NViR: Non-Invasive Viability Estimates for Liver Spheroids Under Drug Exposure

Daniel Dubinsky developed Neural Viability Regression (NViR), a deep learning method for non-invasive viability quantification from microscopy images. The dataset likely contains viability estimates for human liver spheroids exposed to 108 FDA-approved drugs, used to predict Drug-Induced Liver Injury (DILI). The data was published on figshare under a CC-BY-4.0 license in April 2026.

Use Cases

• Predict Drug-Induced Liver Injury (DILI) based on non-invasive viability estimates from microscopy images
• Analyze temporal changes in cell viability during drug exposure experiments
• Benchmark deep learning models for non-invasive cell viability quantification
• Assess the cost-effectiveness of non-destructive viability assays in drug development

Strengths

• Focuses on 108 FDA-approved drugs, providing a relevant test set for pharmaceutical research
• Method enables high-frequency viability assessments, capturing subtle temporal changes
• Published under a CC-BY-4.0 license, facilitating open reuse

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 very small (10.9 KB), indicating limited scope

Provenance

Source

figshare

Collection Method

Viability estimates generated via the Neural Viability Regression (NViR) deep learning method applied to microscopy images of liver spheroids.

Freshness

Last updated 2026-04-09 05:20:09