msb-roshan/BACE
收藏资源简介:
--- dataset_info: features: - name: Class dtype: int64 - name: SMILES dtype: string splits: - name: random_0_train num_bytes: 92020 num_examples: 1211 - name: random_0_val num_bytes: 11731 num_examples: 151 - name: random_0_test num_bytes: 11591 num_examples: 151 - name: random_1_train num_bytes: 92170 num_examples: 1211 - name: random_1_val num_bytes: 11363 num_examples: 151 - name: random_1_test num_bytes: 11809 num_examples: 151 - name: random_2_train num_bytes: 92139 num_examples: 1211 - name: random_2_val num_bytes: 11591 num_examples: 151 - name: random_2_test num_bytes: 11612 num_examples: 151 - name: random_3_train num_bytes: 92406 num_examples: 1211 - name: random_3_val num_bytes: 11438 num_examples: 151 - name: random_3_test num_bytes: 11498 num_examples: 151 - name: random_4_train num_bytes: 92423 num_examples: 1211 - name: random_4_val num_bytes: 11374 num_examples: 151 - name: random_4_test num_bytes: 11545 num_examples: 151 - name: scaffold_0_train num_bytes: 92069 num_examples: 1210 - name: scaffold_0_val num_bytes: 11780 num_examples: 151 - name: scaffold_0_test num_bytes: 11493 num_examples: 152 - name: scaffold_1_train num_bytes: 93055 num_examples: 1210 - name: scaffold_1_val num_bytes: 11452 num_examples: 151 - name: scaffold_1_test num_bytes: 10835 num_examples: 152 - name: scaffold_2_train num_bytes: 92145 num_examples: 1210 - name: scaffold_2_val num_bytes: 12240 num_examples: 151 - name: scaffold_2_test num_bytes: 10957 num_examples: 152 - name: scaffold_3_train num_bytes: 92634 num_examples: 1210 - name: scaffold_3_val num_bytes: 11274 num_examples: 151 - name: scaffold_3_test num_bytes: 11434 num_examples: 152 - name: scaffold_4_train num_bytes: 92725 num_examples: 1210 - name: scaffold_4_val num_bytes: 10982 num_examples: 151 - name: scaffold_4_test num_bytes: 11635 num_examples: 152 download_size: 418827 dataset_size: 1153420 --- # Dataset Card for "BACE" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
数据集概述
特征信息
- Class:分类标签,数据类型为
int64。 - SMILES:化学结构的字符串表示,数据类型为
string。
数据分割详情
- 随机分割:
- 训练集:共5个,每个包含1211个样本。
- 验证集:共5个,每个包含151个样本。
- 测试集:共5个,每个包含151个样本。
- 基于骨架的分割:
- 训练集:共5个,每个包含1210个样本。
- 验证集:共5个,每个包含151个样本。
- 测试集:共5个,每个包含152个样本。
数据集大小
- 下载大小:418827字节。
- 数据集总大小:1153420字节。



