RNRamil I. Nugmanov

Ramil I. Nugmanov

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ramil I. Nugmanov has a total of 134 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Pretraining graph transformers with atom-in-a-molecule quantum properties for improved ADMET modeling

    by Alessio Fallani, Ramil Nugmanov, Jose Arjona-Medina, Jörg Kurt Wegner, Alexandre Tkatchenko, Kostiantyn Chernichenko

    We evaluate the impact of pretraining Graph Transformer architectures on atom-level quantum-mechanical features for the modeling of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of drug-like compounds. We compare this pretraining strategy with two others: one based on molecular quantum properties (specifically the HOMO-LUMO gap) and one using a self-supervised atom masking technique. After fine-tuning on Therapeutic Data Commons ADMET datasets, we evaluate the performance improvement in the different models observing that models pretrained with atomic quantum mechanical properties produce in general better results. We then analyze the latent representations and observe that the supervised strategies preserve the pretraining information after fine-tuning and that different pretrainings produce different trends in latent expressivity across layers. Furthermore, we find that models pretrained on atomic quantum mechanical properties capture more low-frequency Laplacian eigenmodes of the input graph via the attention weights and produce better representations of atomic environments within the molecule. Application of the analysis to a much larger non-public dataset for microsomal clearance illustrates generalizability of the studied indicators. In this case the performances of the models are in accordance with the representation analysis and highlight, especially for the case of masking pretraining and atom-level quantum property pretraining, how model types with similar performance on public benchmarks can have different performances on large scale pharmaceutical data. Scientific contribution We systematically compared three different data type/methodologies for pretraining molecular Graphormer with the purpose of modeling ADMET properties as downstream tasks. The learned representations from differently pretrained models were analyzed in addition to comparison of downstream task performances that have been typically reported in similar works. Such examination methodologies, including a newly introduced analysis of Graphormer’s Attention Rollout Matrix, can guide pretraining strategy selection, as corroborated by a performance evaluation on a larger internal dataset.


  • Open Access

    Pretraining Graph Transformers with Atom-in-a-Molecule Quantum Properties for Improved ADMET Modeling

    by Alessio Fallani, Ramil Nugmanov, Jose Arjona-Medina, Jörg Kurt Wegner, Alexandre Tkatchenko, Kostiantyn Chernichenko

    We evaluate the impact of pretraining Graph Transformer architectures on atom-level quantum-mechanical features for the modeling of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of drug-like compounds. We compare this pretraining strategy with two others: one based on molecular quantum properties (specifically the HOMO-LUMO gap) and one using a self-supervised atom masking technique. After fine-tuning on Therapeutic Data Commons ADMET datasets, we evaluate the performance improvement in the different models observing that models pretrained with atomic quantum mechanical properties produce in general better results. We then analyse the latent representations and observe that the supervised strategies preserve the pretraining information after finetuning and that different pretrainings produce different trends in latent expressivity across layers. Furthermore, we find that models pretrained on atomic quantum mechanical properties capture more low-frequency laplacian eigenmodes of the input graph via the attention weights and produce better representations of atomic environments within the molecule. Application of the analysis to a much larger non-public dataset for microsomal clearance illustrates generalizability of the studied indicators. In this case the performances of the models are in accordance with the representation analysis and highlight, especially for the case of masking pretraining and atom-level quantum property pretraining, how model types with similar performance on public benchmarks can have different performances on large scale pharmaceutical data.

  • PaCh (Packed Chemicals): Computationally Effective Binary Format for Chemical Structure Encoding

    by Ramil Nugmanov

    In this work, we propose a versatile molecule and reaction encoding binary data format that aims to bridge the gap between the advantages of SMILES, like local stereo- and implicit hydrogen encoding, and block-structured MDL MOL with a 2D layout and explicit bond encoding, while addressing their respective limitations. Our new format introduces a balance between size efficiency, processing speed, and comprehensive representation, making it well-suited for various applications in cheminformatics, including deep learning, data storage, and searching. By offering an explicit approach to store atom connectivity (including implicit hydrogens), electronic state, stereochemistry, and other crucial molecular attributes, our proposal seeks to enhance data storage efficiency and promote interoperability among different software tools.


