research data . Audiovisual . 2018

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

Gómez-Bombarelli, Rafael; Wei, Jennifer N.; Duvenaud, David; Hernández-Lobato, José Miguel; Sánchez-Lengeling, Benjamín; Sheberla, Dennis; Aguilera-Iparraguirre, Jorge; Hirzel, Timothy D.; Adams, Ryan P.; Aspuru-Guzik, Alán;
  • Published: 01 Jan 2018
  • Publisher: Figshare
We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder, and a predictor. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predict...
free text keywords: Biophysics, Biochemistry, Pharmacology, Biotechnology, Evolutionary Biology, Immunology, Space Science, Continuous representations, Automatic Chemical Design, chemical structures, vector, molecule, predictor estimates chemical properties, novel chemical structures, 69999 Biological Sciences not elsewhere classified, 39999 Chemical Sciences not elsewhere classified, 80699 Information Systems not elsewhere classified
Download from
Audiovisual . 2018
Provider: figshare
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue