Serum Metabolomics for Intrinsic and Idiosyncratic Drug-Induced Liver Injury Biomarkers

Supplementary file 4_Machine learning-assisted analysis of serum metabolomics for identifying biomarkers in intrinsic and idiosyncratic drug-induced liver injury.docx is a 12.9 KB dataset by Xianni Wei, last updated on 2026-03-18. It contains metabolomic profiling results from 44 DILI cases (17 intrinsic, 27 idiosyncratic) analyzed via HP-CIL LC-MS and machine learning. The study identified four differential metabolites and developed diagnostic models with AUC values up to 0.983.

Use Cases

• Train machine learning models to classify intrinsic vs. idiosyncratic DILI based on identified serum metabolite levels.
• Validate potential biomarkers like Alanyl-Glycine and N2-Acetyl-L-Cystathionine for clinical diagnostic applications.
• Analyze metabolic pathway disruptions in amino acid metabolism related to drug-induced liver injury mechanisms.
• Compare the performance of different statistical and machine learning models for metabolomic biomarker selection.

Strengths

• Includes data from 44 clinically classified DILI cases (17 intrinsic, 27 idiosyncratic).
• Machine learning models demonstrated high diagnostic performance, with reported AUC values greater than 0.8 and up to 0.983.
• Identifies four specific differential metabolites with associated confidence levels (e.g., level 1, level 2a).

Limitations

• Row count and column-level documentation are absent; field semantics must be inferred after download.
• The dataset is very small at 12.9 KB, indicating limited scope, likely containing summary results rather than raw data.
• Description metadata is limited; actual data quality and structure require manual inspection after download.

Provenance

Source

Xianni Wei via figshare.

Collection Method

Metabolomic profiling using high-performance chemical isotope labeling liquid chromatography–mass spectrometry (HP-CIL LC-MS) on serum samples from clinically diagnosed DILI patients.

Freshness

Last updated 2026-03-18 07:36:43; freshness should be verified.