: Estimate drug pricing using features like class, manufacturer, dosage
• Side Effect Classification: Classify severity based on drug properties
• Market Success Analysis: Analyze factors contributing to drug market performance

2. Data Engineering Projects

• ETL Pipeline Development: Practice data cleaning and transformation
• Data Quality Assessment: Implement data validation and quality checks
• Database Design: Create normalized pharmaceutical database schema
• Real-time Processing: Stream processing for drug monitoring systems

3. Business Intelligence

• Pharmaceutical Market Analysis: Manufacturer market share and competitive analysis
• Drug Safety Analytics: Side effect patterns and safety profile analysis
• Regulatory Compliance: Approval trends and regulatory timeline analysis
• Pricing Strategy: Competitive pricing analysis across drug classes

Recommended Next Steps

1. Data Cleaning Pipeline: Implement comprehe...

THIS RESOURCE IS NO LONGER IN SERVICE. Documented on March 12,2025. The AIDSinfo Drug Database provides fact sheets on HIV/AIDS related drugs. The fact sheets describe the drug''s use, pharmacology, side effects, and other information. The database includes: -Approved and investigational HIV/AIDS related drugs -Three versions of each fact sheet: patient, health professional, and Spanish. AIDSinfo is a 100% federally funded U.S. Department of Health and Human Services (DHHS) project that offers the latest federally approved information on HIV/AIDS clinical research, treatment and prevention, and medical practice guidelines for people living with HIV/AIDS, their families and friends, health care providers, scientists, and researchers. Sponsors: -National Institutes of Health (NIH) Office of AIDS Research National Institute of Allergy and Infectious Diseases (NIAID) National Library of Medicine (NLM) -Health Resources and Services Administration (HRSA) -Centers for Disease Control and Prevention (CDC) -Centers for Medicare and Medicaid Services (CMS)

An expert-curated database of pharmacological targets with quantitative information on the prescription medicines and experimental dugs that act on them.

The Database is a research and analysis tool developed at the University of Washington, in the Department of Pharmaceutics. It contains in vitro and in vivo information on drug interactions in humans from the following sources: * 9648 peer-reviewed journal articles referenced in PubMed * 102 New Drug Applications (NDAs) * 411 excerpts of FDA Prescribing Information * In-depth analyses of drug-drug interactions in the context of 40 diseases / co-morbidities. In addition, the database also provides PK Profiles of drugs, QT Prolongation data, including results of TQT studies from recent NDAs, as well as Regulatory Guidances and Editorial Summaries/Syntheses relevant to advances in the field of drug interactions. Access to the Database is licensed by UW Center for Commercialization (C4C) to organizations interested in in-depth information on drug interactions. The Database is particularly useful to scientists/clinicians working in drug discovery and drug development. Database users can search for information using several families of pre-formulated queries based on drug name, enzyme name, transporter name, therapeutic area, and more.

Explore the dynamic Drug Reference App market, revealing key insights, growth drivers, and future trends shaping pharmaceutical information access for doctors, students, and researchers. Discover market size, CAGR, and regional shares.

Comprehensive drug information database

The public drug database allows the general public and healthcare professionals to access data and reference documents on medicinal products marketed or marketed during the last two years in France.

This administrative and scientific database on the treatment and proper use of health products is implemented by the National Agency for the Safety of Medicines and Health Products (ANSM), in liaison with the High Health Authority (HAS) and the National Union of Health Insurance Funds (UNCAM), under the aegis of the Ministry of Social Affairs and Health.

India Medicine Database

Dataset consists of 8 columns : - sub_category: This classification pertains to specific medical categories that define the domain in which the medicine finds its application. - product_name: This is the name of the product, as available in the indian market. - salt_composition: This is the chemical composition of the drug. - product_price:This represents the previous price of the product. Please consider this as a reference, as it tends to be highly volatile in relation to the health market. - product_manufactured:The pharmaceutical company responsible for producing the medicine/drug. - medicine_desc: Comprehensive overview and detailed description of the specific product. - side_effects:Potential adverse effects associated with the drug/medicine. - drug_interactions:Interactions and effects when combining this specific medicine with other drugs.

There are a few missing values in the dataset, but most information is available for the row, so I have left as is.

This dataset contains the Product part to build the Drugs@FDA database. Drugs at FDA is a database of FDA Approved Drug Products available on the FDA official website. It provides information of drug (generic) name, active ingredient, form and strength available, FDA application number, label info, dosage form or route, marketing status and pharmaceutical company as well as patient information, approval letters, review and other facts for drugs approved after 1997.

Global Essential Medicines Database

In June of 2017, we searched the WHO Essential Medicines and Health Products Information Portal, an online repository that contains hundreds of publication on medicines and health products related to WHO priorities, and a full-section dedicated to national essential medicines lists (EMLs). A WHO information specialist actively searched for updated versions of national EMLs, including national formularies, reimbursement lists, and lists based on standard treatment guidelines.

We included all national EMLs that were posted on the WHO’s NEMLs Repository irrespective of publication date and language. When we found more than one national EML from the same country, we used the most recent. We excluded documents that were not EMLs, such as prescribing guidelines. We also included the 20th edition of the WHO Model EML (2017) in this database.

