Identification of Novel Antibacterials Using Machine Learning Techniques

Overview

Journal Front Pharmacol

Date 2019 Sep 12

PMID 31507413

Citations 17

Authors

Yan A Ivanenkov

Alex Zhavoronkov

Renat S Yamidanov

Ilya A Osterman

Petr V Sergiev

Vladimir A Aladinskiy

Anastasia V Aladinskaya

Victor A Terentiev

Mark S Veselov

Andrey A Ayginin

Victor G Kartsev

Dmitry A Skvortsov

Alexey V Chemeris

Alexey Kh Baimiev

Alina A Sofronova

Alexander S Malyshev

Gleb I Filkov

Dmitry S Bezrukov

Bogdan A Zagribelnyy

Evgeny O Putin

Maria M Puchinina

Olga A Dontsova

Affiliations

Soon will be listed here.

Abstract

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 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 model able to find compounds that 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 assessed in the same assay and under the same conditions. This intriguing set has no analogue in the scientific literature. We applied six techniques to mine these data. For external validation, we used 5,000 compounds with low similarity towards training samples. The antibacterial activity of the selected molecules against was assessed using a comprehensive biological study. Kohonen-based nonlinear 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 and . For the best compounds, MIC and CC values were determined to allow us to estimate a selectivity index (SI). Many active compounds have a robust IP position.

Citing Articles

Predicting Antimicrobial Class Specificity of Small Molecules Using Machine Learning.

Gadiya Y, Genilloud O, Bilitewski U, Bronstrup M, von Berlin L, Attwood M J Chem Inf Model. 2025; 65(5):2416-2431.

PMID: 39987507 PMC: 11898080. DOI: 10.1021/acs.jcim.4c02347.

AC-ModNet: Molecular Reverse Design Network Based on Attribute Classification.

Wei W, Fang J, Yang N, Li Q, Hu L, Zhao L Int J Mol Sci. 2024; 25(13).

PMID: 39000049 PMC: 11241775. DOI: 10.3390/ijms25136940.

Implications of Artificial Intelligence in Addressing Antimicrobial Resistance: Innovations, Global Challenges, and Healthcare's Future.

Branda F, Scarpa F Antibiotics (Basel). 2024; 13(6).

PMID: 38927169 PMC: 11200959. DOI: 10.3390/antibiotics13060502.

ABDpred: Prediction of active antimicrobial compounds using supervised machine learning techniques.

Jana T, Sarkar D, Ganguli D, Mukherjee S, Mandal R, Das S Indian J Med Res. 2024; 159(1):78-90.

PMID: 38345040 PMC: 10954100. DOI: 10.4103/ijmr.ijmr_1832_22.

Identification of a Specific Biomarker of Acinetobacter baumannii Global Clone 1 by Machine Learning and PCR Related to Metabolic Fitness of ESKAPE Pathogens.

Alvarez V, Quiroga M, Centron D mSystems. 2023; 8(3):e0073422.

PMID: 37184409 PMC: 10308912. DOI: 10.1128/msystems.00734-22.

References

Wang L, Le X, Li L, Ju Y, Lin Z, Gu Q . Discovering new agents active against methicillin-resistant Staphylococcus aureus with ligand-based approaches. J Chem Inf Model. 2014; 54(11):3186-97. DOI: 10.1021/ci500253q. View

Cronin M, Aptula A, Dearden J, Duffy J, Netzeva T, Patel H . Structure-based classification of antibacterial activity. J Chem Inf Comput Sci. 2002; 42(4):869-78. DOI: 10.1021/ci025501d. View

Mohr K . History of Antibiotics Research. Curr Top Microbiol Immunol. 2016; 398:237-272. DOI: 10.1007/82_2016_499. View

Araya-Cloutier C, Vincken J, van de Schans M, Hageman J, Schaftenaar G, den Besten H . QSAR-based molecular signatures of prenylated (iso)flavonoids underlying antimicrobial potency against and membrane-disruption in Gram positive and Gram negative bacteria. Sci Rep. 2018; 8(1):9267. PMC: 6006161. DOI: 10.1038/s41598-018-27545-4. View

