IAIslambek Ashyrmamatov

Islambek Ashyrmamatov

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Islambek Ashyrmamatov has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Synthesis-Aware Molecular Generation via Reaction-Driven Global Search

    by Islambek Ashyrmamatov, Umit V. Ucak, Juyong Lee

    Synthesizability remains a central challenge in de novo molecular generation. Conventional goal-directed molecular optimization methods, where molecules are generated by optimizing target properties often suffer from low synthetic accessibility. Existing strategies typically address this gap through post hoc filtering or by restricting generation to predefined reaction schemes. The former decouples synthesis from optimization, whereas the latter improves feasibility at the cost of restricting molecular exploration. We present RxnMol, a synthesis-aware molecular optimization framework in which each candidate is encoded as a synthetic-route representation: an ordered sequence of readily available molecular building blocks. A pretrained reaction prediction model converts these building blocks into a product molecule through sequential reaction prediction, while a population-based global optimization algorithm modifies the route representation and evaluates the resulting molecule against the target objective. Thus, molecular optimization operates on synthetic routes rather than solely on final molecular structures. Each selected molecule is obtained from the optimized route representation by RxnMol; therefore, the improved objective values remain directly tied to the corresponding synthetic routes predicted by the model. Across protein target and bioactivity optimization tasks, RxnMol improves Top-1 performance on both generative baselines that optimize molecular structures directly and template-based synthesis-constrained methods in most benchmarks. Together, these results show that de novo molecular design can be formulated as route optimization, where reaction prediction translates route representations into product molecules for objective evaluation.

  • Open Access

    RxnMol: synthesis-aware molecular generation via reaction-driven global chemical space search

    by Islambek Ashyrmamatov, Umit V. Ucak, Juyong Lee

    RxnMol couples global chemical space search with sequential forward-reaction prediction to optimize molecular properties while constructing proposed synthetic routes from purchasable building blocks.

  • Open Access

    Refining EI-MS library search results through atomic-level insights

    by Islambek Ashyrmamatov, Umit V. Ucak, Juyong Lee

    The inherent complexity of mass spectra and the lack of direct correlation between spectral and structural similarities retards structure elucidation and accurate peak annotation. Our methodology employs modified atomic environments from topological radii zero to represent collections of annotated spectral peaks. Rather than aiming for de novo structure prediction from spectra, our objective is to refine and re-rank candidate structures retrieved by existing library search methods using predicted atom environments. We conducted a multi-step complexity reduction to mass-to-fragment mappings and trained the Transformer model to predict the atomic environments of compounds directly from mass and intensity data, achieving a peak precision of 86.1% and a recall rate of 78.4% on the test set. This novel framework not only aids in interpreting EI-MS data by providing insights into structural contents but also refines cosine similarity rankings by suggesting the inclusion or exclusion of certain atomic environments. Our findings over the NIST database suggest that our approach complements conventional methods by improving spectra matching through an in-depth atomic-level analysis.


  • Open Access

    Automated and Efficient Sampling of Chemical Reaction Space

    by Minhyeok Lee, Umit V. Ucak, Jinyoung Jeong, Islambek Ashyrmamatov, Juyong Lee, Eunji Sim

    Machine learning interatomic potentials (MLIPs) promise quantum‐level accuracy at classical force field speeds, but their performance hinges on the quality and diversity of training data. An efficient and fully automated approach to sample chemical reaction space without relying on human intuition, addressing a critical gap in MLIP development is presented. The method combines the speed of tight‐binding calculations with selective high‐level refinement, generating diverse datasets that capture both equilibrium and reactive regions of potential energy surfaces. By employing single‐ended growing string and nudged elastic band methods, reaction pathways previously underrepresented in MLIP training sets, particularly near transition states are systematically explored. This approach yields datasets with rich structural and chemical diversity, essential for robust MLIP development. Open‐source code is provided for the entire workflow, facilitating the integration of the approach into existing MLIP development pipelines.


  • Open Access

    Retrosynthetic reaction pathway prediction through neural machine translation of atomic environments

    by Umit V. Ucak, Islambek Ashyrmamatov, Junsu Ko, Juyong Lee

    Designing efficient synthetic routes for a target molecule remains a major challenge in organic synthesis. Atom environments are ideal, stand-alone, chemically meaningful building blocks providing a high-resolution molecular representation. Our approach mimics chemical reasoning, and predicts reactant candidates by learning the changes of atom environments associated with the chemical reaction. Through careful inspection of reactant candidates, we demonstrate atom environments as promising descriptors for studying reaction route prediction and discovery. Here, we present a new single-step retrosynthesis prediction method, viz. RetroTRAE, being free from all SMILES-based translation issues, yields a top-1 accuracy of 58.3% on the USPTO test dataset, and top-1 accuracy reaches to 61.6% with the inclusion of highly similar analogs, outperforming other state-of-the-art neural machine translation-based methods. Our methodology introduces a novel scheme for fragmental and topological descriptors to be used as natural inputs for retrosynthetic prediction tasks.