Publications
Talk · International Conference on Information Science and Communications Technologies · November 1, 2019
An application of RNN to the inverse-QSAR problem
Alisher Ikramov, Fatima Аdilova
Abstract
RNN model was used in solution of inverse QSAR problem. Authors demonstrate an efficient approach in generating new molecules de nova with desired Activity values. They used SMILES representations of given set and trained a network capable of producing new series of symbols.
Computational Drug Discovery MethodsMachine Learning in Materials ScienceHistory and advancements in chemistryrecurrent neural networksde novo molecule generationSMILES generation
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