  • Open Access

    ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models

    by Aline Hartgers, Ramil Nugmanov, Kostiantyn Chernichenko, Joerg Kurt Wegner

    Chemical reactivity models are developed to predict chemical reaction outcomes in the form of classification (success/failure) or regression (product yield) tasks. The vast majority of the reported models are trained solely on chemical information such as reactants, products, reagents, and solvents, but not on the details of a synthetic protocol. Herein incorporation of procedural text with the aim to augment the Graphormer reactivity model and improve its accuracy is presented. Two major approaches are used: training an adapter Graphormer model that is provided with a GPT-2-derived latent representation of the text procedure (ReacLLaMA-Adapter) and labeling an unlabeled part of a dataset with the LLaMA 2 model followed by training the Graphormer on an extended dataset (Zero-Shot Labeling ReacLLaMA). Both methodologies enhance the discernment of unpromising reactions, thereby providing more accurate models with improved specificity.


  • Open Access

    Oxyethylated Fluoresceine—(thia)calix[4]arene Conjugates: Synthesis and Visible-Light Photoredox Catalysis in Water–Organic Media

    by Vladimir Burilov, Aigul Fatykhova, Diana Mironova, Elza Sultanova, Ramil Nugmanov, Alina Artemenko, Anastasia Volodina, Amina Daminova, Vladimir Evtugyn, Svetlana Solovieva, et al.

    Fluorescent derivatives attract the attention of researchers for their use as sensors, photocatalysts and for the creation of functional materials. In order to create amphiphilic fluorescent derivatives of calixarenes, a fluorescein derivative containing oligoethylene glycol and propargyl groups was obtained. The resulting fluorescein derivative was introduced into three different (thia)calix[4]arene azide derivatives. For all synthesized compounds, the luminescence quantum yields have been established in different solvents. Using UV-visible spectroscopy, dynamic light scattering, as well as transmission and confocal microscopy, aggregation of macrocycles was studied. It was evaluated that calixarene derivatives with alkyl substituents form spherical aggregates, while symmetrical tetrafluorescein-containing thiacalix[4]arene forms extended worm-like aggregates. The macrocycle containing tetradecyl fragments was found to be the most efficient in photoredox ipso-oxidation of phenylboronic acid. In addition, it was shown that in a number of different electron donors (NEt3, DABCO and iPr2EtN), the photoredox ipso-oxidation proceeds best with triethylamine. It has been shown that a low molecular weight surfactant Triton-X100 can also improve the photocatalytic abilities of an oligoethylene glycol fluorescein derivative, thus showing the importance of a combination of micellar and photoredox catalysis.


  • Bidirectional Graphormer for Reactivity Understanding: Neural Network Trained to Reaction Atom-to-Atom Mapping Task

    by Ramil Nugmanov, Natalia Dyubankova, Andrey Gedich, Joerg Kurt Wegner

    This work introduces GraphormerMapper, a new algorithm for reaction atom-to-atom mapping (AAM) based on a transformer neural network adopted for the direct processing of molecular graphs as sets of atoms and bonds, as opposed to SMILES/SELFIES sequence-based approaches, in combination with the Bidirectional Encoder Representations from Transformers (BERT) network. The graph transformer serves to extract molecular features that are tied to atoms and bonds. The BERT network is used for chemical transformation learning. In a benchmarking study with IBM RxnMapper, which is the best AAM algorithm according to our previous study, we demonstrate that our AAM algorithm is superior to it on our "Golden" benchmarking data set.


  • Open Access

    Bidirectional Graphormer for Reactivity Understanding: neural network trained to reaction atom-to-atom mapping task

    by Ramil Nugmanov, Natalia Dyubankova, Andrey Gedich, Joerg Kurt Wegner

    This work introduces GraphormerMapper – a new algorithm for reactions atom-to-atom mapping (AAM) based on a distance-aware BERT neural network. In benchmarking studies with IBM RxnMapper, the best AAM algorithm according to our previous study, we demonstrate that our AAM algorithm is superior on our “Golden” benchmarking dataset. The mapper is implemented in Chython [https://github.com/chython/chython] and Chytorch [https://github.com/chython/chytorch, https://github.com/chython/chytorch-rxnmap] Python packages which are freely available for out-the-box use. Chython is a cheminformatics library with a simple interface for processing reaction and molecular data. The key features of Chython are: chemical functional groups standardization, checking atom valence errors, substructure search, and advanced reaction manipulation, for example, generating products from reactants and reaction atom-to-atom mapping. Chytorch provides a PyTorch-like interface for graph-based neural networks developed specifically for chemical tasks.

