Scaffold-based molecular design with a graph generative model

Abstract

Searching new molecules in areas like drug discovery often starts from the core structures of candidate molecules to optimize the properties of interest. The way as such has called for a strategy of designing molecules retaining a particular scaffold as a substructure. On this account, our present work proposes a scaffold-based molecular generative model. The model generates molecular graphs by extending the graph of a scaffold through sequential additions of vertices and edges. In contrast to previous related models, our model guarantees the generated molecules to retain the given scaffold with certainty. Our evaluation of the model using unseen scaffolds showed the validity, uniqueness, and novelty of generated molecules as high as the case using seen scaffolds. This confirms that the model can generalize the learned chemical rules of adding atoms and bonds rather than simply memorizing the mapping from scaffolds to molecules during learning. Furthermore, despite the restraint of fixing core structures, our model could simultaneously control multiple molecular properties when generating new molecules.

Constrained Bayesian optimization for automatic chemical design using variational autoencoders

“…The literature concerning generative models of molecules has exploded since the first work on the topic Gómez-Bombarelli et al [2018]. Current methods feature molecular representations such as SMILES [Janz et al, 2018, Segler et al, 2017, Skalic et al, 2019, Ertl et al, 2017, Lim et al, 2018, Kang and Cho, 2018, Sattarov et al, 2019, Gupta et al, 2018, Harel and Radinsky, 2018, Yoshikawa et al, 2018, Bjerrum and Sattarov, 2018, Mohammadi et al, 2019 and graphs [Simonovsky and Komodakis, 2018, Li et al, 2018a, De Cao and Kipf, 2018, Kusner et al, 2017, Dai et al, 2018, Samanta et al, 2019, Li et al, 2018b, Kajino, 2019, Jin et al, 2019, Bresson and Laurent, 2019, Lim et al, 2019, Pölsterl and Wachinger, 2019, Krenn et al, 2019, Maziarka et al, 2019, Madhawa et al, 2019, Shen, 2018, Korovina et al, 2019 In this section we conduct an empirical test of the hypothesis from [Gómez-Bombarelli et al, 2018] that the decoder's lack of efficiency is due to data point collection in "dead regions" of the latent space far from the data on which the VAE was trained. We use this information to construct a binary classification Bayesian Neural Network (BNN) to serve as a constraint function that outputs the probability of a latent point being valid, the details of which will be discussed in the section on labelling criteria.…”

A Systematic Survey on Deep Generative Models for Graph Generation

“…Very recently, Simonovsky and Komodakis [119] propose the generation of molecular graphs by predicting their adjacency matrices, and Li et al [79] generated molecules node by node. Then more and more deep graph generative models for molecule generation are proposed in an attempt to ensure chemical validity and efficiency [24,57,82,107,114,144].…”

An Efficient Algorithm to Count Tree-Like Graphs with a Given Number of Vertices and Self-Loops

“…Counting and generation of chemical compounds have a long history and numerous applications in designing novel drugs [ 3 , 4 , 5 , 6 , 7 , 8 ] and structure elucidation [ 9 ]. The problem of counting and generation of chemical compounds can be viewed as the problem of enumerating graphs with given constraints.…”