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

By Artur Kadurin, Alex Aliper, Andrey M. Kazennov, Polina Mamoshina, Quentin Vanhaelen, Kuzma Khrabrov, A. Zhavoronkov. OncoTarget, 2016

323 citations recorded by the source corpus.

Recent advances in deep learning and specifically in generative adversarial networks have demonstrated surprising results in generating new images and videos upon request even using natural language as input. In this paper we present the first application of generative adversarial autoencoders (AAE) for generating novel molecular fingerprints with a defined set of parameters. We developed a 7-layer AAE architecture with the latent middle layer serving as a discriminator. As an input and output the AAE uses a vector of binary fingerprints and concentration of the molecule. In the latent layer we also introduced a neuron responsible for growth inhibition percentage, which when negative indicates the reduction in the number of tumor cells after the treatment. To train the AAE we used the NCI-60 cell line assay data for 6252 compounds profiled on MCF-7 cell line. The output of the AAE was used to screen 72 million compounds in PubChem and select candidate molecules with potential anti-cancer properties. This approach is a proof of concept of an artificially-intelligent drug discovery engine, where AAEs are used to generate new molecular fingerprints with the desired molecular properties.

Subfields: Biophysics, Computational Theory and Mathematics, Media Technology

View Paper: https://www.semanticscholar.org/paper/0b309c0725c717989f6d6ae485fbab521e72d903

How researchers see this paper

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

In Biophysics

In Computational Theory and Mathematics

In Media Technology

Sergey I. Nikolenko

Citations in the corpus

Deep Learning in Pharmacogenomics: From Gene Regulation to Patient Stratification (2018, unknown): “design molecules with desired chemical properties [109-111].”
Molecular representations in AI-driven drug discovery: a review and practical guide (2020, background): “String representations have also seen success in property prediction using the learned latent space representations obtained using autoencoder frameworks [139].”
Integrated deep learned transcriptomic and structure-based predictor of clinical trials outcomes (2016, background): “2015) to generate molecular fingerprints of prospective compounds with the desired molecular properties (Kadurin et al. 2016).”
Deep reinforcement learning for de novo drug design (2017, methodology): “An adversarial autoencoder was proposed (24) as a tool for generating new molecules with the desired properties; however, compounds of interest are selected by means of virtual screening of large libraries, not by designing novel molecules.”
Accelerating the discovery of materials for clean energy in the era of smart automation (2018, background): “In the past year, there have been substantial developments in generative models for chemistry 51–55, 200– 202 , which may change the way Virtual screening could add a step in the virtuous cycle described above by including the metric-driven modification of models used in relating input parameters…”
Converging blockchain and next-generation artificial intelligence technologies to decentralize and accelerate biomedical research and healthcare (2015, methodology): “Similar concepts were applied for molecule generation by Kadurin and colleagues [41].”