Harnessing AI to Revolutionize Antibiotic Discovery
Keywords:
QSAR modeling, artificial intelligence (AI), machine learning, deep learning, and antibiotic discovery Antimicrobial Resistance (AMR) and artificial intelligenceAbstract
The threats posed by antimicrobial resistance (AMR) being rapidly spread to all parts of the world are undermining the effectiveness of all the available classes of antibiotics and thus a new system of detecting the drug efficiently and effectively is required. The curve of multidrug resistance among pathogenic organisms is increasing at a rate exceeding the paradigms of conventional drug discovery that are both time- and cost-consuming. Over the last few years, the pharmaceutical industry has experienced a paradigm shift, and this is because machine learning (ML) and deep learning (DL) have the capacity to question large chemical libraries, predict antimicrobial activity, and design new antibacterial agents rationally. Modern antibiotics are not only effective in averting existing resistance types, but also in preventing emergence of new resistances. In addition, ML and AI methods are utilized in developing drugs based on infectious disease studies to optimize the representations of compounds using quantitative structure-activity relationship (QSAR) models, optimized descriptors, and neural networks. Deep-learning generative systems and reinforcement-learning systems are also used to design new bioactive molecules to combat resistance mechanisms. Those projects, like BacEffluxPred that categorize efflux pumps that initiate antibiotic resistance, complement genomic surveillance and, at the broader level, define important drug targets. Moreover, machine-learning-based drug discovery platforms combine high-content imaging with classification algorithms to clarify and predict antimicrobial mechanisms of action and in addition to discovering the suboptimally active, which is otherwise undiscoverable. The systems will show a significant improvement compared to the conventional computing resources, decreasing the time required to conduct an experiment and enhancing the reproducibility and efficiency of the results gained in the course of preclinical triage. Altogether, the artificially intelligent methods of antibiotic discovery form a new paradigm with regard to pharmaceutical development and microbiological research. Artificial intelligence has the potential to comprehend current global issues connected with antimicrobial resistance, as the synthesis of anticipatory capability at an expedited reaction and within a profound mechanistic coverage. This highlights how the authors have been determined to combine AI with empirical microbiology in order to develop next generation antibiotics as well as revamp therapeutic innovation
Downloads
References
[1] D. M. P. De Oliveira et al., “Antimicrobial resistance in ESKAPE pathogens,” Clin. Microbiol. Rev., vol. 33, no. 3, 2020, doi: 10.1128/CMR.00181-19;PAGE:STRING:ARTICLE/CHAPTER.
[2] M. Craig, “CDC’s Antibiotic Resistance Threats Report, 2019 EXTENDED SPECTRUM β-LACTAMASE (ESBL)-PRODUCING ENTEROBACTERIACEAE,” 2019.
[3] K. R. Chng et al., “Metagenome-wide association analysis identifies microbial determinants of post-antibiotic ecological recovery in the gut,” Nat. Ecol. Evol., vol. 4, no. 9, pp. 1256–1267, Sep. 2020, doi: 10.1038/S41559-020-1236-0;TECHMETA.
[4] J. A. DiMasi, H. G. Grabowski, and R. W. Hansen, “Innovation in the pharmaceutical industry: New estimates of R&D costs,” J. Health Econ., vol. 47, pp. 20–33, May 2016, doi: 10.1016/J.JHEALECO.2016.01.012.
[5] M. D. T. Torres and C. de la Fuente-Nunez, “Toward computer-made artificial antibiotics,” Curr. Opin. Microbiol., vol. 51, pp. 30–38, Oct. 2019, doi: 10.1016/J.MIB.2019.03.004.
[6] W. F. Porto et al., “In silico optimization of a guava antimicrobial peptide enables combinatorial exploration for peptide design,” Nat. Commun. 2018 91, vol. 9, no. 1, pp. 1490-, Apr. 2018, doi: 10.1038/s41467-018-03746-3.
