Andrey Kazennov

// Artur Kadurin 1, 2, 3, 4 , Alexander Aliper 2 , Andrey Kazennov 2, 7 , Polina Mamoshina 2, 5 , Quentin Vanhaelen 2 , Kuzma Khrabrov 1 , Alex Zhavoronkov 2, 6, 7 1 Search Department, Mail.Ru Group Ltd., Moscow, Russia 2 Pharmaceutical Artificial Intelligence Department, Insilico Medicine, Inc., Emerging Technology Centers, Johns Hopkins University at Eastern, Baltimore, Maryland, USA 3 Big Data and Text Analysis Laboratory, Kazan Federal University, Kazan, Republic of Tatarstan, Russia 4 St. Petersburg Department of V.A. Steklov Institute of Mathematics of the Russian Academy of Sciences, Petersburg, Russia 5 Department of Computer Science, University of Oxford, Oxford, UK 6 The Biogerontology Research Foundation, Trevissome Park, Truro TR4 8UN, UK 7 Moscow Institute of Physics and Technology, Dolgoprudny, Russia Correspondence to: Alex Zhavoronkov, email: alex@insilicomedicine.com Keywords: generative adversarian networks, adversarial autoencoder, deep learning, drug discovery, artificial intelligence Received: June 14, 2016      Accepted: November 24, 2016      Published: December 22, 2016 ABSTRACT 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.

Energy evaluation using fast Fourier transforms (FFTs) enables sampling billions of putative complex structures and hence revolutionized rigid protein-protein docking. However, in current methods, efficient acceleration is achieved only in either the translational or the rotational subspace. Developing an efficient and accurate docking method that expands FFT-based sampling to five rotational coordinates is an extensively studied but still unsolved problem. The algorithm presented here retains the accuracy of earlier methods but yields at least 10-fold speedup. The improvement is due to two innovations. First, the search space is treated as the product manifold [Formula: see text], where [Formula: see text] is the rotation group representing the space of the rotating ligand, and [Formula: see text] is the space spanned by the two Euler angles that define the orientation of the vector from the center of the fixed receptor toward the center of the ligand. This representation enables the use of efficient FFT methods developed for [Formula: see text] Second, we select the centers of highly populated clusters of docked structures, rather than the lowest energy conformations, as predictions of the complex, and hence there is no need for very high accuracy in energy evaluation. Therefore, it is sufficient to use a limited number of spherical basis functions in the Fourier space, which increases the efficiency of sampling while retaining the accuracy of docking results. A major advantage of the method is that, in contrast to classical approaches, increasing the number of correlation function terms is computationally inexpensive, which enables using complex energy functions for scoring.

// Michael D. West 1 , Ivan Labat 1 , Hal Sternberg 1 , Dana Larocca 1 , Igor Nasonkin 2 , Karen B. Chapman 3 , Ratnesh Singh 2 , Eugene Makarev 4 , Alex Aliper 4 , Andrey Kazennov 4, 5 , Andrey Alekseenko 4, 10 , Nikolai Shuvalov 4, 5 , Evgenia Cheskidova 4, 5 , Aleksandr Alekseev 4, 5 , Artem Artemov 4 , Evgeny Putin 4, 6 , Polina Mamoshina 4 , Nikita Pryanichnikov 4 , Jacob Larocca 1 , Karen Copeland 7 , Evgeny Izumchenko 8 , Mikhail Korzinkin 4 and Alex Zhavoronkov 4, 9 1 AgeX Therapeutics, Inc., Alameda, CA, USA 2 BioTime, Inc., Alameda, CA, USA 3 Johns Hopkins University, Baltimore, MD, USA 4 Pharmaceutical Artificial Intelligence Department, Insilico Medicine, Inc., Emerging Technology Centers, Johns Hopkins University at Eastern, Baltimore, MD, USA 5 Moscow Institute of Physics and Technology, Dolgoprudny, Russia 6 Computer Technologies Lab, ITMO University, St. Petersburg, Russia 7 Boulder Statistics, Boulder, CO, USA 8 Johns Hopkins University, School of Medicine, Department of Otolaryngology-Head and Neck Cancer Research, Baltimore, MD, USA 9 The Biogerontology Research Foundation, Trevissome Park, Truro, UK 10 Innopolis University, Innoplis, Russia Correspondence to: Michael D. West, email: mwest@biotimeinc.com Alex Zhavoronkov, email: alex@insilicomedicine.com Keywords: cancer marker; Warburg effect; embryonic-fetal transition; deep neural network; stem cells Received: September 18, 2017      Accepted: December 20, 2017      Published: December 28, 2017 ABSTRACT Here we present the application of deep neural network (DNN) ensembles trained on transcriptomic data to identify the novel markers associated with the mammalian embryonic-fetal transition (EFT). Molecular markers of this process could provide important insights into regulatory mechanisms of normal development, epimorphic tissue regeneration and cancer. Subsequent analysis of the most significant genes behind the DNNs classifier on an independent dataset of adult-derived and human embryonic stem cell (hESC)-derived progenitor cell lines led to the identification of COX7A1 gene as a potential EFT marker. COX7A1 , encoding a cytochrome C oxidase subunit, was up-regulated in post-EFT murine and human cells including adult stem cells, but was not expressed in pre-EFT pluripotent embryonic stem cells or their in vitro -derived progeny. COX7A1 expression level was observed to be undetectable or low in multiple sarcoma and carcinoma cell lines as compared to normal controls. The knockout of the gene in mice led to a marked glycolytic shift reminiscent of the Warburg effect that occurs in cancer cells. The DNN approach facilitated the elucidation of a potentially new biomarker of cancer and pre-EFT cells, the embryo-onco phenotype, which may potentially be used as a target for controlling the embryonic-fetal transition.