@Article{OliveiraSilvQuil:2022:MoPrPr,
               author = "Oliveira, Andr{\'e} Freitas and Silva, Juarez L. F. da and 
                         Quiles, Marcos G.",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and 
                         {Universidade de S{\~a}o Paulo (USP)} and {Universidade Federal 
                         de S{\~a}o Paulo (UNIFESP)}",
                title = "Molecular Property Prediction and Molecular Design Using a 
                         Supervised Grammar Variational Autoencoder",
              journal = "Journal of Chemical Information and Modeling",
                 year = "2022",
               volume = "62",
                pages = "817--828",
             abstract = "Some of the most common applications of machine learning (ML) 
                         algorithms dealing with small molecules usually fall within two 
                         distinct domains, namely, the prediction of molecular properties 
                         and the design of novel molecules with some desirable property. 
                         Here we unite these applications under a single molecular 
                         representation and ML algorithm by modifying the grammar 
                         variational autoencoder (GVAE) model with the incorporation of 
                         property information into its training procedure, thus creating a 
                         supervised GVAE (SGVAE). Results indicate that the biased latent 
                         space generated by this approach can successfully be used to 
                         predict the molecular properties of the input molecules, produce 
                         novel and unique molecules with some desired property and also 
                         estimate the properties of random sampled molecules. We illustrate 
                         these possibilities by sampling novel molecules from the latent 
                         space with specific values of the lowest unoccupied molecular 
                         orbital (LUMO) energy after training the model using the QM9 data 
                         set. Furthermore, the trained model is also used to predict the 
                         properties of a hold-out set and the resulting mean absolute error 
                         (MAE) shows values close to chemical accuracy for the dipole 
                         moment and atomization energies, even outperforming ML models 
                         designed to exclusive predict molecular properties using the 
                         SMILES as molecular representation. Therefore, these results show 
                         that the proposed approach is a viable way to provide generative 
                         ML models with molecular property information in a way that the 
                         generation of novel molecules is likely to achieve better results, 
                         with the benefit that these new molecules can also have their 
                         molecular properties accurately predicted.",
                  doi = "10.1021/acs.jcim.1c01573",
                  url = "http://dx.doi.org/10.1021/acs.jcim.1c01573",
                 issn = "1549-9596",
             language = "en",
           targetfile = "Oliveira_2022_Molecular.pdf",
        urlaccessdate = "25 jun. 2024"
}