Deep learning enables rapid identification of potent DDR1 kinase inhibitors

@article{Zhavoronkov2019DeepLE,
  title={Deep learning enables rapid identification of potent DDR1 kinase inhibitors},
  author={Alex Zhavoronkov and Yan A. Ivanenkov and Alexander Aliper and Mark Veselov and Vladimir Aladinskiy and Anastasiya V Aladinskaya and Victor Terentiev and Daniil Polykovskiy and Maksim Kuznetsov and Arip Asadulaev and Yury Volkov and Artem Zholus and Shayakhmetov Rim and Alexander Zhebrak and Lidiya I Minaeva and Bogdan Zagribelnyy and Lennart H Lee and Richard M. Soll and David Madge and Li Xing and Tao Guo and Al{\'a}n Aspuru-Guzik},
  journal={Nature Biotechnology},
  year={2019},
  volume={37},
  pages={1038-1040}
}
We have developed a deep generative model, generative tensorial reinforcement learning (GENTRL), for de novo small-molecule design. GENTRL optimizes synthetic feasibility, novelty, and biological activity. We used GENTRL to discover potent inhibitors of discoidin domain receptor 1 (DDR1), a kinase target implicated in fibrosis and other diseases, in 21 days. Four compounds were active in biochemical assays, and two were validated in cell-based assays. One lead candidate was tested and… 

Deep learning identifies DDR1 kinase inhibitors

TLDR
GSCA1 exhibited potent inhibitory activity against all major HIV-1 types, including viral variants resistant to the antiretroviral therapies currently in clinical use, demonstrating superior activity to rilpivirine — a licensed longacting ARV.

Deep learning approaches for de novo drug design: An overview.

A Bag of Tricks for Automated De Novo Design of Molecules with the Desired Properties: Application to EGFR Inhibitor Discovery

TLDR
The proposed technical solutions are expected to substantially improve the success rate of finding novel bioactive compounds for specific biological targets using generative and reinforcement learning approaches.

Advances and Challenges in De Novo Drug Design Using Three-Dimensional Deep Generative Models

TLDR
This review highlights current developments in 3D molecular generative models combined with deep learning and discusses future directions for de novo drug design.

Design of potent antimalarials with generative chemistry

TLDR
This work built a generative modelling approach, JAEGER, for finding novel chemical matter with desired bioactivity, and designed compounds to inhibit malaria, which exhibited low nanomolar activity in a malaria proliferation assay as well as a biochemical assay measuring activity against PI(4)K.

Generating Novel Compounds Targeting SARS-CoV-2 Main Protease Based on Imbalanced Dataset

TLDR
This paper proposes an efficient pipeline to generate novel SARS-CoV-2 3C-like protease inhibitors using the GPT2 generator and the well performing multi-task predictor based on a number of novel 3CL-target compounds and analyzed their molecular properties.

Comparative study between deep learning and QSAR classifications for TNBC inhibitors and novel GPCR agonist discovery

TLDR
Comparisons between deep neural networks (DNN) and other ligand-based virtual screening (LBVS) methods are performed to demonstrate that DNN and random forest (RF) were superior in hit prediction efficiency and provide experimental evidence that machine learning could identify potent hits in silico from a limited training set.

Development of a Deep Learning Generative Neural Network for Computer-Aided Design of Potential SARS-Cov-2 Inhibitors

Two generative deep learning models have been developed for the computer-aided design of potential inhibitors of the SARS-CoV-2 main protease (MPro), an enzyme critically important for the virus

JAEGER – Hunting for Antimalarials with Generative Chemistry

TLDR
The findings show that JAEGER is a viable approach for finding novel active compounds for drug discovery and shows low nanomolar activity in a malaria proliferation assay as well as a biochemical assay measuring activity against PI(4)K, which is an essential kinase that regulates intracellular development in malaria.
...

References

SHOWING 1-10 OF 32 REFERENCES

Entangled Conditional Adversarial Autoencoder for de Novo Drug Discovery.

TLDR
A new generative architecture is proposed, entangled conditional adversarial autoencoder, that generates molecular structures based on various properties, such as activity against a specific protein, solubility, or ease of synthesis, that is applied to generate a novel inhibitor of Janus kinase 3.

De Novo Design of Bioactive Small Molecules by Artificial Intelligence

TLDR
This study presents the first‐time prospective application of a deep learning model for designing new druglike compounds with desired activities and synthesized five top‐ranking compounds designed by the generative model.

druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico.

TLDR
This work developed an advanced AAE model for molecular feature extraction problems, and demonstrated its advantages compared to VAE in terms of adjustability in generating molecular fingerprints; capacity of processing very large molecular data sets; and efficiency in unsupervised pretraining for regression model.

Reinforced Adversarial Neural Computer for de Novo Molecular Design

TLDR
An original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL).

Prototype-Based Compound Discovery Using Deep Generative Models.

TLDR
This work develops a deep-learning unsupervised-approach that automatically generates potential drug molecules given a prototype drug and shows that the molecules generated by the system are valid molecules and significantly different from the prototype drug.

Inverse molecular design using machine learning: Generative models for matter engineering

TLDR
Methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality, are reviewed.

The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology

TLDR
This paper presents the first application of generative adversarial autoencoders (AAE) for generating novel molecular fingerprints with a defined set of parameters, developed a 7-layer AAE architecture with the latent middle layer serving as a discriminator.

Tuning artificial intelligence on the de novo design of natural-product-inspired retinoid X receptor modulators

TLDR
A deep recurrent neural network is described for de novo design of new chemical entities that are inspired by pharmacologically active natural products, which are shown to be bioactive against the retinoid X receptor.

Adversarial Threshold Neural Computer for Molecular de Novo Design.

TLDR
Analysis of key molecular descriptors and chemical statistical features demonstrated that the molecules generated by ATNC elicited better druglikeness properties, indicating that ATNC is an effective method for producing hit compounds.

DNA-Encoded Library-Derived DDR1 Inhibitor Prevents Fibrosis and Renal Function Loss in a Genetic Mouse Model of Alport Syndrome

TLDR
Compound 2.45 preserves renal function and reduces tissue damage in Col4a3–/– mice (the preclinical mouse model of Alport syndrome) when employing a therapeutic dosing regime, indicating the real therapeutic value of selectively inhibiting DDR1 phosphorylation in vivo.