PROTEINSYNC: МУЛЬТИАГЕНТНЫЙ ФРЕЙМВОРК ПЛАНИРОВАНИЯ ДЛЯ РАСПРЕДЕЛЁННОГО МОДЕЛИРОВАНИЯ МОЛЕКУЛЯРНОЙ ДИНАМИКИ С АДАПТИВНОЙ ПЕРЕБАЛАНСИРОВКОЙ НАГРУЗКИ
Kalit so'zlar
https://doi.org/10.47390/ts-v4i4y2026N04Kalit so'zlar
молекулярная динамика, мультиагентные системы, распределённые вычисления, балансировка нагрузки, биоинформатика, моделирование белков, MAS, ProteinSync.Annotasiya
На стыке биоинформатики и мультиагентных систем предложен фреймворк ProteinSync для распределённого моделирования молекулярной динамики белков. Агенты-вычислители динамически перераспределяют атомные домены в зависимости от локальной вычислительной нагрузки, снижая время симуляции сворачивания белков на 41% по сравнению с OpenMM [4] при том же аппаратном бюджете.
Manbalar
1. Frenkel D., Smit B. Understanding Molecular Simulation: From Algorithms to Applications. 2nd ed. Academic Press, San Diego, 2002. 638 p.
2. Abraham M.J., Murtola T., Schulz R. et al. GROMACS: High performance molecular simulations through multi-level parallelism from laptops to supercomputers // SoftwareX. 2015. Vol. 1–2. P. 19–25.
3. Phillips J.C., Hardy D.J., Maia J.D.C. et al. Scalable molecular dynamics on CPU and GPU architectures with NAMD // Journal of Chemical Physics. 2020. Vol. 153, No. 4. P. 044130.
4. Eastman P., Swails J., Chodera J.D. et al. OpenMM 7: Rapid development of high performance algorithms for molecular dynamics // PLOS Computational Biology. 2017. Vol. 13, No. 7. e1005659.
5. Kumar S., Bouzida D., Swendsen R.H. et al. The weighted histogram analysis method for free-energy calculations on biomolecules // Journal of Computational Chemistry. 1992. Vol. 13, No. 8. P. 1011–1021.
6. Wooldridge M. An Introduction to Multiagent Systems. 2nd ed. John Wiley & Sons, Chichester, 2009. 484 p.
7. Berger M.J., Bokhari S.H. A partitioning strategy for nonuniform problems on multiprocessors // IEEE Transactions on Computers. 1987. Vol. C-36, No. 5. P. 570–580.
8. Hornak V., Abel R., Okur A. et al. Comparison of multiple AMBER force fields and development of improved protein backbone parameters // Proteins: Structure, Function, and Bioinformatics. 2006. Vol. 65, No. 3. P. 712–725.
9. Kale L., Skeel R., Bhandarkar M. et al. NAMD2: Greater scalability for parallel molecular dynamics // Journal of Computational Physics. 1999. Vol. 151, No. 1. P. 283–312.
10. Jumper J., Evans R., Pritzel A. et al. Highly accurate protein structure prediction with AlphaFold // Nature. 2021. Vol. 596, No. 7873. P. 583–589.
11. Libouban P.-Y., Parisel C., Song M. et al. Spatio-temporal learning from molecular dynamics simulations for protein–ligand binding affinity prediction // Bioinformatics. 2025. Vol. 41, No. 8. Article btaf429.
12. Plainer M., Wu H., Klein L. et al. Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models // arXiv:2506.17139. 2025/2026.
13. Wen J., Li X., Yao J. et al. Adaptive-expert-weight-based load balance scheme for dynamic routing of MoE // Frontiers in Neurorobotics. 2025. Vol. 19. Article 1590994.
14. Ahmed I., Syed M.A., Maaruf M., Khalid M. Distributed computing in multi-agent systems: a survey of decentralized machine learning approaches // Computing (Springer). 2025. Vol. 107. Article 2.
15. Rahimov E., Aghayev T. Predictive Load Balancing in Distributed Systems: A Comparative Study // Engineering Proceedings (MDPI). 2026. Vol. 122, Issue 1.
16. Li J., Zhang B., Li M. et al. Scaling Neural-Network-Based Molecular Dynamics with Long-Range Electrostatic Interactions to 51 Nanoseconds per Day // arXiv:2504.15508. 2025.
17. Stavrogiannis C., Sofos F., Karakasidis T.E. Machine Learning-Enhanced Molecular Dynamics: Current State, Challenges and Perspectives // Archives of Computational Methods in Engineering. 2026.
18. Jung J., Tan C., Sugita Y. GENESIS CGDYN: large-scale coarse-grained MD simulation with dynamic load balancing for heterogeneous biomolecular systems // Nature Communications. 2024. Article 3370.
This work is licensed under a 