renumics/cloome_demo

---
dataset_info:
features:
- name: SAMPLE_KEY_mol
dtype: string
- name: SAMPLE_KEY_img
dtype: string
- name: SMILES
dtype: string
- name: mol_embedding_reduced
sequence: float64
- name: img_embedding_reduced
sequence: float64
- name: mol_embedding
sequence: float32
- name: img_embedding
sequence: float32
- name: image
dtype: image
- name: distance
dtype: float64
- name: index
dtype: int64
- name: smiles_image
dtype: image
splits:
- name: train
num_bytes: 975216313.25
num_examples: 30403
download_size: 1002070493
dataset_size: 975216313.25
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---

This is a mirror to the example dataset for the "CLOOME: a new search engine unlocks bioimaging databases for queries with chemical structures" paper by Sanchez-Fernandez et al.

Paper: https://www.biorxiv.org/content/10.1101/2022.11.17.516915v1

Code: https://github.com/ml-jku/cloome


原始信息汇总

数据集详情

特征信息

• SAMPLE_KEY_mol: 字符串类型
• SAMPLE_KEY_img: 字符串类型
• SMILES: 字符串类型
• mol_embedding_reduced: 浮点数序列，类型为float64
• img_embedding_reduced: 浮点数序列，类型为float64
• mol_embedding: 浮点数序列，类型为float32
• img_embedding: 浮点数序列，类型为float32
• image: 图像类型
• distance: 浮点数类型，类型为float64
• index: 整数类型，类型为int64
• smiles_image: 图像类型

数据分割

• train: 包含30403个样本，占用975216313.25字节

数据集大小

• 下载大小: 1002070493字节
• 数据集大小: 975216313.25字节

配置信息

• config_name: default
  • data_files:
    • split: train
    • path: data/train-*