datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
UCI_druggeom_drugs
GEOM: Molecular Conformations (Drugs Subset)
Note: This is a mirrored and specifically preprocessed version of the GEOM dataset (Drugs subset), originally created by Simon Axelrod and Rafael Gómez-Bombarelli. All credit for the original conformational sampling and DFT calculations goes to the original authors. This repository exists to guarantee availability and exact reproducibility for downstream machine learning projects.
Dataset Description
The Geometric Ensemble… See the full description on the dataset page: https://huggingface.co/datasets/raulsofia/geom_drugs.drug-reviewsDrugbankVocabularyChEMBL_Drug_Instruction_Tuning
Dataset Card for ChEMBL Drug Instruction Tuning
Dataset Summary
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
Supported Tasks and Leaderboards
[More Information Needed]
Languages
[More Information Needed]
Dataset Structure
Data Instances
[More Information Needed]
Data Fields
[More Information Needed]
Data Splits
[More Information Needed]… See the full description on the dataset page: https://huggingface.co/datasets/alxfgh/ChEMBL_Drug_Instruction_Tuning.drug-use-corpus
Drug Use Corpus (Spanish)
Binary classification dataset for drug use detection in Spanish tweets
Drug Use Corpus (Spanish)
This dataset contains Spanish-language tweets related to drug use, specifically focusing on references to marijuana, cocaine, and other substances. The dataset is designed for binary classification tasks in the context of substance use detection in social media discussions.
Dataset Description
The Drug Use Corpus consists of 3,000… See the full description on the dataset page: https://huggingface.co/datasets/lhbelfanti/drug-use-corpus.fda-faers-drug-adverse-events
FDA FAERS Drug Adverse Events 2023
One-time dated snapshot.
Reconciled 2023 FAERS extract with 1,541,888 retained cases and seven related tables; supplied 2023 deletion lists applied.
Verified coverage: 2023 Q1–Q4.
Records: 1,541,888 case rows; seven related tables.
This repository contains a 1,000-row public sample, not the full package. A sample does not establish complete historical coverage.
Limitations
Historical 2023 Q1–Q4 quarterly-extract cohort, not a… See the full description on the dataset page: https://huggingface.co/datasets/claritystorm/fda-faers-drug-adverse-events.PubChem_Drug_Instruction_TuningCollection-of-drug-names-in-Persian
Dataset Details
A collection of drug names in Persian
Language(s) (NLP): persian
cyber_drug_dataset
Digital Forensic Investigation Scenario Dataset: Online Drug Trafficking
This dataset is a comprehensive collection of digital artifacts and investigative reports designed for forensic research and education. It simulates a sophisticated Online Drug Trafficking scenario, covering the entire investigation lifecycle from initial intelligence gathering to suspect arrest and financial analysis.
Dataset Structure
The dataset is indexed via a standardized 7-column metadata… See the full description on the dataset page: https://huggingface.co/datasets/K-University-AIED/cyber_drug_dataset.drug_combocima-drug-interactions-es
CIMA Spanish Drug-Drug Interactions Dataset (GALENO IA)
This dataset is the first open-source, structured database of cross drug-drug interactions in Spanish, extracted directly from the official Summary of Product Characteristics (SmPC) sheets of the Spanish Agency for Medicines and Health Products (AEMPS) via their public CIMA Online Medicines Information Center API and structured using the gemma-4-31B-it large language model.
Originally developed as a core clinical decision… See the full description on the dataset page: https://huggingface.co/datasets/lmolino/cima-drug-interactions-es.drugage-lifespan-benchmark
DrugAge Lifespan-Extension Benchmark
Predict the maximum reported percentage change in lifespan for a small molecule, from
structure alone. 754 compounds curated from DrugAge
(Human Ageing Genomic Resources), which aggregates measured lifespan experiments across
C. elegans, Drosophila, mouse and yeast.
Geroscience is missing from ML drug-discovery benchmarking. Public benchmarks are potency,
ADME and tox; none of them asks whether a molecule extends lifespan. This fills that gap… See the full description on the dataset page: https://huggingface.co/datasets/Dinesh4311/drugage-lifespan-benchmark.Drug_Combination_Extractionalgerian-drug-nomenclature
🇩🇿 Algerian Drug Nomenclature — Nomenclature Nationale des Médicaments
A clean, structured, PII-free reference dataset of pharmaceutical products authorised for the Algerian market, derived from the official Nomenclature Nationale des Médicaments (Ministère de la Santé, Algeria).
