Folding@home COVID-19 Datasets: Molecular Simulations of SARS-CoV-2

Folding@home, a massively distributed computing project, generated the world's first exascale distributed computing resource to create these datasets. The repository comprises the single largest collection of molecular simulation data ever released, focusing on understanding vulnerabilities in SARS-CoV-2. It is shared publicly through the AWS Open Data Registry and the MolSSI COVID 19 Molecular Structure and Therapeutics Hub.

Use Cases

• Train ML models for protein-ligand interaction prediction based on biomolecular simulation data.
• Analyze molecular dynamics trajectories to identify potential drug targets based on simulated protein structures.
• Conduct alchemical free energy calculations for drug candidate screening based on simulation outputs.

Strengths

• Data generated by the world's first exascale distributed computing resource, enabling unprecedented scale.
• Datasets are the single largest collection of molecular simulation data ever released.
• Data is shared under a CC0-1.0 license, allowing for broad reuse and analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.
• Row count and file formats are unknown, which may limit suitability assessment.

Provenance

Source

Folding@home Consortium

Collection Method

Generated via massively distributed biomolecular simulations.

Time Range

null

Freshness

null

Geography

null