jirvine/plsdb_and_doric_replicon_split

该数据集包含与细菌复制起点（OriC）相关的序列信息，涵盖了多个特征如序列ID、质粒ID、物种、来源、蛋白质家族ID、复制蛋白ID、复制类型、复制蛋白序列、DNA序列、完整复制子序列等。数据集分为训练集和验证集，分别包含17944和7833个样本。总下载大小为26950070字节，数据集总大小为116919890字节。

This dataset contains sequence information related to bacterial replication origins (OriC), including features such as sequence ID, plasmid ID, species, source, protein family ID, replication protein ID, replication type, replication protein sequence, DNA sequence, full replicon sequence, etc. The dataset is divided into training and validation sets, containing 17,944 and 7,833 samples respectively. The total download size is 26,950,070 bytes, and the total dataset size is 116,919,890 bytes.

原始信息汇总

数据集概述

数据集信息

特征

• OriC sequence: 类型为字符串
• ori_id: 类型为字符串
• plasmid_id: 类型为字符串
• species: 类型为字符串
• source: 类型为字符串
• pfamid_fast: 类型为字符串
• rep_id: 类型为字符串
• Rep_type_fast: 类型为字符串
• rep_seq: 类型为字符串
• rep_dna_seq: 类型为字符串
• full_replicon_seq: 类型为字符串
• split: 类型为字符串
• index_level_0: 类型为int64

数据分割

• train: 包含17944个样本，占用82043973字节
• validation: 包含7833个样本，占用34875917字节

数据集大小

• 下载大小: 26950070字节
• 数据集总大小: 116919890字节

配置

• config_name: default
  • 数据文件:
    • train: 路径为data/train-*
    • validation: 路径为data/validation-*