tydymy/150bp_human_vs_microbial_dna

---
dataset_info:
features:
- name: '#genome'
dtype: string
- name: asm_name
dtype: string
- name: assembly_accession
dtype: string
- name: bioproject
dtype: string
- name: biosample
dtype: string
- name: wgs_master
dtype: float64
- name: seq_rel_date
dtype: string
- name: submitter
dtype: string
- name: ftp_path
dtype: string
- name: img_id
dtype: float64
- name: gtdb_id
dtype: string
- name: scope
dtype: string
- name: assembly_level
dtype: string
- name: genome_rep
dtype: string
- name: refseq_category
dtype: string
- name: release_type
dtype: string
- name: taxid
dtype: float64
- name: species_taxid
dtype: float64
- name: organism_name
dtype: string
- name: infraspecific_name
dtype: string
- name: isolate
dtype: string
- name: superkingdom
dtype: string
- name: phylum
dtype: string
- name: class
dtype: string
- name: order
dtype: string
- name: family
dtype: string
- name: genus
dtype: string
- name: species
dtype: string
- name: classified
dtype: bool
- name: unique_name
dtype: string
- name: lv1_group
dtype: string
- name: lv2_group
dtype: string
- name: score_faa
dtype: float64
- name: score_fna
dtype: float64
- name: score_rrna
dtype: float64
- name: score_trna
dtype: float64
- name: total_length
dtype: float64
- name: contigs
dtype: float64
- name: gc
dtype: float64
- name: n50
dtype: float64
- name: l50
dtype: float64
- name: proteins
dtype: float64
- name: protein_length
dtype: float64
- name: coding_density
dtype: float64
- name: completeness
dtype: float64
- name: contamination
dtype: float64
- name: strain_heterogeneity
dtype: float64
- name: markers
dtype: float64
- name: 5s_rrna
dtype: string
- name: 16s_rrna
dtype: string
- name: 23s_rrna
dtype: string
- name: trnas
dtype: float64
- name: draft_quality
dtype: string
- name: start_position
dtype: int64
- name: autotrain_text
dtype: string
- name: autotrain_label
dtype:
class_label:
names:
'0': 0
'1': 1
splits:
- name: train
num_bytes: 70411052
num_examples: 100000
- name: validation
num_bytes: 3528945
num_examples: 5000
download_size: 15423840
dataset_size: 73939997
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---
# Dataset Card for "autotrain-data-human_dna_classify_150bp"

[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

原始信息汇总

数据集信息

特征

• #genome: 字符串
• asm_name: 字符串
• assembly_accession: 字符串
• bioproject: 字符串
• biosample: 字符串
• wgs_master: 浮点数
• seq_rel_date: 字符串
• submitter: 字符串
• ftp_path: 字符串
• img_id: 浮点数
• gtdb_id: 字符串
• scope: 字符串
• assembly_level: 字符串
• genome_rep: 字符串
• refseq_category: 字符串
• release_type: 字符串
• taxid: 浮点数
• species_taxid: 浮点数
• organism_name: 字符串
• infraspecific_name: 字符串
• isolate: 字符串
• superkingdom: 字符串
• phylum: 字符串
• class: 字符串
• order: 字符串
• family: 字符串
• genus: 字符串
• species: 字符串
• classified: 布尔值
• unique_name: 字符串
• lv1_group: 字符串
• lv2_group: 字符串
• score_faa: 浮点数
• score_fna: 浮点数
• score_rrna: 浮点数
• score_trna: 浮点数
• total_length: 浮点数
• contigs: 浮点数
• gc: 浮点数
• n50: 浮点数
• l50: 浮点数
• proteins: 浮点数
• protein_length: 浮点数
• coding_density: 浮点数
• completeness: 浮点数
• contamination: 浮点数
• strain_heterogeneity: 浮点数
• markers: 浮点数
• 5s_rrna: 字符串
• 16s_rrna: 字符串
• 23s_rrna: 字符串
• trnas: 浮点数
• draft_quality: 字符串
• start_position: 整数
• autotrain_text: 字符串
• autotrain_label:
  • 类别标签:
    • 0: 0
    • 1: 1

数据分割

• train:
  • 字节数: 70411052
  • 样本数: 100000
• validation:
  • 字节数: 3528945
  • 样本数: 5000

数据大小

• 下载大小: 15423840
• 数据集大小: 73939997

配置

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