jjingliu/approved_drug_target

---
license: cc-by-nc-4.0
task_categories:
- text-generation
language:
- en
tags:
- chemistry
- biology
- medical
pretty_name: approved_drug_target
size_categories:
- 10K<n<100K
configs:
- config_name: approved_drug_target
data_files:
- split: train
path: approved_drug_target.json
- config_name: uniprot_sequence
data_files:
- split: uniprot_seq
path: uniprotId_sequence_2024_11_01.json
---
# Approved Drug SMILES and Protein Sequence Dataset

This dataset provides a curated collection of approved drug Simplified Molecular Input Line Entry System (SMILES) strings and their associated protein sequences. Each small molecule has been approved by at least one regulatory body, ensuring the safety and relevance of the data for computational applications. The dataset includes 1,660 approved small molecules and their 2,093 related protein targets.

# Dataset

The data comes from the following sources:

- DrugBank
- UniProt
- ChEMBL
- ZINC20

# Data verification and processing
A total of 1,710 approved small molecules were retrieved from the DrugBank database, 117 of which were labeled as withdrawn. After assessment by a physician (Ali Motahharynia) and a pharmacist (Mahsa Sheikholeslami), 50 withdrawn drugs were excluded due to safety concerns, resulting in 1,660 approved small molecules. 2,116 protein targets were associated with these drugs, but 27 proteins were missing or unverified in UniProt database. These were manually replaced or verified using UniProt IDs, identical protein names, or Basic Local Alignment Search Tool (BLAST) for alignment matching, ultimately leading to 2,093 verified protein targets. Protein with UniProt ID “Q5JXX5” was deleted from the UniProt database and was therefore excluded from the dataset.

# Data structure
- SMILES: Contains the SMILES strings for each of the approved molecules. These SMILES were retrieved from DrugBank, ChEMBL, and ZINC20 databases.
- Sequences: Contains protein sequences retrieved from UniProt database.

# You can load this dataset with:
```python
from datasets import load_dataset

dataset = load_dataset("alimotahharynia/approved_drug_target", "approved_drug_target")
```
You can also download the dataset directly in JSON format.

# Citation
If you use this dataset in your research, please cite our paper:
```
Sheikholeslami, M., Mazrouei, N., Gheisari, Y., Fasihi, A., Irajpour, M., & Motahharynia, A*.
DrugGen enhances drug discovery with large language models and reinforcement learning.
Sci Rep 15, 13445 (2025). https://doi.org/10.1038/s41598-025-98629-1
```