50 Novel Anti-Tubercular Compounds with Computational Target Predictions

GSK's Tres Cantos Antimycobacterial Set screening identified 50 drug-like compounds prioritized from 250,000 candidates. The dataset includes computational predictions of their mechanisms of action, generated by Maria Jose Rebollo-Lopez in 2020. It is intended to support open-source tuberculosis drug discovery.

Use Cases

• Prioritize compounds for experimental validation based on their predicted mechanisms of action and physicochemical characteristics.
• Train predictive models for antitubercular activity using structural similarity data from the 50 released compounds.
• Analyze the relationship between antitubercular potency and physicochemical characteristics across the prioritized compound set.
• Validate computational biology algorithms for target prediction using the hypothesized targets for the 50 novel compounds.

Strengths

• Compounds were prioritized from a large screening effort of 250,000 compounds.
• Includes computational target predictions for 50 novel, drug-like compounds.
• Data is released under a permissive CC0 1.0 public domain license.

Limitations

• The dataset is small, containing only 50 compounds, limiting statistical power for some analyses.
• Target predictions are computational hypotheses and require experimental validation.
• No raw screening data or detailed compound structures are provided in the described metadata.

Provenance

Source

Maria Jose Rebollo-Lopez, associated with GSK's Tres Cantos Antimycobacterial Set (TCAMS-TB).

Collection Method

Compounds were identified through a screening of 250,000 compounds, prioritized by potency and physicochemical traits, with targets predicted via computational algorithms.

Freshness

Last updated in June 2020.