Kidney Toxicity Biomarker Data from In Vitro Systems Toxicology Study

Aggregating gene expression and high-content imaging data from primary human kidney cells exposed to 46 diverse toxicants. It was used to identify biomarkers for predicting nephrotoxicity and inferring mechanisms of toxicity via Random Forest machine learning and network analysis. The data includes mRNA levels of HMOX1 and SQSTM1, along with imaging features capturing cell morphology and nucleus texture changes.

Use Cases

• Train a Random Forest model using mRNA levels of HMOX1 and SQSTM1 and imaging features to predict kidney toxicity of chemical compounds.
• Perform network analysis on high-content imaging phenotypes across seven time points to infer potential mechanisms of toxicity for candidate therapeutics.
• Validate biomarker panels by testing their ability to predict toxicity for candidate therapeutics that exhibited issues in late-stage preclinical or clinical studies.

Strengths

• Includes data from 46 diverse kidney toxicants, providing a basis for predictive modeling.
• Combines multidimensional data types: gene expression (mRNA levels) and high-content imaging phenotypical data.
• Biomarkers were validated on candidate therapeutics that showed toxicity in late-stage studies.

Limitations

• The dataset is derived from an in vitro model using primary human kidney cells, which may not fully recapitulate in vivo kidney toxicity.
• Sample size is limited to 46 toxicants, which may constrain the generalizability of the predictive models.
• The temporal coverage and specific time points for the imaging data are not detailed in the provided description.

Provenance

Source

Dryad, authored by Susanne Ramm.

Collection Method

Data generated from primary human kidney cells exposed to toxicants, analyzed using systems biology approaches including Random Forest machine learning and network analysis.

Freshness

Last updated in June 2019.