pvrancx/tyk2_fep

---
license: apache-2.0
dataset_info:
features:
- name: Smiles
dtype: string
- name: DockingScore
dtype: float64
- name: dG
dtype: float64
- name: dGError
dtype: float64
splits:
- name: train
num_bytes: 641714
num_examples: 8997
- name: test
num_bytes: 71163
num_examples: 1000
download_size: 315048
dataset_size: 712877
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
tags:
- molecule
- chemistry
- smiles
- free_energy
size_categories:
- 1K<n<10K
---

Molecular dataset: 10,000 TYK2 inhibitors (SMILES strings) with Docking scores and Relative Binding Free Energy (dG)

Dataset from paper:

James Thompson, W Patrick Walters, Jianwen A Feng, Nicolas A Pabon, Hongcheng Xu, Michael Maser, Brian B Goldman, Demetri Moustakas, Molly Schmidt, Forrest York,
Optimizing active learning for free energy calculations, Artificial Intelligence in the Life Sciences, Volume 2, 2022, 100050, ISSN 2667-3185,
https://doi.org/10.1016/j.ailsci.2022.100050.

https://www.sciencedirect.com/science/article/pii/S2667318522000204

original source: https://github.com/google-research/google-research/tree/master/al_for_fep

原始信息汇总

数据集概述

数据集信息

• 特征:

  • Smiles: 数据类型为字符串。
  • DockingScore: 数据类型为浮点数（float64）。
  • dG: 数据类型为浮点数（float64）。
  • dGError: 数据类型为浮点数（float64）。

• 数据分割:

  • 训练集:
    • 字节数: 641714
    • 样本数: 8997
  • 测试集:
    • 字节数: 71163
    • 样本数: 1000

• 数据大小:

  • 下载大小: 315048
  • 数据集大小: 712877

配置

• 默认配置:
  • 训练集路径: data/train-*
  • 测试集路径: data/test-*

标签

• molecule
• chemistry
• smiles
• free_energy

数据集规模

• 1K<n<10K