A Turing Test for Molecular Generators.

Autor: Bush JT; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Pogany P; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Pickett SD; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Barker M; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Baxter A; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Campos S; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Cooper AWJ; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Hirst D; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Inglis G; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Nadin A; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Patel VK; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Poole D; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Pritchard J; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Washio Y; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., White G; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K., Green DVS; GSK Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K.
Jazyk: angličtina
Zdroj: Journal of medicinal chemistry [J Med Chem] 2020 Oct 22; Vol. 63 (20), pp. 11964-11971. Date of Electronic Publication: 2020 Oct 12.
DOI: 10.1021/acs.jmedchem.0c01148
Abstrakt: Machine learning approaches promise to accelerate and improve success rates in medicinal chemistry programs by more effectively leveraging available data to guide a molecular design. A key step of an automated computational design algorithm is molecule generation, where the machine is required to design high-quality, drug-like molecules within the appropriate chemical space. Many algorithms have been proposed for molecular generation; however, a challenge is how to assess the validity of the resulting molecules. Here, we report three Turing-inspired tests designed to evaluate the performance of molecular generators. Profound differences were observed between the performance of molecule generators in these tests, highlighting the importance of selection of the appropriate design algorithms for specific circumstances. One molecule generator, based on match molecular pairs, performed excellently against all tests and thus provides a valuable component for machine-driven medicinal chemistry design workflows.
Databáze: MEDLINE
Externí odkaz: