Expansion of DNA-Encoded Library Hits Using Generative Chemistry and Ultra-Large Compound Catalogs

AI-driven virtual screening expands DEL hits, identifying 14 compounds with IC50 values ≤ 100 μM, enhancing chemical diversity and drug-likeness.

• Why it matters: Limited chemical space coverage and drug-likeness in DNA-encoded libraries hinder efficient hit expansion, restricting drug discovery progress.
• What they did: Researchers integrated validated DEL data with generative AI to explore and expand chemical space, screening ultra-large libraries and identifying purchasable, diverse compounds.
• The result: The approach yielded novel, commercially available hits with improved drug-like properties, demonstrating a rapid, scalable platform for hit expansion in drug discovery.