[7] J. M. Stokes et al., “A Deep Learning Approach to Antibiotic Discovery,” Cell, vol. 180, no. 4, pp. 688-702.e13, Feb. 2020, doi: 10.1016/j.cell.2020.01.021.
[8] A. Cherkasov et al., “QSAR Modeling: Where Have You Been? Where Are You Going To?,” J. Med. Chem., vol. 57, no. 12, pp. 4977–5010, Jun. 2014, doi: 10.1021/JM4004285.
[9] G. J. P. Van Westen, R. F. Swier, J. K. Wegner, A. P. I. Jzerman, H. W. T. Van Vlijmen, and A. Bender, “Benchmarking of protein descriptor sets in proteochemometric modeling (part 1): comparative study of 13 amino acid descriptor sets,” J. Cheminformatics 2013 51, vol. 5, no. 1, pp. 41-, Sep. 2013, doi: 10.1186/1758-2946-5-41.
[10] M. Awale, F. Sirockin, N. Stiefl, and J. L. Reymond, “Drug Analogs from Fragment-Based Long Short-Term Memory Generative Neural Networks,” J. Chem. Inf. Model., vol. 59, no. 4, pp. 1347–1356, Apr. 2019, doi: 10.1021/ACS.JCIM.8B00902.
[11] D. Pandey, B. Kumari, N. Singhal, and M. Kumar, “BacEffluxPred: A two-tier system to predict and categorize bacterial efflux mediated antibiotic resistance proteins,” Sci. Reports 2020 101, vol. 10, no. 1, pp. 9287-, Jun. 2020, doi: 10.1038/s41598-020-65981-3.
[12] M. Popova, O. Isayev, and A. Tropsha, “Deep reinforcement learning for de novo drug design,” Sci. Adv., vol. 4, no. 7, Jul. 2018, doi: 10.1126/SCIADV.AAP7885.
[13] J. D. Durrant and R. E. Amaro, “Machine-learning techniques applied to antibacterial drug discovery,” Chem. Biol. Drug Des., vol. 85, no. 1, pp. 14–21, Jan. 2015, doi: 10.1111/CBDD.12423;WGROUP:STRING:PUBLICATION.
[14] R. A. Mansbach et al., “Machine Learning Algorithm Identifies an Antibiotic Vocabulary for Permeating Gram-Negative Bacteria,” J. Chem. Inf. Model., vol. 60, no. 6, pp. 2838–2847, Jun. 2020, doi: 10.1021/ACS.JCIM.0C00352.
[15] S. Zoffmann et al., “Machine learning-powered antibiotics phenotypic drug discovery,” Sci. Reports 2019 91, vol. 9, no. 1, pp. 5013-, Mar. 2019, doi: 10.1038/s41598-019-39387-9.
[16] Chan HCS, Shan H, Dahoun T, Vogel H, Yuan S. Advancing drug discovery via artificial intelligence. Trends Pharmacol Sci. 2019;40(8):592‐604.
[17]. Mak K‐K, Pichika MR. Artificial intelligence in drug development: present status and future prospects. Drug Discovery Today. 2019;24(3):773‐780.
[18] Hinton GE, Krizhevsky A, Wang SD. Transforming Auto‐Encoders. Berlin, Heidelberg, Germany: Springer; 2011
[19] Becker G, Bolbos R, Costes N, Redoute J, Newman‐Tancredi A, Zimmer L. Selective serotonin 5‐HT1A receptor biased agonists elicit distinct brain activation patterns: a pharmacoMRI study. Sci Rep. 2016;6:26633.
[20] Downey D, Dutta A, McKie S, et al. Comparing the actions of lanicemine and ketamine in depression: key role of the anterior cingulate. Eur Neuropsychopharmacol. 2016;26(6):994‐1003.
[21] von Pföstl V, Li J, Zaldivar D, et al. Effects of lactate on the early visual cortex of non‐human primates, investigated by pharmaco‐MRI and neurochemical analysis. Neuroimage. 2012;61(1):98‐105
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