From each EML we abstracted medicines using International Nonproprietary Names (INNs). For medicines whose names were not in English we used the Anatomical Therapeutic Chemical (ATC) classification system, if available, or translated the names with the help of Google Translate. We listed each medicine individually, whether it was part of a combination product or not. We treated as the same medicine bases and their salts (e.g. promethazine hydrochloride and promethazine) as well as different compounds of the same vitamin or mineral (e.g. ferrous fumarate and ferrous sulfate). We excluded diagnostic agents, antiseptics, disinfectants, and saline solutions.

In this database "1" and "0" indicate the presence or absence of the medicine respectively on an EML.

The VA Drug Pricing database contains the current prices for pharmaceuticals purchased by the federal government. These listed prices are based on the Federal Supply Schedule (FSS). This database is mandated by Public Law 102-585, the Veterans Health Care Act of 1992, which sets the maximum amount that a drug may be bought for by the Veterans Health Administration (VHA). The source of this information is contained in printed contracts or data files supplied by the drug manufacturers, representing the pricing agreements between VHA and the manufacturers. Price data is input by the National Acquisition Center (NAC) into the database administered by the Pharmacy Benefits Management Strategic Health Care Group. Information from this database is published on the World Wide Web at the following site: http://www.pbm.va.gov. The users of this database include pharmaceutical manufacturers, drug wholesalers, Office of Inspector General (OIG) and those who purchase pharmaceuticals for the VHA and other government agencies.

List showing the name of product, name of registration certificate holder, Hong Kong registration number (Permit No) and active ingredient(s) of each registered pharmaceutical product.

Psychedelic Drug Database

Psychotropic and psychedelics drugs database with molecular descriptors

By Juan Jose [source]

About this dataset

This dataset is a comprehensive database of psychotropic and psychedelic drugs, focusing on their molecular descriptors. The data was sourced from the PubChem Database, which is a widely-used resource for chemical information. The main objective of this project is to create an easily accessible and centralized database specifically for psychedelic compounds.

To achieve this, the dataset includes information on identified psychedelic compounds obtained from the PubChem Database. Additionally, molecular descriptors for these compounds were generated using the KNIME Analytics Platform and RDKit module. These molecular descriptors provide important characteristics and properties of each compound, making it easier to perform quantitative structure-activity relationship (QSAR) and quantitative structure-property relationship (QSPR) analyses.

By providing access to such data, researchers and scientists can have a valuable resource for studying psychoactive substances in a more efficient manner. This database offers consolidated and accurate information about various psychotropic drugs, aiding in research related to their effects, mechanisms of action, toxicity profiles, and potential therapeutic uses.

External resources used in this project include the PubChem Project website as well as the KNIME Analytics Platform and RDKit software tools. With these resources combined, this dataset serves as a dependable repository for both basic research purposes as well as applications in drug design or development efforts targeting psychoactive substances.

The columns within this dataset provide detailed information about each compound's molecular descriptors derived from its chemical structure. This diverse set of characteristics enables researchers to compare different compounds based on their structural features or predict certain properties using computational models.

Overall, this comprehensive psychotropic and psychedelics drugs database plays a crucial role in advancing understanding of these substances' pharmacological activities while facilitating more efficient drug discovery processes through predictive modeling approaches like QSAR/QSPR analysis

How to use the dataset

Understanding the Columns

• Compound Name: The name or identifier of each compound in the database.
• Molecular Formula: The chemical formula representing the number and types of atoms in a compound.
• Molecular Weight: The mass of a molecule, calculated as the sum of atomic weights.
• Canonical SMILES: A simplified molecular representation using standardised notation for atoms and bonds.
• Isomeric SMILES: A more specific molecular representation that includes information about stereochemistry (the spatial arrangement of atoms). 6-10. Additional columns may be included with specific molecular descriptors depending on how they were generated.

Accessing Additional Information

To delve deeper into any given compound in this database, make use of external resources such as The PubChem Project. This comprehensive resource provides additional data on each compound including chemical properties, biological activities, safety information, and much more.

Performing QSAR or QSPR Analysis

One potential application for this dataset is Quantitative Structure-Activity Relationship (QSAR) or Quantitative Structure-Property Relationship (QSPR) analysis. These approaches involve studying the relationship between a set of chemical properties (molecular descriptors) and an observed activity/property value for a set of compounds.

To perform QSAR/QSPR analysis using this dataset:

• Import these data into your preferred analytics platform such as KNIME Analytics Platform.
• Use the molecular descriptors provided in the dataset as independent variables.
• Obtain an activity/property dataset as your dependent variable (e.g., biological activity, toxicity, physical property).
• Apply appropriate machine learning or statistical modeling techniques to build a model that predicts the activity/property based on the molecular descriptors.
• Evaluate and validate your model using suitable methods (e.g., cross-validation, external test set).

Precautions and Ethical Considerations

While this database provides valuable information for research purposes, it is essential to handle psychedelic substances with caution and adhere to legal and ethical considerations.

• Leg...