This is reference product data — registration numbers, INNs, brand names, dosages, manufacturers, and reimbursement status. It contains no personal, patient, or transactional data of any kind.… See the full description on the dataset page: https://huggingface.co/datasets/tkawen/algerian-drug-nomenclature.drug-use-raw-tweets
Drug Use Raw Tweets
Full pool of tweets collected via GoXCrap and
Corpus Creator for the
drug-use-corpus project. This is the raw,
uncategorized collection: none of these tweets have been manually labeled as Positive/Negative for
drug-use content. It is published so other researchers can continue the manual categorization process,
extend it to other substances, or use it as a source pool for related tasks.
drug-use-corpus (the labeled EPB corpus used to train the models in this… See the full description on the dataset page: https://huggingface.co/datasets/lhbelfanti/drug-use-raw-tweets.drug-comb-dataclinical-drift-based-drug-similarity-substitution-mapping-v0.1What this dataset tests
Drug similarity based on systemic drift fingerprintsnot target class.
Required outputs
drift similarity score
shared drift axes
critical difference axes
substitution recommendation class
rationale trace
monitoring plan
Recommendation classes
preferred substitute
conditional substitute
complement not substitute
do not substitute
avoid in frail profiles
Use case
Third layer of the Drug-Induced System Drift Library.
drug-reviews-final-datasetnadac-national-average-drug-acquisition-cost-2024
NADAC (National Average Drug Acquisition Cost) 2024
Description
National Average Drug Acquisition Cost (NADAC) weekly reference data for the calendar year.
Dataset Details
Publisher: Centers for Medicare & Medicaid Services
Last Modified: 2024-12-23
Contact: Medicaid.gov (Medicaid.gov@cms.hhs.gov)
Source
Original data can be found at: https://healthdata.gov/d/3tha-57c6
Usage
You can load this dataset using:
from datasets import… See the full description on the dataset page: https://huggingface.co/datasets/HHS-Official/nadac-national-average-drug-acquisition-cost-2024.DrugLinksAfrica_Pharmacovigilance_Adverse_Drug_Reactions
Africa Pharmacovigilance Adverse Drug Reactions Dataset
A curated, structured dataset of 71 detailed adverse drug reaction (ADR) reports across 26 African countries, addressing a critical gap in pharmacovigilance data representation for African populations in global drug safety research.
🌍 Why This Dataset Matters
Most pharmacovigilance datasets are dominated by Western populations, leaving a significant gap in understanding drug safety profiles for African patients —… See the full description on the dataset page: https://huggingface.co/datasets/Oduwo/Africa_Pharmacovigilance_Adverse_Drug_Reactions.Drug_QADrugFormDB
DrugFormDB: A Dataset for Medication Form Classification
Dataset Description
DrugFormDB is a comprehensive dataset containing medication form classifications for approved drugs. The dataset was created using a two-stage classification system:
Initial classification using GPT-4
Validation using PubMedBERT embeddings
Key Features
3,150+ Drug Classifications: Covers a wide range of approved medications
Multiple Forms per Drug: Many drugs are available in… See the full description on the dataset page: https://huggingface.co/datasets/ahruf/DrugFormDB.DrugFormDB
DrugFormDB: A Dataset for Medication Form Classification
Dataset Description
DrugFormDB is a comprehensive dataset containing medication form classifications for approved drugs. The dataset was created using a two-stage classification system:
Initial classification using GPT-4
Validation using PubMedBERT embeddings
Key Features
3,150+ Drug Classifications: Covers a wide range of approved medications
Multiple Forms per Drug: Many drugs are available in… See the full description on the dataset page: https://huggingface.co/datasets/VidyaGude/DrugFormDB.africa-synth-hiv-treatment-cascade-drug-all
Africa Synth Hiv Treatment Cascade Drug All | Africa (Electric Sheep Africa metadata inventory)
Size category: 10K<n<100K - Formats: csv - Sector: health - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Health datasets… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-synth-hiv-treatment-cascade-drug-all.Collection-of-drug-names-in-Persian
Dataset Details
A collection of drug names in Persian
Language(s) (NLP): persian
clinical-5node-ddi-buf-lag-cpl-drug-interaction-toxicity-v0.1
What this repo does
This dataset models a drug interaction toxicity cascade by measuring when drug interaction pressure rises, physiologic buffer capacity erodes, clinical response lags, and care-team coupling tightens across prescribers, crossing a phase transition into an unrecoverable toxicity cascade state.
Core quad
ddibuflagcpl
Prediction target
label_cascade_state
Row structure
One row represents a clinical medication-risk scenario with… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-5node-ddi-buf-lag-cpl-drug-interaction-toxicity-v0.1.clinical-drug-toxicity-instability-v0.1
clinical-drug-toxicity-instability-v0.1
What this dataset does
This dataset evaluates whether models can detect instability caused by pharmacological load exceeding clearance capacity.
Each row represents a simplified drug metabolism scenario observed across three time points.
The task is to determine whether pharmacological regulation remains stable or is moving toward toxic instability.
Core stability idea
Drug toxicity occurs when drug accumulation exceeds… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-drug-toxicity-instability-v0.1.Drugbank_Summary_Drug_Sequence