as-cle-bert/VirBiCla-training

---
license: mit
---

# Dataset Card for VirBiCla-training

VirBiCla is a ML-based viral DNA detector designed for long-read sequencing metagenomics.

This dataset is a support dataset for training the base ML model.

## Dataset Details

### Dataset Description

- **Curated by:** [Astra Bertelli](https://astrabert.vercel.app/)
- **License:** MIT License

### Dataset Sources [optional]

<!-- Provide the basic links for the dataset. -->

- **Repository:** [GitHub repository for VirBiCla](https://github.com/AstraBert/VirBiCla)

## Uses

This dataset is intended as support for training the base VirBiCla model

## Dataset Structure

Dataset is a CSV file composed of 60.003 record sequences (coming from RefSeq 16S bacterial rRNA, 18S fungal rRNA, SSU eukaryotic rRNA and RefSeq viral genomes) evaluated on 13 features.

Features are:

- Domain
- A, T, C and G proportion
- Percentage of A, T, C and G homopolimeric regions
- Gene density
- Entropy
- Effective Number of Codons (codon usage metrics)

## Dataset Creation

Find everything that is needed for Dataset creation on [VirBiCla website](https://astrabert.github.io/VirBiCla)

## Bias, Risks, and Limitations

The dataset is mainly directed towards amplicon-sequencing and long-read sequencing, which are the best use cases for VirBiCla.

## Citation

Please consider cite the author of this work (Astra Bertelli) and VirBiCla [GitHub repository](https://github.com/AstraBert/VirBiCla) when using this dataset or the associated model.

原始信息汇总

数据集概述

数据集名称

VirBiCla-training

数据集描述

VirBiCla-training 是一个用于训练基于机器学习的病毒DNA检测模型的支持数据集，专门设计用于长读序列元基因组学。

数据集详情

数据集描述

• 维护者： Astra Bertelli
• 许可证： MIT License

数据集来源

• 仓库： GitHub仓库

数据集用途

该数据集旨在支持训练基础的VirBiCla模型。

数据集结构

数据集为CSV格式，包含60,003条记录序列，这些序列来自RefSeq 16S细菌rRNA、18S真菌rRNA、SSU真核rRNA和RefSeq病毒基因组，评估了13个特征。

特征列表

• 域
• A, T, C 和 G 的比例
• A, T, C 和 G 同聚物区域的百分比
• 基因密度
• 熵
• 有效密码子数（密码子使用度量）

数据集创建

数据集创建所需的所有信息可在 VirBiCla网站 找到。

偏差、风险和限制

数据集主要针对扩增子测序和长读序列，这是VirBiCla的最佳使用案例。