Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks

By Marwin H. S. Segler, Thierry Kogej, Christian Tyrchan, Mark P. Waller. 2017

1,386 citations recorded by the source corpus.

In de novo drug design, computational strategies are used to generate novel molecules with good affinity to the desired biological target. In this work, we show that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language processing. We demonstrate that the properties of the generated molecules correlate very well with the properties of the molecules used to train the model. In order to enrich libraries with molecules active toward a given biological target, we propose to fine-tune the model with small sets of molecules, which are known to be active against that target. Against Staphylococcus aureus, the model reproduced 14% of 6051 hold-out test molecules that medicinal chemists designed, whereas against Plasmodium falciparum (Malaria), it reproduced 28% of 1240 test molecules. When coupled with a scoring function, our model can perform the complete de novo drug design cycle to generate large sets of novel molecules for drug discovery.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Generative Models, Computational Chemistry & Drug Discovery

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 Materials Chemistry

In Molecular Biology

In Generative Models

In Computational Chemistry & Drug Discovery

Citations in the corpus

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (2018, background): “Recently, there has been signiﬁcant advances in applying deep learning models to molecule generation [15, 38, 7, 9, 22, 4, 31, 27, 34, 42].”
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models (2018, methodology): “Most previous work on discovering molecule structures make use of a expert-crafted sequence representations of molecular graph structures (SMILES) (Olivecrona et al., 2017; Segler et al., 2017; Gómez-Bombarelli et al., 2016).”
GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders (2018, positive): “…molecules have an intuitive representation as graphs, the ﬁeld has had to resort to textual representations with ﬁxed syntax, e.g. so-called SMILES strings, to exploit recent progress made in text generation with RNNs (Olivecrona et al., 2017; Segler et al., 2017; G´omez-Bombarelli et al., 2016).”
Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models (2017, background): “, 2017] and [Segler et al., 2017] trained recurrent neural networks to generate drug-like molecules.”
3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (2023, methodology): “The most common molecular string representation is SMILES (Weininger, 1988), where many existing language models such as RNN can be re-purposed for the molecule generation task (Bjerrum and Threlfall, 2017; G´omez-Bombarelli et al., 2018; Kus-ner et al., 2017; Segler et al., 2018).”
Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions (2018, positive): “RNNs have shown to be successful in generating SMILES sequences for de novo drug discovery [20] and recent work also showed that the RNN’s outputs could be optimized for speciﬁc properties through transfer-learning and ﬁne-tuning on sequences with desired properties [11].”
Artificial intelligence in drug development: present status and future prospects. (2019, background): “This is caused by the vast size of what is known as chemical space, which is estimated to be in the order of 10 60 molecules [27].”
Artificial Intelligence For Natural Product Drug Discovery (2023, background): “…109–112 ; for instance, for predicting drug–target binding affinity 113 , SMILES-based approaches for de novo drug-like molecule generation 114,115 , graph-based de novo molecular generation 116 , and property prediction 117,118 and surface mesh-based approaches for protein pocket-conditioned…”
GuacaMol: Benchmarking Models for De Novo Molecular Design (2018, methodology): “Merk, Schneider and coworkers validated the SMILES-LSTM transfer learning method 14 by generating compounds 1-3 for nuclear receptors, which after synthesis and testing showed micro-to nanomolar activity (see Figure 1).”