Salivary Microbiota Meta-Analysis for Multi-Disease Prediction

A meta-analysis of 16S saliva data from 22 cohorts comprising 7,750 samples collected between 2016 and 2024. Bioinformatics analyses identified nine core microbiota and constructed random forest models for disease prediction. The dataset was created by Qixiang Yuan and published on figshare.

Use Cases

• Training multi-class random forest models for disease prediction based on 16S microbiota data.
• Identifying core microbial taxa in healthy saliva samples based on the negative control group analysis.
• Comparing microbiota structure across physiological and pathological states at the genus level.
• Establishing healthy baseline profiles for saliva microbiota to serve as a reference for disease studies.

Strengths

• Includes 7,750 samples from 22 cohorts.
• Models achieved AUC scores ranging from 0.898 to 1.000.
• Identified nine specific core microbiota, such as g:Streptococcus.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect temporal bias inherent to the PubMed source (2016–2024).

Provenance

Source

figshare

Collection Method

Meta-analysis of public 16S saliva data from PubMed.

Time Range

2016–2024

Freshness

Last updated 2026-04-15 05:46:09; freshness should be verified.