Application оf Machine Learning in Physicochemistry of Active Substances
УДК 544.169
Abstract
The paper presents the latest advances in machine learning for solving pressing problems in the physicochemistry of active substances. It discusses how data mining and neural network models help overcome the limitations of traditional methods. It reviews systems capable of detecting unknown reactions in archived mass spectrometry data (MEDUSA), predicting molecular structures from mass spectra (Spec2Mol), and generating spectra for new compounds, thereby addressing the shortage of reference samples. In quantum chemistry, the success of hybrid methods (AIQM1) is demonstrated. These methods combine quantum mechanical calculations with neural networks to achieve high accuracy while significantly reducing computational costs. The application of machine learning in materials science for the automatic analysis of microscopic images to study defects and the organization of nanoparticles is also discussed. In the context of organic synthesis and drug design, approaches using machine learning to predict the biological activity of molecules (MI-QSAR) and the yields of chemical reactions (Yield-BERT) are presented. In conclusion, it is emphasized that machine learning is a powerful tool that complements classical approaches and accelerates scientific discoveries.
Downloads
References
Beck A.G., Muhoberac M., Randolph C.E., et al. Recent Developments in Machine Learning for Mass Spectrometry // ACS Measurement Science Au. 2024. Vol. 4. No 3. P. 233-246. https://doi.org/10.1021/acsmeasuresciau.3c00060
Исаева Е.Р., Кокова Э.А., Смущенко Н.А. Искусственный интеллект в науке: новые методы исследований и автоматизации научного процесса // Развитие науки в XXI веке: научно-методические и практические аспекты : сборник научных трудов по материалам XXI Международной научно-практической конференции (г.к. Анапа, 03 января 2025 г.). Анапа: НИЦ ЭСП в ЮФО. 2025. C. 28-32.
Плеханов В.И. Искусственный интеллект как инструмент решения задач материаловедения // Актуальные вопросы науки 2025 : сборник статей XI Международной научно-практической конференции. Пенза: МЦНС «Наука и Просвещение». 2025. С. 34-37.
Kozlov K.S., Boiko D.A., Burykina J.V., et al. Discovering Organic Reactions with a Machine-Learning-Powered Deciphering of Tera-Scale Mass Spectrometry Data // Nature Communications. 2025. Vol. 16. No 1. P. 2587. https://doi.org/10.1038/s41467-025-56905-8
Litsa E.E., Chenthamarakshan V., Das P., et al. An End-To-End Deep Learning Framework for Translating Mass Spectra to De-Novo Molecules // Communications Chemistry. 2023. Vol. 6. No 1. P. 132. https://doi.org/10.1038/s42004-023-00932-3
Peters-Clarke T.M., Coon J.J., Riley N.M. Instrumentation at the Leading Edge of Proteomics // Analytical Chemistry. 2024. Vol. 96. No 20. P. 7976-8010. https://doi.org/10.1021/acs. analchem.3c04497
Wang F., Pasin D., Skinnider M.A., et al. Deep Learning-Enabled MS/MS Spectrum Prediction Facilitates Automated Identification of Novel Psychoactive Substances // Analytical Chemistry. 2023. Vol. 95. No 50. P. 18326-18334. https://doi.org/10.1021/acs.analchem.3c02413
Zheng P., Zubatyuk R., WuW., et al. Artificial Intelligence-Enhanced Quantum Chemical Method with Broad Applicability // Nature Communications. 2021. Vol. 12. No 1. P. 7022. https://doi.org/10.1038/s41467-021-27340-2
Ramabhadran R.O., Raghavachari K. Extrapolation to the Gold-Standard in Quantum Chemistry: Computationally Efficient and Accurate CCSD(T) Energies for Large Molecules Using an Automated Thermochemical Hierarchy // Journal of Chemical Theory and Computation. 2013. Vol. 9. No 9. P. 3986-3994. https://doi.org/10.1021/ct400465q
Boiko D.A., Pentsak E.O., Cherepanova V.A., et al. Electron Microscopy Dataset for the Recognition of Nanoscale Ordering Effects and Location of Nanoparticles // Scientific Data. 2020. Vol. 7. No 1. P. 101. https://doi.org/10.1038/s41597-020-0439-1
Boiko D.A., Pentsak E.O., Cherepanova V.A. ,et al. Deep Neural Network Analysis of Nanoparticle Ordering to Identify Defects in Layered Carbon Materials // Chemical Science. 2021. Vol. 12. No 21. P. 7428-7441. https://doi.org/10.1039/ d0sc05696k
Copyright (c) 2026 Михаил Андреевич Зарудских, Александр Сергеевич Безносюк
This work is licensed under a Creative Commons Attribution 4.0 International License.
Izvestiya of Altai State University is a golden publisher, as we allow self-archiving, but most importantly we are fully transparent about your rights.
Authors may present and discuss their findings ahead of publication: at biological or scientific conferences, on preprint servers, in public databases, and in blogs, wikis, tweets, and other informal communication channels.
Izvestiya of Altai State University allows authors to deposit manuscripts (currently under review or those for intended submission to Izvestiya of Altai State University) in non-commercial, pre-print servers such as ArXiv.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0) 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).
