Pre-computed Reference Features for 25 Human Microbiome Bacterial Species

Pre-computed reference features for 25 bacterial species spanning 14 genera commonly found in the human microbiome. The dataset was authored by Liang and is available under an MIT license. It was last updated on April 26, 2026.

Use Cases

• Training machine learning models for bacterial species classification based on pre-computed features.
• Developing reference databases for comparative metagenomic studies of the human microbiome.
• Benchmarking feature extraction and selection algorithms for microbial genomics.

Strengths

• Covers 25 bacterial species from 14 genera, providing a focused taxonomic scope.
• The dataset is 275.9 MB in size, indicating a medium-scale feature set.
• Released under a permissive MIT license, facilitating open use and redistribution.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for specific modeling tasks.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Pre-computed from unspecified source data.

Freshness

Last updated 2026-04-26 03:29:32; freshness should be verified.