DEVELOPMENT OF A METHOD OF SMART-TECHNOLOGY EFFICIENCY ASSESSMENT FOR PREDICTING MEDICINAL COMPOUNDS PROPERTIES AND ANALYSIS OF DATABASES USING MODERN SOFTWARE

Nowadays, it is promising to develop innovative methods for creating new drugs with desired properties in order to reduce time and financial costs. The search for effective drug compounds is a complex, multi-stage process, in which it is necessary to process a huge amount of chemical data. The application of modern artificial intelligence methods to predict the structure-property dependence of drug compounds is relevant. The article presents the developed Smart-technology for prediction based on modified algorithms of artificial immune systems. Smart-technology effectiveness assessment is carried out using the FMEA (Failure Mode and Effects Analysis) methodology in order to analyze the causes and consequences of defects. An FMEA model has been developed for assessing the risks of the functioning of Smart technology stages. As an example, there are considered medicinal compounds of the sulfanilamide group.

1. Chenye Qiu. A novel multi-swarm particle swarm optimization for feature selection // Genetic programming and evolvable machines. – Springer, 2019. - №20. – P. 503-529.

2. Zheng-Ming Gao, Juan Zhao. An Improved Grey Wolf Optimization Algorithm with Variable Weights // Computational Intelligence and Neuroscience. – 2019. – Vol.1. - №3. – P.1-13.

3. Mohamed Abdel-Basset, Laila A. Shawky. Flower pollination algorithm: a comprehensive review // Artificial Intelligence Review. – 2019. – Vol. 52. – P. 2533-2557.

4. Xi Wang. The Application of Genetic Algorithms in the Biological Medical Diagnostic Research // International journal of BIO automation. – 2016. – Vol.20. - №4. – P. 493 – 504.

5. Ilyes Jenhani, Zied Elouedi. Re-visiting the artificial immune recognition system: a survey and an improved version // Artificial Intelligence Review. – 2014. – Vol. 42. – P. 821–833.

6. David González-Patiño, Yenny Villuendas-Rey, Amadeo José Argüelles-Cruz, Oscar Camacho-Nieto, Cornelio Yáñez-Márquez. AISAC: An Artificial Immune System for Associative Classification Applied to Breast Cancer Detection // Applied science. – 2020. – Vol.10.- №2. – Р. 515.

7. Weiwei Zhang, Kui Gao, Weizheng Zhang, Xiao Wang, Qiuwen Zhang & Hua Wang.A hybrid clonal selection algorithm with modified combinatorial recombination and success-history based adaptive mutation for numerical optimization //A hybrid clonal selection algorithm with modified combinatorial recombination and success-history based adaptive mutation for numerical optimization. – Applied Intelligence, 2018. – Vol.49. – P.819-836.

8. Khulan Batbayar, Márta Takács, Miklos Kozlovszky. Medical device software risk assessment using FMEA and fuzzy linguistic approach: case study // 11th IEEE International Symposium on Applied Computational Intelligence and Informatics. – 2016. – P.197-202.

9. Chiozza M.L., Ponzetti C. FMEA: a model for reducing medical errors // Clinica Chimica Acta; International Journal of Clinical Chemistry. – 2009. – Vol. 404 (1). – P. 75-78.

10. Hirotaka Inoue, Shu Yamada. Failure mode and effects analysis in pharmaceutical research // International Journal of Quality and Service Sciences. – 2010.- Vol. 2(3). – P. 369-382.

11. Samigulina G.A., Samigulina Z.I. Development of multi-agent technology for prediction of the «structure-property» dependence of drugs on the basis of modified algorithms of artificial immune systems // Proceedings of International Work Conference on Bioinformatics and Biomedical Engineering, IWBBIO 2018, April 25-27. –Spain, Granada. – 2018. – P. 1-2.

12. Самигулина Г.А., Самигулина З.И. Информационная система ведения научных исследований для прогнозирования зависимости «структура-свойство» лекарственных соединений на основе модифицированных алгоритмов искусственных иммунных систем // Проблемы информатики. – 2019. – № 3(44). – С. 31-46.