Theoretical and Computational Chemistry

Comparison Between SMILES-Based Differential Neural Computer and Recurrent Neural Network Architectures for De Novo Molecule Design


In recent years, deep learning for de novo molecular generation has become a rapidly growing research area. Recurrent neural networks (RNN) using the SMILES molecular representation is one of the most common approaches used. Recent study shows that the differentiable neural computer (DNC) can make considerable improvement over the RNN for modeling of sequential data. In the current study, DNC has been implemented as an extension to REINVENT, an RNN-based model that has already been used successfully to make de novo molecular design. The model was benchmarked on its capacity to learn the SMILES language on the GDB-13 and MOSES datasets. The DNC shows improvement on all test cases conducted at the cost of significantly increased computational time and memory consumption.


Thumbnail image of dnc_manuscript_for_publication.pdf
download asset dnc_manuscript_for_publication.pdf 0.42 MB [opens in a new tab]

Supplementary material

Thumbnail image of dnc_manuscript_for_publication.docx
download asset dnc_manuscript_for_publication.docx 0.22 MB [opens in a new tab]
dnc manuscript for publication

Supplementary weblinks