AhR Agonists in Elbe River Sediments Identified via Machine Learning

Chemical and bioactivity data from a study combining high-resolution fractionation with machine learning to identify aryl hydrocarbon receptor (AhR) agonists in sediment from the Elbe River, Germany. The dataset includes 145 AhR-active features identified by GC-HRMS and machine learning models, with 26 chemicals bioanalytically and chemically confirmed. It was authored by Haotian Wang and last updated on May 12, 2026.

Use Cases

• Training models to predict AhR activation based on chemical features from GC-HRMS data.
• Benchmarking virtual fractionation techniques against traditional bioanalytical confirmation methods.
• Analyzing the contribution of polycyclic aromatic hydrocarbons (PAHs) and other tentatively identified chemicals to overall mixture effects in sediments.

Strengths

• Includes 26 bioanalytically and chemically confirmed AhR-active chemicals.
• Provides semiquantified concentrations and estimated potencies for tentatively identified agonists.
• The described method doubled the contribution of known US EPA priority PAHs to the explained AhR activation (from less than 10% to 14-47%).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is specific to a proof-of-concept study on sediment from the Elbe River, Germany.

Provenance

Source

figshare

Collection Method

Combined high-resolution fractionation with machine-learning-driven virtual fractionation and analysis by gas chromatography coupled with high-resolution mass spectrometry (GC-HRMS).

Freshness

Last updated 2026-05-12 00:04:03

Geography

Elbe River, Germany