Spangler S, Jacobs M, Appelbaum P . Activities of RPR 106972 (a new oral streptogramin), cefditoren (a new oral cephalosporin), two new oxazolidinones (U-100592 and U-100766), and other oral and parenteral agents against 203 penicillin-susceptible and -resistant pneumococci. Antimicrob Agents Chemother. 1996; 40(2):481-4. PMC: 163140. DOI: 10.1128/AAC.40.2.481. View

McGuire J, BUNCH R, Anderson R, BOAZ H, FLYNN E, Powell H . Ilotycin, a new antibiotic. Antibiot Chemother (Northfield). 2014; 2(6):281-3. View

Balakin K, Ivanenkov Y, Skorenko A, Nikolsky Y, Savchuk N, Ivashchenko A . In silico estimation of DMSO solubility of organic compounds for bioscreening. J Biomol Screen. 2004; 9(1):22-31. DOI: 10.1177/1087057103260006. View

Kaczor A, Polski A, Sobotka-Polska K, Pachuta-Stec A, Makarska-Bialokoz M, Pitucha M . Novel Antibacterial Compounds and their Drug Targets - Successes and Challenges. Curr Med Chem. 2016; 24(18):1948-1982. DOI: 10.2174/0929867323666161213102127. View

Molina E, Diaz H, Gonzalez M, Rodriguez E, Uriarte E . Designing antibacterial compounds through a topological substructural approach. J Chem Inf Comput Sci. 2004; 44(2):515-21. DOI: 10.1021/ci0342019. View

10.

Garcia-Domenech R, de Julian-Ortiz J . Antimicrobial activity characterization in a heterogeneous group of compounds. J Chem Inf Comput Sci. 1998; 38(3):445-9. DOI: 10.1021/ci9702454. View

11.

Yang X, Chen D, Wang M, Xue Y, Chen Y . Prediction of antibacterial compounds by machine learning approaches. J Comput Chem. 2008; 30(8):1202-11. DOI: 10.1002/jcc.21148. View

12.

Gonzalez-Diaz H, Torres-Gomez L, Guevara Y, Almeida M, Molina R, Castanedo N . Markovian chemicals "in silico" design (MARCH-INSIDE), a promising approach for computer-aided molecular design III: 2.5D indices for the discovery of antibacterials. J Mol Model. 2005; 11(2):116-23. DOI: 10.1007/s00894-004-0228-3. View

13.

Kohanski M, Dwyer D, Collins J . How antibiotics kill bacteria: from targets to networks. Nat Rev Microbiol. 2010; 8(6):423-35. PMC: 2896384. DOI: 10.1038/nrmicro2333. View

14.

Wiegand I, Hilpert K, Hancock R . Agar and broth dilution methods to determine the minimal inhibitory concentration (MIC) of antimicrobial substances. Nat Protoc. 2008; 3(2):163-75. DOI: 10.1038/nprot.2007.521. View

15.

Projan S . Why is big Pharma getting out of antibacterial drug discovery?. Curr Opin Microbiol. 2003; 6(5):427-30. DOI: 10.1016/j.mib.2003.08.003. View

16.

Salabert-Salvador M, Perez-Gimenez F, Tomas-Vert F . Artificial neural network applied to prediction of fluorquinolone antibacterial activity by topological methods. J Med Chem. 2000; 43(6):1143-8. DOI: 10.1021/jm980448z. View

17.

Zhang Z . Introduction to machine learning: k-nearest neighbors. Ann Transl Med. 2016; 4(11):218. PMC: 4916348. DOI: 10.21037/atm.2016.03.37. View

18.

Osterman I, Khabibullina N, Komarova E, Kasatsky P, Kartsev V, Bogdanov A . Madumycin II inhibits peptide bond formation by forcing the peptidyl transferase center into an inactive state. Nucleic Acids Res. 2017; 45(12):7507-7514. PMC: 5499580. DOI: 10.1093/nar/gkx413. View

19.

Naeem A, Badshah S, Muska M, Ahmad N, Khan K . The Current Case of Quinolones: Synthetic Approaches and Antibacterial Activity. Molecules. 2016; 21(4):268. PMC: 6274096. DOI: 10.3390/molecules21040268. View

20.

Karakoc E, Cherkasov A, Sahinalp S . Distance based algorithms for small biomolecule classification and structural similarity search. Bioinformatics. 2006; 22(14):e243-51. DOI: 10.1093/bioinformatics/btl259. View