Gut Microbiome Functional Pathways for Predicting ICI Response in NSCLC

Feifei Wei's dataset contains gut microbiome profiles from 77 Japanese patients with non-small cell lung cancer receiving immune checkpoint inhibitors. It compares taxonomic versus functional features for predicting clinical outcomes, including treatment response and survival. The data was last updated on 2026-05-15.

Use Cases

• Predicting immune checkpoint inhibitor treatment response based on MetaCyc pathway features.
• Comparing the predictive power of taxonomic versus functional microbiome profiles for clinical outcomes.
• Developing interpretable machine learning models using SHAP analysis on microbial metabolic pathways.
• Investigating the role of specific pathways like nitrogen metabolism and short-chain fatty acid biosynthesis in patient response.

Strengths

• Includes data from 77 patient samples, providing a defined cohort size.
• Compares six distinct feature sets (three taxonomic, three functional) for analysis.
• Model development includes nested internal and external validation for robustness.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is small at 103.3 KB, indicating limited scope.

Provenance

Source

Feifei Wei via figshare.

Collection Method

Pretreatment fecal samples from patients profiled using 16S rRNA sequencing.

Freshness

Last updated 2026-05-15 04:21:48; freshness should be verified.

Geography

Japan.