Main areas and prospects for using artificial intelligence and machine learning to accelerate the development of new medicines
DOI:
https://doi.org/10.32687/1561-5936-2025-29-3-213-220Keywords:
overview, artificial intelligence, machine learning, medicines developAbstract
The article is dedicated to the directions and prospects of using artificial intelligence (AI) and machine learning (ML) in the development of new medicines. Innovative approaches have been presented that radically transform traditional processes of drug discovery and development. The main applications of AI/ML are presented: target identification and validation, molecular design, prediction of drug compound properties, and laboratory process automation. Technological solutions in this field are presented, such as Direct-to-Biology platforms, CRISPR technologies, high throughput imaging, and generative AI models. The key advantages of implementing AI/ML include accelerating medicines development, reducing costs, enhancing prediction accuracy, and expanding molecular design capabilities. To realize this potential, it is necessary to continue investing in technology and training specialists with an interdisciplinary profile. The integration of AI into research opens up new prospects for developing innovative, personalized treatment methods.References
Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. 2014.
Drug Discovery — ELRIG [Electronic resource]. URL: https://elrig.org/portfolio/drug-discovery-2024/ (accessed: 02th January 2025).
Sheikh M, Iqra F, Ambreen H, Pravin KA, Ikra M, Chung YS Integrating artificial intelligence and high-throughput phenotyping for crop improvement. J. Integr. Agric. 2024;(23):1787—1802.
Fang S, Wei R, Cui Y, Su L. Advancing AI protein structure prediction and design: from amino acid “bones” to new era of all-atom “flesh”. Green Carbon. 2024;(2):209—210.
Pioneering TechBio Solutions in Drug Discovery. Recursion [Electronic resource]. Available from: https://www.recursion.com/ (Аccessed: 02th January 2025).
Stevens R, Bendito-Mol E, Battersby DJ, Miah AH, Wellaway N, Law RP at all. Integrated Direct-to-Biology Platform for the Nanoscale Synthesis and Biological Evaluation of PROTACs. Journal of medicinal chemistry. 2022;66(22):15437—15452. DOI: 10.1021/acs.jmedchem.3c01604
Abbasi AF, Asim MN, Dengel A. Transitioning from wet lab to artificial intelligence: a systematic review of AI predictors in CRISPR. J Transl Med. 2025;23(1):153. DOI: 10.1186/s12967-024-06013-w
Advancing Gene Editing with ePsCas9 Technology [Electronic resource]. Available from: https://www.astrazeneca.com/what-science-can-do/topics/clinical-innovation/advancing-gene-editing-with-epscas9-technology.html (Аccessed: 02th January 2025).
Degtev D, Bravo J, Emmanouilidi A, Zdravković A, Choong O, Touza J et al. Engineered PsCas9 enables therapeutic genome editing in mouse liver with lipid nanoparticles. Nature Communications. 2024;15(1):1—15.
On the CRISPR horizon: democratising access to genome-editing technologies. Available from: https://www.drugtargetreview.com/article/107337/on-the-crispr-horizon-democratising-access-to-genome-editing-technologies/ (Accessed: 02th January 2025).
Constructive Bio. Available from: https://www.constructive.bio/. (Accessed: 02th January 2025).
Chen L, Xin X, Zhang Y, Li S, Zhao X, Li S. et al. Advances in Biosynthesis of Non-Canonical Amino Acids (ncAAs) and the Methods of ncAAs Incorporation into Proteins. Molecules. 2023;28(18):6745.
Chen Y, Jin S, Zhang M, Hu Y, Wu KL, Chung A. et al. Unleashing the potential of noncanonical amino acid biosynthesis to create cells with precision tyrosine sulfation. Nat Commun. 2022;(13):5434.
Automating Discovery: Laboratory Automation, High Throughput Experimentation, Diagnostics and Laboratory Robotics/AI. Available from: https://eu-robotics.net/2024-09-fll-white-paper-launched-on-lab-robotics/ (accessed: 02th January 2025).
Towards a research roadmap for laboratory robotics — 2024 — Wiley Analytical Science. Available from: https://analyticalscience.wiley.com/content/article-do/towards-research-roadmap-laboratory-robotics (accessed: 02th January 2025).
Royall P. Using Robotics in Laboratories During the COVID-19 Outbreak: A Review. IEEE Robotics & Automation Magazine.
PDFs | Review articles in LABORATORY AUTOMATION. Available from: https://www.researchgate.net/topic/Laboratory-Automation/publications (accessed: 02th January 2025).
Li H, Li T, Quang D, Guan Y. Network Propagation Predicts Drug Synergy in Cancers. Cancer Res. 2018;78(18):5446—5457.
