About

I work where deep learning meets cheminformatics, teaching models to understand molecules and chemical reactions. I build chython, my open-source Python library for working with molecules and reactions. I’m currently exploring AI agents for chemistry, including lab robots with agents in the loop.

Experience

2025 – now
Senior Principal Scientist
Johnson & Johnson Innovative Medicine
2021 – 2025
Principal Scientist
Johnson & Johnson Innovative Medicine
2019 – 2021
Associate Professor of Chemistry (part-time)
Kazan Federal University
2014 – 2021
Senior Researcher
Kazan Federal University

Education

2011 – 2014
PhD, Organic Chemistry
A.E. Arbuzov Institute of Organic and Physical Chemistry, Russian Academy of Sciences
2012 – 2014
MSc, Chemoinformatics and Molecular Modeling
Kazan State University
2006 – 2011
MSc, Organic Chemistry
Kazan State University

Selected publications

2025
Pretraining graph transformers with atom-in-a-molecule quantum properties for improved ADMET modeling
Fallani A., Nugmanov R., et al. · Journal of Cheminformatics
2025
Benchmarking molecular conformer augmentation with context-enriched training: graph-based transformer versus GNN models
Valsecchi C., Arjona-Medina J. A., Dyubankova N., Nugmanov R. · Journal of Cheminformatics
2024
PaCh (Packed Chemicals): computationally effective binary format for chemical structure encoding
Nugmanov R. · J. Chem. Inf. Model.
2024
ReacLLaMA: merging chemical and textual information in chemical reactivity AI models
Hartgers A., Nugmanov R., et al. · arXiv
2023
Global reactivity models are impactful in industrial synthesis applications
Neves P., McClure K., Verhoeven J., Dyubankova N., Nugmanov R., et al. · Journal of Cheminformatics
2022
Bidirectional Graphormer for reactivity understanding: neural network trained to reaction atom-to-atom mapping task
Nugmanov R., Dyubankova N., Gedich A., Wegner J. K. · J. Chem. Inf. Model.
2022
Atom-to-atom mapping: a benchmarking study of popular mapping algorithms and consensus strategies
Lin A., Dyubankova N., Madzhidov T., Nugmanov R., et al. · Molecular Informatics
2021
Discovery of novel chemical reactions by deep generative recurrent neural network
Bort W., Baskin I., Gimadiev T., Mukanov A., Nugmanov R., et al. · Scientific Reports
2019
CGRtools: Python library for molecule, reaction, and condensed graph of reaction processing
Nugmanov R., Mukhametgaleev R., Akhmetshin T., et al. · J. Chem. Inf. Model.
Full list on Google Scholar →