Publications
Talk · AIP conference proceedings · January 1, 2023
Using machine learning algorithms to predict the activity of fullerene nanoparticles
Alisher Ikramov, Bakhtiyor Rasulev, Fatima Аdilova
Abstract
There are several studies indicating the overall positive results of carbon nanoparticles applications in medicine. Fullerene nanoparticles gain an attention of the medical community as fast, effective and low-toxic drug delivery agent of chemical drugs. In this work, we analyzed 169 fullerene nanoparticles and developed several machine learning models to predict their activities against 1107 target proteins. We selected the best model that utilizes Extra Trees Regressor which is achieved R2 of 0.83 and Root-mean-square error of 293.54 on the test set. The model outperformed previously published models both on the train and test sets.
Computational Drug Discovery MethodsFullerene Chemistry and ApplicationsMachine Learning in Materials Sciencefullerene nanoparticlesactivity predictionprotein targets
More by Fatima Adilova
- Graph-based density-variation outlier removal for chronic disease prediction: A leakage-free benchmark and component-wise ablationResults in Engineering · 2026
- Monotonic System Framework for Globally Optimal Structuring of Complex Data2026
- Boosting LLM Adaptation: Superior Stability and Convergence via OLoRA+ Across Diverse NLP BenchmarksInternational Siberian workshops and tutorials on electron devices and materials · 2026
- Генерации графов заданной структуры: от глубоких нейронных сетей к квантовым моделям (на примере создания новых лекарств)Problems of Computational and Applied Mathematics · 2026