Impact Factor 3.845 | CiteScore 3.92
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Pharmacol. | doi: 10.3389/fphar.2019.00913

Identification of Novel Antibacterials using Machine-learning Techniques

Yan Ivanenkov1, 2, 3, 4*,  Alex Zhavoronkov4, Renat Yamidanov4, 5, Ilya Osterman3, 6, Petr Sergiev6, 7, Vladimir Aladinskiy2, 4, Anastasia Aladinskaya2, 4, Victor Terentiev2, 4, 5, Mark Veselov2, 4, 5, Andrey Ayginin2, 5,  Victor Kartsev8,  Dmitry Skvortsov7, Alexey Chemeris5, Alexey Baimiev5, Alina Sofronova9,  Alexander Malyshev4, 10, Gleb Filkov2, Dmitry Bezrukov3, 6,  Bogdan Zagribelny11, Evgeny Putin12, Maria Puchinina2 and Olga Dontsova3, 6, 7
  • 1ChemDiv (United States), United States
  • 2Moscow Institute of Physics and Technology, Russia
  • 3Chemical faculty, Lomonosov Moscow State University, Russia
  • 4Insilico Medicine, Inc., United States
  • 5Institute of Biochemistry and Genetics of Ufa Scientific Centre (RAS), Russia
  • 6Skolkovo Institute of Science and Technology, Russia
  • 7Belozersky Institute of Physico-Chemical Biology, Lomonosov Moscow State University, Russia
  • 8InterBioScreen ltd, Russia
  • 9Faculty of Bioengineering and Bioinformatics, Lomonosov Moscow State University, Russia
  • 10Faculty of Basic Medicine, Lomonosov Moscow State University, Russia
  • 11Lomonosov Moscow State University, Russia
  • 12ITMO University, Russia

Many pharmaceutical companies are avoiding the development of novel antibacterials due to a range of rational reasons and the high risk of failure. However, there is an urgent need for novel antibiotics especially against resistant bacterial strains. Available in silico models suffer from many drawbacks and, therefore, are not applicable for scoring novel molecules with high structural diversity by their antibacterial potency. Considering this, the overall aim of this study was to develop an efficient in silico model able to find compounds which have plenty of chances to exhibit antibacterial activity. Based on a proprietary screening campaign, we have accumulated a representative dataset of more than 140,000 molecules with antibacterial activity against E. coli assessed in the same assay and under the same conditions. This intriguing set has no analogue in the scientific literature. We applied six in silico techniques to mine this data. For external validation, we used 5,000 compounds with low similarity towards training samples. Antibacterial activity of the selected molecules against E. coli was assessed using a comprehensive biological study. Kohonen-based non-linear mapping was used for the first time and provided the best predictive power (av. 75.5%). Several compounds showed an outstanding antibacterial potency and were identified as translation machinery inhibitors in vitro and in vivo. For the best compounds, MIC and CC50 values were determined to allow us to estimate a selectivity index (SI). Many active compounds have a robust IP position.

Keywords: novel antibacterials, Machine learning techniques, Translation inhibitors, Virtual Screening, Kohonen-based SOM

Received: 15 Feb 2019; Accepted: 19 Jul 2019.

Copyright: © 2019 Ivanenkov, Zhavoronkov, Yamidanov, Osterman, Sergiev, Aladinskiy, Aladinskaya, Terentiev, Veselov, Ayginin, Kartsev, Skvortsov, Chemeris, Baimiev, Sofronova, Malyshev, Filkov, Bezrukov, Zagribelny, Putin, Puchinina and Dontsova. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Dr. Yan Ivanenkov, ChemDiv (United States), San Diego, 92121, California, United States,