QSAR Model Validation Results for Dehydrosqualene Synthase Inhibitors

Juliana Amorim published results on 2026-04-29 from a pharmacophore and QSAR screening of 299,845 natural products. The work identified 1,978 compounds with predicted Ki values of 100 nM or lower, including 47 with sub-nanomolar predicted activity. Five representative compounds showed stable binding interactions in molecular dynamics simulations, indicating potential as antivirulence leads against Staphylococcus aureus.

Use Cases

• Validate QSAR model performance based on predicted Ki values for 1,978 candidate compounds
• Identify promising lead compounds for antivirulence agents based on predicted sub-nanomolar activity
• Analyze structural features of recovered chemotypes based on the model's ability to capture scaffolds beyond its training data
• Prioritize compounds for experimental validation based on molecular dynamics simulation results showing stable interactions with key CrtM residues

Strengths

• Screens a large library of 299,845 natural products for chemical diversity
• Identifies 1,978 candidate compounds with predicted Ki values of 100 nM or lower
• Highlights 47 molecules with remarkable predicted activity below 1.0 nanomolar
• Demonstrates model validation by recovering nine chemotypes of known inhibitors not included in training

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• Data is a small 388.2 KB file, indicating limited scope and likely summary results rather than raw screening data

Provenance

Source

figshare, author Juliana Amorim

Collection Method

Pharmacophore-based screening followed by QSAR-based screening of a natural product library

Freshness

Last updated 2026-04-29 17:42:15; freshness should be verified