scikit-fingerprints/ExpansionRx_OpenADMET_MBPB

---
license: cc-by-4.0
task_categories:
- tabular-regression
- graph-ml
- text-classification
tags:
- chemistry
- biology
- medical
pretty_name: ExpansionRx-OpenADMET MBPB
size_categories:
- 1K<n<10K
configs:
- config_name: default
data_files:
- split: train
path: "mbpb.csv"
---
# ExpansionRx-OpenADMET MBPB

MBPB dataset from the ExpansionRx-OpenADMET Blind Challenge [[1]](#1) [[2]](#2). It is intended to be used through
[scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints) library.

The task is to predict MBPB of molecules.

| **Characteristic** | **Description** |
|:------------------:|:-----------------:|
| Tasks | 1 |
| Task type | regression |
| Total samples | 1426 |
| Recommended split | time |
| Recommended metric | MAE |

## References
<a id="1">[1]</a>
OpenADMET team
"Announcement 1: ExpansionRx-OpenADMET Blind Challenge"
https://openadmet.ghost.io/expansionrx-openadmet-blind-challenge/

<a id="2">[2]</a>
HuggingFace Hub - ExpansionRx-OpenADMET challenge full dataset
https://huggingface.co/datasets/openadmet/openadmet-expansionrx-challenge-data

---
许可证: cc-by-4.0
任务类别:
- 表格回归（tabular-regression）
- 图机器学习（graph-ml）
- 文本分类（text-classification）
标签:
- 化学
- 生物学
- 医学
展示名称: ExpansionRx-OpenADMET MBPB
样本量区间:
- 1000 < 样本数 < 10000
配置项:
- 配置名称: 默认（default）
数据文件:
- 划分集: 训练集（train）
路径: "mbpb.csv"
---

# ExpansionRx-OpenADMET MBPB

本数据集源自ExpansionRx-OpenADMET盲测挑战赛[[1]](#1)[[2]](#2)，推荐通过[scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints)库进行使用。

本数据集的任务为预测分子的MBPB值。

| **特征** | **描述** |
|:-------:|:-------:|
| 任务数 | 1 |
| 任务类型 | 回归 |
| 总样本数 | 1426 |
| 推荐划分方式 | 时间划分 |
| 推荐评估指标 | 平均绝对误差（MAE） |

## 参考文献
<a id="1">[1]</a>
OpenADMET团队
"公告1: ExpansionRx-OpenADMET盲测挑战赛"
https://openadmet.ghost.io/expansionrx-openadmet-blind-challenge/

<a id="2">[2]</a>
HuggingFace Hub——ExpansionRx-OpenADMET挑战赛完整数据集
https://huggingface.co/datasets/openadmet/openadmet-expansionrx-challenge-data