SUN’IY INTELLEKT ASOSIDA ORGANIK SINTEZ JARAYONLARINI PROGNOZLASH VA OPTIMALLASHTIRISH ISTIQBOLLARI
Xayrulloyev R. U.
Annotatsiya
Organik sintez zamonaviy kimyo, farmatsevtika, materialshunoslik va ekologik texnologiyalar rivojining asosiy yo‘nalishlaridan biridir. Biroq murakkab molekulalarni sintez qilish ko‘p bosqichli, resurs va vaqt talab qiluvchi jarayon bo‘lib, samarali natijaga erishish ko‘pincha tajribaviy yo‘l bilan amalga oshiriladi. Ushbu maqolada sun’iy intellekt (SI) texnologiyalarining organik sintez jarayonlarini prognozlash, reaksiyalar samaradorligini oshirish va yangi moddalarning sintez yo‘llarini optimallashtirishdagi imkoniyatlari tahlil qilinadi. Maqolada xalqaro tajribalar, xususan MIT, Stanford, DeepMind hamda Cornell universitetlarining ilg‘or ishlanmalari tahlil qilinib, ularning O‘zbekiston ilmiy-amaliy muhitida qo‘llanish istiqbollari muhokama etiladi. Shuningdek, kimyo sanoatini raqamli transformatsiya qilishda ma’lumotlarga asoslangan (“data-driven”) yondashuvlarning afzalliklari va ularni joriy etishning ilmiy asoslari keltiriladi.
Adabiyotlar
- Aspuru-Guzik, A., Sanchez-Lengeling, B., & de Almeida, A. F. (2018). Artificial Intelligence and the discovery of new molecules. Nature Reviews Chemistry, 2(10), 347–358.
- Lowe, D. (2017). Chemical reactions from US patents (1976–2016). Harvard Dataverse. https://dataverse.harvard.edu/
- Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017). Neural message passing for quantum chemistry. Proceedings of the 34th International Conference on Machine Learning (ICML).
- Schwaller, P., et al. (2019). Molecular Transformer: A model for uncertainty-calibrated chemical reaction prediction. ACS Central Science, 5(9), 1572–1583.
- Coley, C. W., Jin, W., Rogers, L., & Barzilay, R. (2020). Chemma: Machine learning for reaction optimization. Journal of Chemical Information and Modeling, 60(10), 4358–4373.
- Segler, M. H. S., Preuss, M., & Waller, M. P. (2018). Planning chemical syntheses with deep neural networks and symbolic AI. Nature, 555(7698), 604–610.
- IBM Research (2021). RXN for Chemistry Project Overview. IBM Research Europe. https://rxn.res.ibm.com
- Anastas, P. T., & Zimmerman, J. B. (2018). The 12 principles of green engineering as a basis for sustainable design. Green Chemistry, 20(2), 342–358.
- MIT Chemistry AI Lab (2021). Deep Reaction Predictor: Data-driven synthesis optimization. Massachusetts Institute of Technology.
- RSC (2022). Green Chemistry Metrics Platform. Royal Society of Chemistry. https://www.rsc.org/journals/green-chemistry
- Jin, W., Coley, C. W., & Barzilay, R. (2020). Predicting organic reaction outcomes with machine learning. Accounts of Chemical Research, 53(2), 287–298.
- O‘zbekiston Respublikasi Innovatsion rivojlanish agentligi (2023). Kimyo sanoatini raqamlashtirish konsepsiyasi. Toshkent: Ilmiy nashr.
- O‘zbekiston Fanlar akademiyasi Kimyo instituti (2024). Organik sintezda sun’iy intellekt texnologiyalarining istiqbollari bo‘yicha hisobot. Toshkent