Deep Scaffold Hopping with Multi-modal Transformer Neural Networks

Zheng, Shuangjia; Lei, Zengrong; Ai, Haitao; Chen, Hongming; Deng, Daiguo; Yang, Yuedong

doi:10.26434/chemrxiv.13011767.v1

Cited by 8 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used molecule structural similarity to artificially construct a parallel training set with paired molecules, limiting the diversity of the target chemical space. Several variants [17,18,19] have been proposed to modify the unstable training process but still remain imperfect due to the unpractical supervision settings. Compared to previous works, our approach is the first to perform unsupervised molecule attributes transfer on non-parallel datasets.…”

Section: Related Workmentioning

confidence: 99%

Molecular Attributes Transfer from Non-Parallel Data

Zheng¹,

Song²,

Zhang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Optimizing chemical molecules for desired properties lies at the core of drug development. Despite initial successes made by deep generative models and reinforcement learning methods, these methods were mostly limited by the requirement of predefined attribute functions or parallel data with manually pre-compiled pairs of original and optimized molecules. In this paper, for the first time, we formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data through adversarial training strategies. Our model further enables both preservation of molecular contents and optimization of molecular properties through combining auxiliary guided-variational autoencoders and generative flow techniques. Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Molecular Attributes Transfer from Non-Parallel Data

Zheng¹,

Song²,

Zhang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“… 19 Zheng et al proposed a scaffold hopping model using the Transformer architecture. 20 The goal of this model is to predict the “hopped” molecule with improved pharmaceutical activity and a dissimilar two-dimensional (2D) structure but a similar three-dimensional (3D) structure by inputting a reference molecule and a specified protein. All of these works used the complete encoder–decoder architecture of the Transformer.…”

Section: Introductionmentioning

confidence: 99%

Transformer-Based Generative Model Accelerating the Development of Novel BRAF Inhibitors

et al. 2021

View full text Add to dashboard Cite

The de novo drug design based on SMILES format is a typical sequence-processing problem. Previous methods based on recurrent neural network (RNN) exhibit limitation in capturing long-range dependency, resulting in a high invalid percentage in generated molecules. Recent studies have shown the potential of Transformer architecture to increase the capacity of handling sequence data. In this work, the encoder module in the Transformer is used to build a generative model. First, we train a Transformer-encoder-based generative model to learn the grammatical rules of known drug molecules and a predictive model to predict the activity of the molecules. Subsequently, transfer learning and reinforcement learning were used to fine-tune and optimize the generative model, respectively, to design new molecules with desirable activity. Compared with previous RNN-based methods, our method has improved the percentage of generating chemically valid molecules (from 95.6 to 98.2%), the structural diversity of the generated molecules, and the feasibility of molecular synthesis. The pipeline is validated by designing inhibitors against the human BRAF protein. Molecular docking and binding mode analysis showed that our method can generate small molecules with higher activity than those carrying ligands in the crystal structure and have similar interaction sites with these ligands, which can provide new ideas and suggestions for pharmaceutical chemists.

show abstract

“…The most attractive feature of DNNs for de novo drug design is their ability to probabilistically generate compound structures [ 13 , 23 ]. DNNs are able to take non-trivial structure–activity patterns into account, thereby increasing the potential for scaffold hopping and the diversity of designed molecules [ 24 , 25 ]. A number of generators based on DNNs was developed recently demonstrating the ability of various network architectures to generate compounds of given properties [ 13 , 23 , 26 – 29 ].…”

Section: Introductionmentioning

confidence: 99%

GenUI: interactive and extensible open source software platform for de novo molecular generation and cheminformatics

Liu

Svozil

2021

J Cheminform

View full text Add to dashboard Cite

Many contemporary cheminformatics methods, including computer-aided de novo drug design, hold promise to significantly accelerate and reduce the cost of drug discovery. Thanks to this attractive outlook, the field has thrived and in the past few years has seen an especially significant growth, mainly due to the emergence of novel methods based on deep neural networks. This growth is also apparent in the development of novel de novo drug design methods with many new generative algorithms now available. However, widespread adoption of new generative techniques in the fields like medicinal chemistry or chemical biology is still lagging behind the most recent developments. Upon taking a closer look, this fact is not surprising since in order to successfully integrate the most recent de novo drug design methods in existing processes and pipelines, a close collaboration between diverse groups of experimental and theoretical scientists needs to be established. Therefore, to accelerate the adoption of both modern and traditional de novo molecular generators, we developed Generator User Interface (GenUI), a software platform that makes it possible to integrate molecular generators within a feature-rich graphical user interface that is easy to use by experts of diverse backgrounds. GenUI is implemented as a web service and its interfaces offer access to cheminformatics tools for data preprocessing, model building, molecule generation, and interactive chemical space visualization. Moreover, the platform is easy to extend with customizable frontend React.js components and backend Python extensions. GenUI is open source and a recently developed de novo molecular generator, DrugEx, was integrated as a proof of principle. In this work, we present the architecture and implementation details of GenUI and discuss how it can facilitate collaboration in the disparate communities interested in de novo molecular generation and computer-aided drug discovery.

show abstract

Deep Scaffold Hopping with Multi-modal Transformer Neural Networks

Cited by 8 publications

References 34 publications

Molecular Attributes Transfer from Non-Parallel Data

Molecular Attributes Transfer from Non-Parallel Data

Transformer-Based Generative Model Accelerating the Development of Novel BRAF Inhibitors

GenUI: interactive and extensible open source software platform for de novo molecular generation and cheminformatics

Contact Info

Product

Resources

About