Classification of artificial intelligence applications in chemistry: from automation to digital scientific thinking

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

A three-level classification of the application of artificial intelligence (AI) in chemical sciences is proposed, reflecting the increasing degree of involvement of technologies in scientific and production processes: from the automation of routine tasks (AI assistant level) to the creation of specialized analytical solutions for processing experimental data (AI analyst level), and further to the prospect of intelligent systems capable of forming scientific hypotheses and designing substances and processes (AI researcher level). The presented classification can serve as a basis for the formation of roadmaps for the digital transformation of chemical sciences, as well as for the implementation of scientific and technological development programs within priority areas. The term participating technology is introduced for the first time to denote a new form of interaction between humans and AI, in which the digital system becomes part of the scientific process, rather than just a tool.

Full Text

Restricted Access

About the authors

Valentine P. Ananikov

Zelinsky Institute of Organic Chemistry RAS

Author for correspondence.
Email: val@ioc.ac.ru
ORCID iD: 0000-0002-6447-557X

Academician of Russian Academy of Sciences, Dr. Sci.

Russian Federation, Moscow

References

  1. Ananikov V. P. Top 20 Influential AI-Based Technologies in Chemistry. Art. Int. Chem. 2024; 2(2): 100075. https://doi.org/10.1016/j.aichem.2024.100075.
  2. Ding H., Hua P., Huang Z. Survey on Recent Progress of AI for Chemistry: Methods, Applications, and Opportunities. arXiv, 2025; arXiv:2502.17456. https://doi.org/10.48550/arXiv.2502.17456.
  3. Berber S., Brückner M., Maurer N., Huwer J. Artificial Intelligence in Chemistry Research–Implications for Teaching and Learning. J. Chem. Educ. 2025; 102(4): 1445–1456. https://doi.org/10.1021/acs.jchemed.4c01033.
  4. Dabas R. Twenty Ways AI is Advancing Chemistry. Chemistry World, 17 October 2024. 28.05.2025. URL: https://www.chemistryworld.com/news/twenty-ways-ai-is-advancing-chemistry/4020269.article.
  5. Ramos M. C., Collison C. J., White A. D. A Review of Large Language Models and Autonomous Agents in Chemistry. Chem. Sci. 2025; 16:2514–2572. https://doi.org/10.1039/D4SC03921A.
  6. Kumar A., Zavala V. M. Editorial for the AI/ML in Chemical Engineering Special Issue. Ind. Eng. Chem. Res. 2025; 64(19): 9441–9442. https://pubs.acs.org/doi/10.1021/acs.iecr.5c01582.
  7. Romagnoli J. A., Briceño-Mena L., Manee V. AI in Chemical Engineering. Edition 1, CRC Press, Boca Raton, 2024, 308 p. https://doi.org/10.1201/9781003455905.
  8. Caccavale F., Gargalo C. L., Kager J., Larsen S., Gernaey K. V., Krühne U. ChatGMP: A Case of AI Chatbots in Chemical Engineering Education Towards the Automation of Repetitive Tasks. Comput. Educ.: Artif. Intell. 2025; 8: 100354. https://doi.org/10.1016/j.caeai.2024.100354.
  9. Ghasemlou M., Nguyen H. C., Talekar S., Pfeffer F. M., Barrow C. J. Artificial Intelligence (AI) for More Sustainable Chemistry and a Greener Future. ACS Sustain. Chem. Eng. 2025; 13: 3830–3833. https://doi.org/10.1021/acssuschemeng.5c00853.
  10. Artificial Intelligence for Chemical Sciences, ed. Kulkarni S., Bhandari S., Varshney D., William P., Apple Academic Press, New York, 2025. 414 p. https://doi.org/10.1201/9781003569282.
  11. Yuan M., Guo Q., Wang Y. The Current Research Status and Prospects of AI in Chemical Science. Prog. Nat. Sci.: Mater. Int. 2024; 34: 859–872. https://doi.org/10.1016/j.pnsc.2024.08.003.
  12. Vu V.-H., Bui K.-H., Dang K. D. D., Duong-Tuan M., Le D. D., Nguyen-Dang T. Finding Environmental-Friendly Chemical Synthesis with AI and High-Throughput Robotics. J. Sci.: Adv. Mater. Devices. 2025; 10(1): 100818. https://doi.org/10.1016/j.jsamd.2024.100818.
  13. Bienstock R. J. AI/ML Methodologies and the Future-will They be Successful in Designing the Next Generation of New Chemical Entities? J. Cheminform. 2025; 17, 46. https://doi.org/10.1186/s13321-025-00995-5.
  14. Ishida S., Sato T., Honma T., Terayama K. Large Language Models Open New Way of AI-Assisted Molecule Design for Chemists. J. Cheminform. 2025; 17, 36. https://doi.org/10.1186/s13321-025-00984-8.
  15. Han R., Yoon H., Kim G., Lee H., Lee Y. Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery. Pharmaceuticals. 2023; 16(9): 1259. https://doi.org/10.3390/ph16091259.
  16. Liu C., Chen Y., Mo F. Transforming Organic Chemistry Research Paradigms: Moving From Manual Efforts to the intersection of Automation and Artificial Intelligence, arXiv. 2023; arXiv:2312.00808. https://doi.org/10.48550/arXiv.2312.00808.
  17. Boiko D. A., MacKnight R., Kline B., Gomes G. Autonomous Chemical Research with Large Language Models. Nature. 2023; 624: 570–578. https://doi.org/10.1038/s41586-023-06792-0.
  18. Song T., Luo M., Zhang X., Chen L., Huang Y., Cao J. et al. A Multiagent-Driven Robotic AI Chemist Enabling Autonomous Chemical Research on Demand. J. Am. Chem. Soc. 2025; 147(15):12534–12545. https://doi.org/10.1021/jacs.4c17738.
  19. Ma K. AI agents in chemical research: GVIM – an intelligent research assistant system. Digit. Discov. 2025; 4: 355-375. https://doi.org/10.1039/D4DD00398E.
  20. Eremin D. B., Galushko A. S., Boiko D. A., Pentsak E. O., Chistyakov I. V., Ananikov V. P. Toward Totally Defined Nanocatalysis: Deep Learning Reveals the Extraordinary Activity of Single Pd/C Particles. J. Am. Chem. Soc. 2022; 144(13): 6071–6079. https://doi.org/10.1021/jacs.2c01283.
  21. Boiko D. A., Kozlov K. S., Burykina J. V., Ilyushenkova V. V., Ananikov V. P. Fully Automated Unconstrained Analysis of High-Resolution Mass Spectrometry Data with Machine Learning. J. Am. Chem. Soc. 2022; 144(32): 14590–14606. https://doi.org/10.1021/jacs.2c03631.
  22. Kozlov K. S., Boiko D. A., Detusheva E. V., Detushev K. V., Pentsak E. O., Vereshchagin A. N., Ananikov V. P. Digital Biology Approach for Macroscale Studies of Biofilm Growth and Biocide Effects with Electron Microscopy. Dig. Discov. 2023; 2: 1522–1539. https://doi.org/10.1039/D3DD00048F.
  23. Daniel T., Xuan J. Responsible Use of Generative AI in Chemical Engineering. Digit. Chem. Eng. 2024; 12: 100168. https://doi.org/10.1016/j.dche.2024.100168.
  24. Yuan Y., Chaffart D., Wu T., Zhu J. Transparency: The Missing Link to Boosting AI Transformations in Chemical Engineering. Engineering. 2024; 39, 45–60. https://doi.org/10.1016/j.eng.2023.11.024.
  25. Ruff E. F., Zemke J. M. O. Discussing the Ethics of Professional AI Use in Undergraduate Chemistry Courses. J. Chem. Educ. 2025; 102(4): 1457–1464. https://doi.org/10.1021/acs.jchemed.4c01038.
  26. Guo T., Guo K., Nan B., Liang Z., Guo Z., Chawla N. V., Wiest O., Zhang X. What Can Large Language Models Do in Chemistry? A Comprehensive Benchmark on Eight Tasks. arXiv, 2023; arXiv:2305.18365. https://doi.org/10.48550/arXiv.2305.18365.
  27. Zimmermann Y., Bazgir A., Al-Feghali A. et al. 34 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discovery. arXiv, 2025; arXiv:2505.03049. https://doi.org/10.48550/arXiv.2505.03049.
  28. Han Y., Wan Z., Chen L., Yu K., Chen X. From Generalist to Specialist: A Survey of Large Language Models for Chemistry. arXiv, 2024; arXiv:2412.19994. https://doi.org/10.48550/arXiv.2412.19994.
  29. Jablonka K. M., Ai Q., Al-Feghali A. et al. 14 Examples of How LLMs Can Transform Materials Science and Chemistry: a Reflection on a Large Language Model Hackathon. Digit. Discov. 2023; 2: 1233–1250. https://doi.org/10.1039/D3DD00113J.
  30. Tyrin A. S., Boiko D. A., Kolomoets N. I., Ananikov V. P. Digitization of Molecular Complexity with Machine Learning. Chem. Sci. 2025; 16: 6895–6908. https://doi.org/10.1039/D4SC07320G.
  31. Kozlov K. S., Boiko D. A., Burykina J. V., Ilyushenkova V. V., Kostyukovich A.Yu., Patil E. D., Ananikov V. P. Discovering Organic Reactions with a Machine-Learning-Powered Deciphering of Tera-Scale Mass Spectrometry Data. Nat. Commun. 2025; 16: 2587. https://doi.org/10.1038/s41467-025-56905-8.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. The relationship between different scenarios for the digital development of chemistry and the change in the depth of transformation of science and the rate of accumulation of new knowledge depending on the chosen digitalization strategy. Reproduced from the article [1] under the CC BY 4.0 license

