ProbioSML: 1,072 Genomic Features from Bacteria Used as Probiotics

ProbioSML is a machine learning-derived genomic dataset containing 1,072 non-redundant protein-coding sequences. It was created by Diego Lucas Neres Rodrigues through pangenomic analysis and supervised machine learning of bacterial genomes from taxa frequently reported as probiotics and reference gut-associated bacteria. The dataset, last updated in April 2026, is publicly available under a CC-BY-4.0 license.

Use Cases

• Exploratory analysis of genomic patterns associated with probiotic taxa based on the 1,072 discriminative features.
• Comparative genomics studies between probiotic and reference gut bacteria based on the gene presence-absence matrices.
• Benchmarking machine learning methods for feature extraction in genomics based on the described Random Forest, SVM, and Logistic Regression approaches.
• Functional annotation analysis of bacterial genes based on the provided annotations accompanying the protein sequences.

Strengths

• Contains 1,072 discriminative genomic features identified through supervised machine learning.
• Includes functional annotations and gene presence-absence matrices for comparative analysis.
• Publicly available with all data and scripts for reproducibility under a permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The 6.6 KB file size indicates a very limited scope, likely containing metadata or summary matrices rather than raw genomic sequences.

Provenance

Source

Diego Lucas Neres Rodrigues via figshare and Zenodo.

Collection Method

Generated from comparative pangenomic analysis combined with supervised machine learning (Random Forest, SVM, Logistic Regression).

Time Range

null

Freshness

Last updated 2026-04-22 05:46:24; freshness should be verified.

Geography

null