Multi-objective de novo drug design with conditional graph generative model

By Yibo Li, Liang Ren Zhang, Zhenming Liu. 2018

401 citations recorded by the source corpus.

Recently, deep generative models have revealed itself as a promising way of performing de novo molecule design. However, previous research has focused mainly on generating SMILES strings instead of molecular graphs. Although available, current graph generative models are are often too general and computationally expensive. In this work, a new de novo molecular design framework is proposed based on a type of sequential graph generators that do not use atom level recurrent units. Compared with previous graph generative models, the proposed method is much more tuned for molecule generation and has been scaled up to cover significantly larger molecules in the ChEMBL database. It is shown that the graph-based model outperforms SMILES based models in a variety of metrics, especially in the rate of valid outputs. For the application of drug design tasks, conditional graph generative model is employed. This method offers highe flexibility and is suitable for generation based on multiple objectives. The results have demonstrated that this approach can be effectively applied to solve several drug design problems, including the generation of compounds containing a given scaffold, compounds with specific drug-likeness and synthetic accessibility requirements, as well as dual inhibitors against JNK3 and GSK-3β.

Subfields: Computational Theory and Mathematics, Environmental Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Environmental Chemistry

Citations in the corpus

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (2018, background): “Li et al. [25] and Li et al. [26] described sequential graph generation models where conditioning labels can be incorporated to generate molecules whose molecular properties are close to speciﬁed target scores.”
Learning Multimodal Graph-to-Graph Translation for Molecular Optimization (2018, background): “Recently proposed graph decoders (Simonovsky & Komodakis, 2018; Li et al., 2018b; Jin et al., 2018; You et al., 2018b; Liu et al., 2018) focus on learning generative models of graphs.”
Permutation Invariant Graph Generation via Score-Based Generative Modeling (2020, methodology): “Implementation-wise, we sample N from the empirical distribution of number of nodes in the training dataset, as done in (Li et al., 2018b).”
Efficient Graph Generation with Graph Recurrent Attention Networks (2019, methodology): “[19] is the most similar to ours, where one column of the adjacency matrix is also generated at each step, and the generation process is modeled as either Markovian or recurrent using a global RNN, which works well for molecule generation.”
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining (2020, background): “Although many variants of these algorithms have been applied to real-world problems such as chemical design [22, 26, 31, 32, 4], the sample efﬁciency of this paradigm is currently unclear.”
GuacaMol: Benchmarking Models for De Novo Molecular Design (2018, neutral): “…models based on neural networks have since been further explored, with work on VAEs, 17,36–45 RNNs, 46–58 generative adversarial networks (GANs), 54,55,59,60 adversarial au-toencoders (AAEs), 61–64 and graph convolutional networks, 16,57,60,65 using SMILES strings or graphs to represent molecules.”
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, methodology): “…applied for e.g., in QSAR models and drug design (Kadurin et al., 2017; Chen et al., 2018; Fleming, 2018; Green et al., 2018; Gupta et al., 2018; Li et al., 2018b; Lo et al., 2018; Popova et al., 2018; Simões et al., 2018) aiming at identifying systems, molecules and materials with optimal…”
Graph Neural Networks and Their Current Applications in Bioinformatics (2021, background): “Li et al. (2018b) proposed a conditional graph generation model and explored two types of graph generation architectures.”
Artificial intelligence in drug discovery: recent advances and future perspectives (2021, background): “Recently, instances of conditional generative approaches have been suggested, which leverage additional information guiding the design, such as three-dimensional shape [144], drug-likeness [142], synthesizability [142,145], molecular descriptors values [146], and gene expression signatures [147].”
Randomized SMILES strings improve the quality of molecular generative models (2019, background): “Alternatively, SMILES generative models can be also understood as action (or policy)-based graph generative models [16, 46] in which a molecular graph is built stepwise.”
MolGAN: An implicit generative model for small molecular graphs (2018, methodology): “…to explore alternative generative architectures within the Mol-GAN framework, such as recurrent graph-based generative models (Johnson, 2017; Li et al., 2018b; You et al., 2018), as our current one-shot prediction of the adjacency tensor is most likely feasible only for graphs of small size.”
Graph convolutional networks for computational drug development and discovery (2019, background): “[46] De novo molecular design github.com/kevinid/molecule_generator Jin et al .”
Differentiable Scaffolding Tree for Molecular Optimization (2021, neutral): “It is evaluated by well-trained 3 random forest classiﬁers using ECFP6 ﬁngerprints using ExCAPE-DB dataset [32, 23].”