Bestas B, Wimberger S, Degtev D, Madsen А, Rottner ФА., Karisson F. at al. A Type II-B Cas9 nuclease with minimized off-targets and reduced chromosomal translocations in vivo. Nat Commun. 2023;14(1):5474.
Reimagining Drug Discovery Process with AI — Isomorphic Labs. Available from: https://www.isomorphiclabs.com/ (Аccessed: 02th January 2025).
Roerden M, Castro AB, Cui Y, Harake N, Kim B, Dye J, Roerden M et al. Neoantigen architectures define immunogenicity and drive immune evasion of tumors with heterogenous neoantigen expression. J Immunother Cancer. 2024;12(11):e010249.
Litchfield K, Augustine M, Nene N, Fu H, Pinder C, Ligamari L et al. Immunotherapy drug target identification using machine learning and patient-derived tumour explant validation. Biomedical Foundation Models — IBM Research [Internet]. 2024 Nov; Available from: https://research.ibm.com/projects/biomedical-foundation-models. DOI:10.21203/rs.3.rs-5499857/v1
Biomedical Foundation Models — IBM Research [Electronic resource]. URL: https://research.ibm.com/projects/biomedical-foundation-models (accessed: 02.01.2025).
United Kingdom — IBM Research. Available from: https://research.ibm.com/labs/uk (accessed: 02th January 2025).
Aliper A, Plis S, Artemov A, Ulloa A, Mamoshina P, Zhavoronkov A. Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data. Mol Pharm. 2016;13(7):2524—2530. DOI: 10.1021/acs.molpharmaceut.6b00248
Insilico Medicine. Available from: https://insilico.com/ (Accessed: 02th January 2025).
Kamya P, Ozerov IV, Pun FW, et al. PandaOmics: An AI-Driven Platform for Therapeutic Target and Biomarker Discovery. J Chem Inf Model. 2024;64(10):3961—3969. DOI: 10.1021/acs.jcim.3c01619
Ivanenkov YA, Polykovskiy D, Bezrukov D, et al. Chemistry42: An AI-Driven Platform for Molecular Design and Optimization. J Chem Inf Model. 2023;63(3):695—701. DOI: 10.1021/acs.jcim.2c01191
Lu M, Yin J, Zhu Q, Lin G, Mou M, Liu F, et al. Artificial Intelligence in Pharmaceutical Sciences. Engineering [Internet]. 2023 Aug [cited 2024 Jul 4]; 27: 37—69. Available from: https://linkinghub.elsevier.com/retrieve/pii/S2095809923001649.
Levin JM, Oprea TI, Davidovich S, Clozel T, Overington J, Vanhaelen Q et al. Artificial intelligence, drug repurposing and peer review. Nat Biotechnol. 2020;38(10):1127—1131. DOI: 10.1038/s41587-020-0686-x
RXRX3: Phenomics Map of Biology. Available from: https://www.rxrx.ai/rxrx3 (Accessed: 02th January 2025).
Downloads
Published
Issue
Section
License
Authors retain copyright and grant the journal right of the first publication. The article simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
By submitting the article and accompanying files (hereinafter – the “Work”) the author (all the authors of the work, if it is created in co-authorship) agrees that he provides OAO Izdatelstvo Meditsina exclusive and perpetual right to use the work free of charge (exclusive, perpetual and royalty-free license) on the territory of Russia and foreign countries in the following ranges and volume:
- the publication of works on paper and / or electronic format, producing reprints of works, placing it on the Internet, both in the open and paid access, sending works metadata or full text indexing to various databases and repositories;
- reproduction of the work, i.e. the production of one or more copies of a work or part thereof in any material form, including in the form of audio or video recording. Recording on electronic media, including recording in computer memory, is also considered as a reproduction;
- distribution of works through sale or other alienation of its original or copies;
- public display of the work, that is, any demonstration of the original or copy of a work, either directly or on the screen using film, slide, television pictures or other technical means, as well as a demonstration of individual frames of an audiovisual work without concern for their order, either directly or with the help of technical means in a place open for free visits, or in a place where a significant number of individuals do not belong to the normal family, regardless of the perceived in the place of its display or elsewhere at the same time demonstrating product;
- import-export of the work or its parts for any lawful purpose (paid and gratis);
- translation or other processing of the works;
- bringing the work to the public so that anyone can access the work from any place and at any time of their choice;
- accommodation of works or parts thereof in a variety of collections of similar works;
- granting of rights in full or in part to third (physical and legal) persons at both the paid and free of charge.
Author’s items are not provided. The title is available by subscription.