Download (576KB)
Indexing metadata
3. Fig. 2. Study of biofilms using SEM: a – the process of preparing data for training the neural network; b – examples of annotated data in different images; c – biofilms of S. aureus ATCC 6538: biofilm obtained after 24 h of incubation on the surface of a solid nutrient medium (left); biofilm after 72 h of incubation (right); d – dynamics of S. aureus biofilm formation with display of statistics by area: cells, matrix, channels and cell-free zones; the results were obtained using a neural network for image segmentation based on the U-Net architecture. Reproduced from the article [22] under the CC BY 3.0 license

Download (761KB)
Indexing metadata
4. Fig. 3. Differences in the approaches of man and nature to the synthesis of complex molecules from the point of view of molecular complexity: a – graph of the dependence of molecular complexity on the synthesis method

Download (373KB)
Indexing metadata
5. Fig. 3. Differences in human and natural approaches to the synthesis of complex molecules in terms of molecular complexity: b – variation in the molecular complexity of chemical compounds; c – comparison of synthetic approaches of humans and nature. Reproduced from article [30] under CC BY 3.0 license

Download (526KB)
Indexing metadata
6. Fig. 4. Integration of an AI researcher in chemistry: historical practice (a) and AI-powered hypothesis generation based on previous experiments (b). Reproduced from [31] under CC BY 4.0 license

Download (637KB)
Indexing metadata

Copyright (c) 2025 Ananikov V.P.