  • Open Access

    Prediction of Optimal Conditions of Hydrogenation Reaction Using the Likelihood Ranking Approach

    by Valentina A. Afonina, Daniyar A. Mazitov, Albina Nurmukhametova, Maxim D. Shevelev, Dina A. Khasanova, Ramil I. Nugmanov, Vladimir A. Burilov, Timur I. Madzhidov, Alexandre Varnek

    The selection of experimental conditions leading to a reasonable yield is an important and essential element for the automated development of a synthesis plan and the subsequent synthesis of the target compound. The classical QSPR approach, requiring one-to-one correspondence between chemical structure and a target property, can be used for optimal reaction conditions prediction only on a limited scale when only one condition component (e.g., catalyst or solvent) is considered. However, a particular reaction can proceed under several different conditions. In this paper, we describe the Likelihood Ranking Model representing an artificial neural network that outputs a list of different conditions ranked according to their suitability to a given chemical transformation. Benchmarking calculations demonstrated that our model outperformed some popular approaches to the theoretical assessment of reaction conditions, such as k Nearest Neighbors, and a recurrent artificial neural network performance prediction of condition components (reagents, solvents, catalysts, and temperature). The ability of the Likelihood Ranking model trained on a hydrogenation reactions dataset, (~42,000 reactions) from Reaxys® database, to propose conditions that led to the desired product was validated experimentally on a set of three reactions with rich selectivity issues.


  • CGRdb2.0: A Python Database Management System for Molecules, Reactions, and Chemical Data

    by Timur Gimadiev, Ramil Nugmanov, Aigul Khakimova, Adeliya Fatykhova, Timur Madzhidov, Pavel Sidorov, Alexandre Varnek

    This work introduces CGRdb2.0─an open-source database management system for molecules, reactions, and chemical data. CGRdb2.0 is a Python package connecting to a PostgreSQL database that enables native searches for molecules and reactions without complicated SQL syntax. The library provides out-of-the-box implementations for similarity and substructure searches for molecules, as well as similarity and substructure searches for reactions in two ways─based on reaction components and based on the Condensed Graph of Reaction approach, the latter significantly accelerating the performance. In benchmarking studies with the RDKit database cartridge, we demonstrate that CGRdb2.0 performs searches faster for smaller data sets, while allowing for interactive access to the retrieved data.


  • QSAR Modeling Based on Conformation Ensembles Using a Multi-Instance Learning Approach

    by Dmitry V. Zankov, Mariia Matveieva, Aleksandra V. Nikonenko, Ramil I. Nugmanov, Igor I. Baskin, Alexandre Varnek, Pavel Polishchuk, Timur I. Madzhidov

    Modern QSAR approaches have wide practical applications in drug discovery for designing potentially bioactive molecules. If such models are based on the use of 2D descriptors, important information contained in the spatial structures of molecules is lost. The major problem in constructing models using 3D descriptors is the choice of a putative bioactive conformation, which affects the predictive performance. The multi-instance (MI) learning approach considering multiple conformations in model training could be a reasonable solution to the above problem. In this study, we implemented several multi-instance algorithms, both conventional and based on deep learning, and investigated their performance. We compared the performance of MI-QSAR models with those based on the classical single-instance QSAR (SI-QSAR) approach in which each molecule is encoded by either 2D descriptors computed for the corresponding molecular graph or 3D descriptors issued for a single lowest energy conformation. The calculations were carried out on 175 data sets extracted from the ChEMBL23 database. It is demonstrated that (i) MI-QSAR outperforms SI-QSAR in numerous cases and (ii) MI algorithms can automatically identify plausible bioactive conformations.