The database contains information on: Pharmacies regularly provide the ZZZS with data on dispensed medicines that were prescribed on the green card prescription (to be charged to compulsory health insurance) and white (self-pay) prescription.

Saudi Arabia Drug Database (Metadata, PILs & SPCs) - AR/EN

🟢 Overview

This is a comprehensive database of registered pharmaceutical products in the Kingdom of Saudi Arabia, collected from the official public portal of the Saudi Food and Drug Authority (SFDA).

This dataset is uniquely bilingual (Arabic / English) and provides rich, structured metadata (JSON). This makes it a valuable resource for researchers, students, Natural Language Processing (NLP) specialists, and data scientists interested in the healthcare and pharmaceutical informatics sectors in the Middle East.

🔑 Key Features

• Rich Metadata: Each drug includes detailed structured data (see "Data Structure" below), such as official price, trade and generic names, legal classification, manufacturer, agent, and storage conditions.
• Bilingual (AR/EN): Provides the "Patient Information Leaflet" (PIL) in both Arabic and English, opening significant opportunities for bilingual NLP research.
• Specialized Leaflets (SPCs): Contains the "Summary of Product Characteristics" (SPC), the technical leaflet aimed at healthcare professionals, which provides in-depth technical data.
• Processor-Ready Format (JSON): The data is organized in a JSON format, making it easy to parse and process programmatically.
• Comprehensive: The vast majority of drug records contain the full set of metadata and all three associated leaflets.

🗂️ Data Structure

The dataset is provided as a single .zip archive which contains 563 individual JSON files.

• Each JSON file contains a list of 15 drug records.
• Each drug record is an object containing its metadata and the three leaflet texts.

Example Single Drug Record

Each drug record contains a Drug Data object (the metadata) and three keys for the leaflets:

json{
 "Drug Data": {
  "Registration Number": "0202256789",
  "Register Year": "2025",
  "Trade Name": "Brevie",
  "Generic Name": "BRIVARACETAM",
  "Strength": "50",
  "Strength Unit": "mg",
  "Administration Route": "Oral use",
  "Pharmaceutical Form": "Film-coated tablet",
  "Package Size": "60",
  "Packages Types": "Blister",
  "Legal Classification": "Prescription",
  "Product Control": "Uncontrolled",
  "Drug Type": "Generic",
  "ShelfLife in Months": "36",
  "Storage Conditions": "do not store above 30°c",
  "Public price (SAR)": "266.05",
  "Manufacture": "MSN LABORATORIES PRIVATE LIMITED",
  "الوكيل": "SUDAIR PHARMA COMPANY",
  "Marketing Company": "SUDAIR PHARMA COMPANY"
 },
 "Patient Information Leaflet (PIL) in English": "[...English leaflet text...]",
 "Patient Information Leaflet (PIL) in Arabic": "[...Arabic leaflet text...]",
 "Summary of Product Characteristics (SPC)": "[...Healthcare professional leaflet text...]"
}
````
## 🔗 Data Collection Code

The full code used to collect and structure this dataset is publicly available on GitHub:

👉 **[Data Collection Repository](https://github.com/MQushaym/web-scraping-data-collection)**

This repository contains the web scraping and data processing scripts used to compile and clean the dataset.


-----

## 🎯 Potential Use Cases

 * **AI Agents & RAG (Retrieval-Augmented Generation):**

   * **(Highly Recommended)** Building a specialized AI Agent (like a GPT or LLM assistant) that answers complex questions about Saudi-registered drugs.
   * This dataset acts as a perfect "Knowledge Base" for RAG. The agent can retrieve specific leaflets (PILs/SPCs) or structured metadata (like price, storage, manufacturer) to provide accurate, verifiable, and context-aware answers.
   * Developing advanced Q\&A systems for both patients ("Can I take this drug with X?") and professionals ("What are the contraindications for this drug?").

 * **Natural Language Processing (NLP):**

   * Building specialized medical terminology translation models (Ar/En).
   * Named Entity Recognition (NER) to identify side effects, active ingredients, and dosages from the leaflet texts.
   * Text summarization of the long SPC and PIL documents.

 * **Data Analysis & Health Informatics:**

   * Analyzing drug pricing in relation to manufacturers or drug type (Generic/Innovator).
   * Constructing knowledge graphs (KGs) that link drugs, ingredients, manufacturers, and legal classifications.
   * Studying storage conditions in relation to pharmaceutical forms.

-----

## 📄 License & Citation

This dataset is made available under the **CC BY-NC 4.0 (Attribution-NonCommercial 4.0)** license.

This means you are free to use it for **academic and research purposes** as long as you provide **attribution (citation)** and do not use it for commercial purposes.

When using this dataset, please cite as follows:

> **Data collected and structured by:** Meshal AL-Qushaym
> **Dataset:** KS...

Gene expression data from published journal articles that test hypotheses relevant to neuroscience of addiction and addictive behavior. Data types include effects of particular drug, strain, or knock out on particular gene, in particular anatomical region. Focuses on gene expression data and exposes data from investigations using DNA microarrays, polymerase chain reaction, immunohistochemistry and in-situ hybridizations. Data are available for query through NIF interface.Data submissions are welcome.